膝关节超分辨率重建（包括自监督技术）的技术演进

To develop a super‐resolution technique using convolutional neural networks for generating thin‐slice knee MR images from thicker input slices, and compare this method with alternative through‐plane interpolation methods.

PURPOSE To investigate the potential of combining Compressed Sensing (CS) and a newly developed AI-based super resolution reconstruction prototype consisting of a series of convolutional neural networks (CNN) for a complete five-minute 2D knee MRI protocol. METHODS In this prospective study, 20 volunteers were examined using a 3T-MRI-scanner (Ingenia Elition X, Philips). Similar to clinical practice, the protocol consists of a fat-saturated 2D-proton-density-sequence in coronal, sagittal and transversal orientation as well as a sagittal T1-weighted sequence. The sequences were acquired with two different resolutions (standard and low resolution) and the raw data reconstructed with two different reconstruction algorithms: a conventional Compressed SENSE (CS) and a new CNN-based algorithm for denoising and subsequently to interpolate and therewith increase the sharpness of the image (CS-SuperRes). Subjective image quality was evaluated by two blinded radiologists reviewing 8 criteria on a 5-point Likert scale and signal-to-noise ratio calculated as an objective parameter. RESULTS The protocol reconstructed with CS-SuperRes received higher ratings than the time-equivalent CS reconstructions, statistically significant especially for low resolution acquisitions (e.g., overall image impression: 4.3 ± 0.4 vs. 3.4 ± 0.4, p < 0.05). CS-SuperRes reconstructions for the low resolution acquisition were comparable to traditional CS reconstructions with standard resolution for all parameters, achieving a scan time reduction from 11:01 min to 4:46 min (57 %) for the complete protocol (e.g. overall image impression: 4.3 ± 0.4 vs. 4.0 ± 0.5, p < 0.05). CONCLUSION The newly-developed AI-based reconstruction algorithm CS-SuperRes allows to reduce scan time by 57% while maintaining unchanged image quality compared to the conventional CS reconstruction.

BACKGROUND AND OBJECTIVE With the rapid development of medical imaging and intelligent diagnosis, artificial intelligence methods have become a research hotspot of radiography processing technology in recent years. The low definition of knee magnetic resonance image texture seriously affects the diagnosis of knee osteoarthritis. This paper presents a super-resolution reconstruction method to address this problem. METHODS In this paper, we propose an efficient medical image super-resolution (EMISR) method, in which we mainly adopted three hidden layers of super-resolution convolution neural network (SRCNN) and a sub-pixel convolution layer of efficient sub-pixel convolution neural network (ESPCN). The addition of the efficient sub-pixel convolutional layer in the hidden layer and the small network replacement consisting of concatenated convolutions to address low-resolution images but not high-resolution images are important. The EMISR method also uses cascaded small convolution kernels to improve reconstruction speed and deepen the convolution neural network to improve reconstruction quality. RESULTS The proposed method is tested in the public dataset IDI, and the reconstruction quality of the algorithm is higher than that of the sparse coding-based network (SCN) method, the SRCNN method, and the ESPCN method (+ 2.306 dB, + 2.540 dB, + 1.089 dB improved); moreover, the reconstruction speed is faster than its counterparts (+ 4.272 s, + 1.967 s, and + 0.073 s improved). CONCLUSION The experimental results show that our EMISR framework has improved performance and greatly reduces the number of parameters and training time. Furthermore, the reconstructed image presents more details, and the edges are more complete. Therefore, the EMISR technique provides a more powerful medical analysis in knee osteoarthritis examinations.

Background Deep learning (DL) methods can improve accelerated MRI but require validation against an independent reference standard to ensure robustness and accuracy. Purpose To validate the diagnostic performance of twofold-simultaneous-multislice (SMSx2) twofold-parallel-imaging (PIx2)-accelerated DL superresolution MRI in the knee against conventional SMSx2-PIx2-accelerated MRI using arthroscopy as the reference standard. Materials and Methods Adults with painful knee conditions were prospectively enrolled from December 2021 to October 2022. Participants underwent fourfold SMSx2-PIx2-accelerated standard-of-care and investigational DL superresolution MRI at 3 T. Seven radiologists independently evaluated the MRI examinations for overall image quality (using Likert scale scores: 1, very bad, to 5, very good) and the presence or absence of meniscus and ligament tears. Articular cartilage was categorized as intact, or partial or full-thickness defects. Statistical analyses included interreader agreements (Cohen κ and Gwet AC2) and diagnostic performance testing used area under the receiver operating characteristic curve (AUC) values. Results A total of 116 adults (mean age, 45 years ± 15 [SD]; 74 men) who underwent arthroscopic surgery within 38 days ± 22 were evaluated. Overall image quality was better for DL superresolution MRI (median Likert score, 5; range, 3-5) than conventional MRI (median Likert score, 4; range, 3-5) (P < .001). Diagnostic performances of conventional versus DL superresolution MRI were similar for medial meniscus tears (AUC, 0.94 [95% CI: 0.89, 0.97] vs 0.94 [95% CI: 0.90, 0.98], respectively; P > .99), lateral meniscus tears (AUC, 0.85 [95% CI: 0.78, 0.91] vs 0.87 [95% CI: 0.81, 0.94], respectively; P = .96), and anterior cruciate ligament tears (AUC, 0.98 [95% CI: 0.93, >0.99] vs 0.98 [95% CI: 0.93, >0.99], respectively; P > .99). DL superresolution MRI (AUC, 0.78; 95% CI: 0.75, 0.81) had higher diagnostic performance than conventional MRI (AUC, 0.71; 95% CI: 0.67, 0.74; P = .002) for articular cartilage lesions. DL superresolution MRI did not introduce hallucinations or erroneously omit abnormalities. Conclusion Compared with conventional SMSx2-PIx2-accelerated MRI, fourfold SMSx2-PIx2-accelerated DL superresolution MRI in the knee provided better image quality, similar performance for detecting meniscus and ligament tears, and improved performance for depicting articular cartilage lesions. © RSNA, 2025 Supplemental material is available for this article. See also the editorial by Nevalainen in this issue.

… knee magnetic resonance imaging super-resolution. First, we aggregate multi-scale patch embedding from the multi-contrast knee … sparse attention of the knee MR image, which can …

To assess the accuracy of deep learning reconstruction (DLR) technique on synthetic MRI (SyMRI) including T2 measurements and diagnostic performance of DLR synthetic MRI (SyMRIDL) in patients with knee osteoarthritis (KOA) using conventional MRI as standard reference. This prospective study recruited 36 volunteers and 70 patients with suspected KOA from May to October 2023. DLR and non-DLR synthetic T2 measurements (T2-SyMRIDL, T2-SyMRI) for phantom and in vivo knee cartilage were compared with multi-echo fast-spin-echo (MESE) sequence acquired standard T2 values (T2MESE). The inter-reader agreement on qualitative evaluation of SyMRIDL and the positive percent agreement (PPA) and negative percentage agreement (NPA) were analyzed using routine images as standard diagnosis. DLR significantly narrowed the quantitative differences between T2-SyMRIDL and T2MESE for 0.8 ms with 95% LOA [−5.5, 7.1]. The subjective assessment between DLR synthetic MR images and conventional MRI was comparable (all p > 0.05); Inter-reader agreement for SyMRIDL and conventional MRI was substantial to almost perfect with values between 0.62 and 0.88. SyMRIDL MOAKS had substantial inter-reader agreement and high PPA/NPA values (95%/99%) using conventional MRI as standard reference. Moreover, T2-SyMRIDL measurements instead of non-DLR ones significantly differentiated normal-appearing from injury-visible cartilages. DLR synthetic knee MRI provided both weighted images for clinical diagnosis and accurate T2 measurements for more confidently identifying early cartilage degeneration from normal-appearing cartilages. One-acquisition synthetic MRI based on deep learning reconstruction provided an accurate quantitative T2 map and morphologic images in relatively short scan time for more confidently identifying early cartilage degeneration from normal-appearing cartilages compared to the conventional morphologic knee sequences. Deep learning reconstruction (DLR) synthetic knee cartilage T2 values showed no difference from conventional ones. DLR synthetic T1-, proton density-, STIR-weighted images had high positive percent agreement and negative percentage agreement using MRI OA Knee Score features. DLR synthetic T2 measurements could identify early cartilage degeneration from normal-appearing ones. Deep learning reconstruction (DLR) synthetic knee cartilage T2 values showed no difference from conventional ones. DLR synthetic T1-, proton density-, STIR-weighted images had high positive percent agreement and negative percentage agreement using MRI OA Knee Score features. DLR synthetic T2 measurements could identify early cartilage degeneration from normal-appearing ones.

Background - Deep learning (DL) super-resolution image reconstruction enables higher acceleration factors for combined parallel imaging-simultaneous multislice-accelerated knee MRI but requires performance validation against external reference standards. Objective - The purpose of this study was to validate the clinical efficacy of sixfold-accelerated sub-5-minute 3-T knee MRI employing combined threefold parallel imaging (PI)-twofold simultaneous multislice (SMS) acceleration and DL super-resolution image reconstruction against arthroscopic surgery. Methods - Consecutive adult patients with painful knee conditions who underwent sixfold PI-SMS-accelerated DL super-resolution 3-T knee MRI and arthroscopic surgery between October 2022 and July 2023 were retrospectively included. Seven fellowship-trained musculoskeletal radiologists independently assessed the MRI studies for image quality parameters, presence of artifacts, structural visibility (Likert scales: 1 [very bad/severe] to 5 [very good/absent]), and the presence of cruciate ligament tears, collateral ligament tears, meniscal tears, cartilage defects, and fractures. Statistical analyses included kappa-based interreader agreements and diagnostic performance testing. Results - The final sample included 124 adult patients (mean age ± SD, 46 ± 17 years; 79 men, 45 women) who underwent knee MRI and arthroscopic surgery within a median of 28 days (range, 4-56 days). Overall image quality was good to very good (median, 4 [IQR, 4-5]) with very good interreader agreement (κ = 0.86). Motion artifacts were absent (median, 5 [IQR, 5-5]), and image noise was minimal (median, 4 [IQR, 4-5]). Visibility of anatomic structures was very good (median, 5 [IQR, 5-5]). Diagnostic performance for diagnosing arthroscopy-validated structural abnormalities was good to excellent (AUC ≥ 0.81) with at least good interreader agreement (κ ≥ 0.72). The sensitivity, specificity, accuracy, and AUC values were 100%, 99%, 99%, and 0.99, for anterior cruciate ligament tears; 100%, 100%, 100%, and 1.00 for posterior cruciate ligament tears; 90%, 95%, 94%, and 0.93 for medial meniscus tears; 76%, 97%, 90%, and 0.86 for lateral meniscus tears; and 85%, 88%, 88%, and 0.81 for articular cartilage defects, respectively. Conclusion - Sixfold PI-SMS-accelerated sub-5-minute DL super-resolution 3-T knee MRI has excellent diagnostic performance for detecting internal derangement. Clinical Impact - Sixfold PI-SMS-accelerated DL super-resolution 3-T knee MRI provides high efficiency through short scan times and high diagnostic performance.

Super‐resolution is an emerging method for enhancing MRI resolution; however, its impact on image quality is still unknown.

Objectives: The purpose of this study was to assess whether a 3-min 2D knee protocol can meet the needs for clinical application if using a SuperResolution reconstruction approach. Methods: In this prospective study, a total of 20 volunteers underwent imaging of the knee using a 3T MRI scanner (Philips Ingenia Elition X 3.0T, Philips). The imaging protocol, consisting of a fat-saturated 2D proton density sequence in coronal, sagittal, and transverse orientations, as well as a sagittal T1-weighted sequence, was acquired with standard and ultra-low resolution. The standard sequences were reconstructed using an AI-assisted Compressed SENSE method (SmartSpeed). The ultra-low-resolution sequences have been reconstructed using a vendor-provided prototype. Four experienced readers (two radiologists and two orthopedic surgeons) evaluated the sequences for image quality, anatomical structures, and incidental pathologies. The consensus evaluation of two different experienced radiologists specialized in musculoskeletal imaging served as the gold standard. Results: The acquisition time for the entire protocol was 11:01 min for standard resolution and 03:36 min for ultra-low resolution. In the overall assessment, CS-SuperRes-reconstructed sequences showed slightly improved accuracy and increased specificity compared to the standard CS-AI method (0.87 vs. 0.86 and 0.9 vs. 0.87, respectively), while the standard method exhibited a higher sensitivity (0.73 vs. 0.57). Overall, 24 out of 40 pathologies were detected in the ultra-low-resolution images compared to 26 in the standard images. Conclusions: The CS-SuperRes method enables a 2D knee protocol to be completed in 3 min, with improved accuracy compared to the clinical standard.

Objectives The purpose of this study was to assess the technical feasibility of 3-dimensional (3D) super-resolution reconstruction (SRR) of 2D turbo spin echo (TSE) knee magnetic resonance imaging (MRI) and to compare its image quality with conventional 3D TSE sampling perfection with application optimized contrast using different flip angle evolutions (SPACE) MRI. Materials and Methods Super-resolution reconstruction 2D TSE MRI and 3D TSE SPACE images were acquired from a phantom and from the knee of 22 subjects (8 healthy volunteers and 14 patients) using a clinical 3-T scanner. For SRR, 7 anisotropic 2D TSE stacks (voxel size, 0.5 × 0.5 × 2.0 mm3; scan time per stack, 1 minute 55 seconds; total scan time, 13 minutes 25 seconds) were acquired with the slice stack rotated around the phase-encoding axis. Super-resolution reconstruction was performed at an isotropic high-resolution grid with a voxel size of 0.5 × 0.5 × 0.5 mm3. Direct isotropic 3D image acquisition was performed with the conventional SPACE sequence (voxel size, 0.5 × 0.5 × 0.5 mm3; scan time, 12 minutes 42 seconds). For quantitative evaluation, perceptual blur metrics and edge response functions were obtained in the phantom image, and signal-to-noise and contrast-to-noise ratios were measured in the images from the healthy volunteers. Images were qualitatively evaluated by 2 independent radiologists in terms of overall image quality, edge blurring, anatomic visibility, and diagnostic confidence to assess normal and abnormal knee structures. Nonparametric statistical analysis was performed, and significance was defined for P values less than 0.05. Results In the phantom, perceptual blur metrics and edge response functions demonstrated a clear improvement in spatial resolution for SRR compared with conventional 3D SPACE. In healthy subjects, signal-to-noise and contrast-to-noise ratios in clinically relevant structures were not significantly different between SRR and 3D SPACE. Super-resolution reconstruction provided better overall image quality and less edge blurring than conventional 3D SPACE, yet the perceived image contrast was better for 3D SPACE. Super-resolution reconstruction received significantly better visibility scores for the menisci, whereas the visibility of cartilage was significantly higher for 3D SPACE. Ligaments had high visibility on both SRR and 3D SPACE images. The diagnostic confidence for assessing menisci was significantly higher for SRR than for conventional 3D SPACE, whereas there were no significant differences between SRR and 3D SPACE for cartilage and ligaments. The interreader agreement for assessing menisci was substantial with 3D SPACE and almost perfect with SRR, and the agreement for assessing cartilage was almost perfect with 3D SPACE and moderate with SRR. Conclusions We demonstrate the technical feasibility of SRR for high-resolution isotropic knee MRI. Our SRR results show superior image quality in terms of edge blurring, but lower image contrast and fluid brightness when compared with conventional 3D SPACE acquisitions. Further contrast optimization and shortening of the acquisition time with state-of-the-art acceleration techniques are necessary for future clinical validation of SRR knee MRI.

… additional experiments on a knee MRI dataset that includes … This is because the knee dataset contains a very limited … Figure 15 illustrates the visual comparison results on the knee …

In this paper, we propose a wavelet-aware transformer network (WATNet) for multi-contrast knee MRI super-resolution. Unlike conventional image domain-based super-resolution methods that can not explicitly model the lost high-frequency information, our WATNet endeavors to adaptively fuse the complementary frequency information of the multi-contrast image in the wavelet domain and further refine it in the image domain. The proposed WATNet consists of the multi-scale wavelet transformation (MSWT) module, wavelet-aware transformer (WAT) module, and reconstruction (Rec) module. Specifically, the MSWT module learns to transform the MR image to multi-scale wavelet domain features by the wavelet transformation. The WAT module can adaptively search and transfer similar wavelet domain reference information to the low-resolution one. The Rec module can restore high-quality images in the image domain. To further capture more high-frequency details, we also design the wavelet-based high-frequency loss. The qualitative and quantitative experimental results indicate that our proposed WATNet outperforms most state-of-the-art methods.

… Post-acquisition, super-resolution (SR) filtering is a viable … Evaluations based on synthetic data and clinical knee MRI … framework for super-resolution that models MRI acquisition param…

PURPOSE High resolution 3D MR images are well suited for automated cartilage segmentation in the human knee joint. However, volumetric scans such as 3D Double-Echo Steady-State (DESS) images are not routinely acquired in clinical practice which limits opportunities for reliable cartilage segmentation using (fully) automated algorithms. In this work, a method for generating synthetic 3D MR (syn3D-DESS) images with better contrast and higher spatial resolution from routine, low resolution, 2D Turbo-Spin Echo (TSE) clinical knee scans is proposed. METHODS A UNet convolutional neural network is employed for synthesizing enhanced artificial MR images suitable for automated knee cartilage segmentation. Training of the model was performed on a large, publically available dataset from the OAI, consisting of 578 MR examinations of knee joints from 102 healthy individuals and patients with knee osteoarthritis. RESULTS The generated synthetic images have higher spatial resolution and better tissue contrast than the original 2D TSE, which allow high quality automated 3D segmentations of the cartilage. The proposed approach was evaluated on a separate set of MR images from 88 subjects with manual cartilage segmentations. It provided a significant improvement in automated segmentation of knee cartilages when using the syn3D-DESS images compared to the original 2D TSE images. CONCLUSION The proposed method can successfully synthesise 3D DESS images from 2D TSE images to provide images suitable for automated cartilage segmentation.

This study introduces a hybrid analytical super-resolution (SR) pipeline aimed at enhancing the resolution of medical magnetic resonance imaging (MRI) scans. The primary objective is to overcome the limitations of clinical MRI resolution without the need for additional expensive hardware. The proposed pipeline involves three key steps: pre-processing to re-slice and register the image stacks; SR reconstruction to combine information from three orthogonal image stacks to generate a high-resolution image stack; and post-processing using an artefact reduction convolutional neural network (ARCNN) to reduce the block artefacts introduced during SR reconstruction. The workflow was validated on a dataset of six knee MRIs obtained at high resolution using various sequences. Quantitative analysis of the method revealed promising results, showing an average mean error of 1.40 ± 2.22% in voxel intensities between the SR denoised images and the original high-resolution images. Qualitatively, the method improved out-of-plane resolution while preserving in-plane image quality. The hybrid SR pipeline also displayed robustness across different MRI sequences, demonstrating potential for clinical application in orthopaedics and beyond. Although computationally intensive, this method offers a viable alternative to costly hardware upgrades and holds promise for improving diagnostic accuracy and generating more anatomically accurate models of the human body.

… This study aims to improve image super-resolution techniques by balancing distortion … Toward Improving Super-Resolution, which focuses on producing high-quality knee magnetic …

… –SMSx2–accelerated DL super-resolution 3T knee MRI at our institution between October … painful knee conditions. Inclusion criteria were PIx3–SMSx2 DL super-resolution knee MRI …

… segment, treating each as a separate image although MRI is processed as voxels (3D). This … be observed on a single MRI slice. Note that the first or last slices of knee MRI may not have …

Background Fast magnetic resonance imaging (MRI) can significantly improve patient tolerance and examination efficiency, but it may compromise image quality. This study investigated the feasibility of using a deep learning-assisted three-dimensional iterative image enhancement (DL-3DIIE) system to achieve high-resolution fast imaging of the knee. Methods This prospective study included participants scheduled for knee MRI plain scans at the Northern Jiangsu People’s Hospital between September 2023 and January 2024. The participants underwent knee MRI with both conventional and fast scans. Three MRI protocols were compared: conventional MRI, fast MRI with reduced acquisition parameters, and DL-3DIIE MRI, which enhanced fast images with deep learning to improve overall image quality. Image quality was assessed subjectively (quality scores) and objectively using peak signal-to-noise ratio (PSNR), multi-scale structural similarity index (MS-SSIM), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR). Results The analysis included 134 patients (mean age 55.1±9.5 years; 46.3% male). For both sagittal proton density weighted imaging-fast spin echo (PDWI-FSE) and T1 weighted imaging-fast spin echo (T1WI-FSE) sequences, DL-3DIIE MRI achieved significantly higher SNRs and CNRs across all tissues and tissue contrasts compared with both conventional and fast MRI (all P<0.05). Quantitative metrics of image quality were also improved, with PSNR and MS-SSIM significantly higher for DL-3DIIE MRI than fast MRI in all sequences (all P<0.001). Subjective image quality assessment demonstrated that DL-3DIIE MRI yielded significantly higher scores for lesion conspicuity, margin delineation, and overall diagnostic confidence compared with conventional MRI (all P<0.05). Conclusions DL-3DIIE MRI provides superior quantitative and subjective image quality compared with both conventional and fast MRI, including higher SNR, CNR, PSNR, and MS-SSIM, as well as improved lesion and margin visibility. These findings support the potential of DL-3DIIE to accelerate knee MRI while preserving or improving diagnostic performance.

RATIONALE AND OBJECTIVES The objective of this study was to evaluate a combination of deep learning (DL)-reconstructed parallel acquisition technique (PAT) and simultaneous multislice (SMS) acceleration imaging in comparison to conventional knee imaging. MATERIALS AND METHODS Adults undergoing knee magnetic resonance imaging (MRI) with DL-enhanced acquisitions were prospectively analyzed from December 2023 to April 2024. The participants received T1 without fat saturation and fat-suppressed PD-weighted TSE pulse sequences using conventional two-fold PAT (P2) and either DL-enhanced four-fold PAT (P4) or a combination of DL-enhanced four-fold PAT with two-fold SMS acceleration (P4S2). Three independent readers assessed image quality, signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR), and radiomics features. RESULTS 34 participants (mean age 45±17years; 14 women) were included who underwent P4S2, P4, and P2 imaging. Both P4S2 and P4 demonstrated higher CNR and SNR values compared to P2 (P<.001). P4 was diagnostically inferior to P2 only in the visualization of cartilage damage (P<.005), while P4S2 consistently outperformed P2 in anatomical delineation across all evaluated structures and raters (P<.05). Radiomics analysis revealed significant differences in contrast and gray-level characteristics among P2, P4, and P4S2 (P<.05). P4 reduced time by 31% and P4S2 by 41% compared to P2 (P<.05). CONCLUSION P4S2 DL acceleration offers significant advancements over P4 and P2 in knee MRI, combining superior image quality and improved anatomical delineation at significant time reduction. Its improvements in anatomical delineation, energy consumption, and workforce optimization make P4S2 a significant step forward.

BACKGROUND. Potential approaches for abbreviated knee MRI, including prospective acceleration with deep learning, have achieved limited clinical implementation. OBJECTIVE. The objective of this study was to evaluate the interreader agreement between conventional knee MRI and a 5-minute 3D quantitative double-echo steady-state (qDESS) sequence with automatic T2 mapping and deep learning super-resolutionaugmentation and to compare the diagnostic performance of the two methods regarding findings from arthroscopic surgery. METHODS. Fifty-one patients with knee pain underwent knee MRI that included an additional 3D qDESS sequence with automatic T2 mapping. Fourier interpolation was followed by prospective deep learning super resolution to enhance qDESS slice resolution twofold. A musculoskeletal radiologist and a radiology resident performed independent retrospective evaluations of articular cartilage, menisci, ligaments, bones, extensor mechanism, and synovium using conventional MRI. Following a 2-month washout period, readers reviewed qDESS images alone followed by qDESS with the automatic T2 maps. Interreader agreement between conventional MRI and qDESS was computed using percentage agreement and Cohen kappa. The sensitivity and specificity of conventional MRI, qDESS alone, and qDESS plus T2 mapping were compared with arthroscopic findings using exact McNemar tests. RESULTS. Conventional MRI and qDESS showed 92% agreement in evaluating all tissues. Kappa was 0.79 (95% CI, 0.76–0.81) across all imaging findings. In 43 patients who underwent arthroscopy, sensitivity and specificity were not significantly different (p = .23 to > .99) between conventional MRI (sensitivity, 58–93%; specificity, 27–87%) and qDESS alone (sensitivity, 54–90%; specificity, 23–91%) for cartilage, menisci, ligaments, and synovium. For grade 1 cartilage lesions, sensitivity and specificity were 33% and 56%, respectively, for conventional MRI; 23% and 53% for qDESS (p = .81); and 46% and 39% for qDESS with T2 mapping (p = .80). For grade 2A lesions, values were 27% and 53% for conventional MRI, 26% and 52% for qDESS (p = .02), and 58% and 40% for qDESS with T2 mapping (p < .001). CONCLUSION. The qDESS method prospectively augmented with deep learning showed strong interreader agreement with conventional knee MRI and near-equivalent diagnostic performance regarding arthroscopy. The ability of qDESS to automatically generate T2 maps increases sensitivity for cartilage abnormalities. CLINICAL IMPACT. Using prospective artificial intelligence to enhance qDESS image quality may facilitate an abbreviated knee MRI protocol while generating quantitative T2 maps.

Objectives This study aimed to examine various combinations of parallel imaging (PI) and simultaneous multislice (SMS) acceleration imaging using deep learning (DL)-enhanced and conventional reconstruction. The study also aimed at comparing the diagnostic performance of the various combinations in internal knee derangement and provided a quantitative evaluation of image sharpness and noise using edge rise distance (ERD) and noise power (NP), respectively. Materials and Methods The data from adult patients who underwent knee magnetic resonance imaging using various DL-enhanced acquisitions between June 2021 and January 2022 were retrospectively analyzed. The participants underwent conventional 2-fold PI and DL protocols with 4- to 8-fold acceleration imaging (P2S2 [2-fold PI with 2-fold SMS], P3S2, and P4S2). Three readers evaluated the internal knee derangement and the overall image quality. The diagnostic performance was calculated using consensus reading as a standard reference, and we conducted comparative evaluations. We calculated the ERD and NP for quantitative evaluations of image sharpness and noise, respectively. Interreader and intermethod agreements were calculated using Fleiss κ. Results A total of 33 patients (mean age, 49 ± 19 years; 20 women) were included in this study. The diagnostic performance for internal knee derangement and the overall image quality were similar among the evaluated protocols. The NP values were significantly lower using the DL protocols than with conventional imaging (P < 0.001), whereas the ERD values were similar among these methods (P > 0.12). Interreader and intermethod agreements were moderate-to-excellent (κ = 0.574–0.838) and good-to-excellent (κ = 0.755–1.000), respectively. In addition, the mean acquisition time was reduced by 47% when using DL with P2S2, by 62% with P3S2, and by 71% with P4S2, compared with conventional P2 imaging (2 minutes and 55 seconds). Conclusions The combined use of DL-enhanced 8-fold acceleration imaging (4-fold PI with 2-fold SMS) showed comparable performance with conventional 2-fold PI for the evaluation of internal knee derangement, with a 71% reduction in acquisition time.

Objectives The aim of this study was to evaluate the use of a multicontrast deep learning (DL)–reconstructed 4-fold accelerated 2-dimensional (2D) turbo spin echo (TSE) protocol and the feasibility of 3-dimensional (3D) superresolution reconstruction (SRR) of DL-enhanced 6-fold accelerated 2D Dixon TSE magnetic resonance imaging (MRI) for comprehensive knee joint assessment, by comparing image quality and diagnostic performance with a conventional 2-fold accelerated 2D TSE knee MRI protocol. Materials and Methods This prospective, ethics-approved study included 19 symptomatic adult subjects who underwent knee MRI on a clinical 3 T scanner. Every subject was scanned with 3 DL-enhanced acquisition protocols in a single session: a clinical standard 2-fold in-plane parallel imaging (PI) accelerated 2D TSE-based protocol (5 sequences, 11 minutes 23 seconds) that served as a reference, a DL-reconstructed 4-fold accelerated 2D TSE protocol combining 2-fold PI and 2-fold simultaneous multislice acceleration (5 sequences, 6 minutes 24 seconds), and a 3D SRR protocol based on DL-enhanced 6-fold accelerated (ie, 3-fold PI and 2-fold simultaneous multislice) 2D Dixon TSE MRI (6 anisotropic 2D Dixon TSE acquisitions rotated around the phase-encoding axis, 6 minutes 24 seconds). This resulted in a total of 228 knee MRI scans comprising 21,204 images. Three readers evaluated all pseudonymized and randomized images in terms of image quality using a 5-point Likert scale. Two of the readers (musculoskeletal radiologists) additionally evaluated anatomical visibility and diagnostic confidence to assess normal and pathological knee structures with a 5-point Likert scale. They recorded the presence and location of internal knee derangements, including cartilage defects, meniscal tears, tears of ligaments, tendons and muscles, and bone injuries. The statistical analysis included nonparametric Friedman tests, and interreader and intrareader agreement assessment using the weighted Fleiss-Cohen kappa (κ) statistic. P values of less than 0.05 were considered statistically significant. Results The evaluated DL-enhanced 4-fold accelerated 2D TSE protocol provided very similar image quality and anatomical visibility to the standard 2D TSE protocol, whereas the 3D SRR Dixon TSE protocol scored less in terms of overall image quality due to reduced edge sharpness and the presence of artifacts (P < 0.001). Subjective signal-to-noise ratio, contrast resolution, fluid brightness, and fat suppression were good to excellent for all protocols. For 1 reader, the Dixon method of the 3D SRR protocol provided significantly better fat suppression than the spectral fat saturation applied in the standard 2D TSE protocol (P < 0.05). The visualization of knee structures with 3D SRR Dixon TSE was very similar to the standard protocol, except for cartilage, tendons, and bone, which were affected by the presence of reconstruction and aliasing artifacts (P < 0.001). The diagnostic confidence of both readers was high for all protocols and all knee structures, except for cartilage and tendons. The standard 2D TSE protocol showed a significantly higher diagnostic confidence for assessing tendons than 3D SRR Dixon TSE MRI (P < 0.01). The interreader and intrareader agreement for the assessment of internal knee derangements using any of the 3 protocols was substantial to almost perfect (κ = 0.67–1.00). For cartilage, the interreader agreement was substantial for DL-enhanced accelerated 2D TSE (κ = 0.79) and almost perfect for standard 2D TSE (κ = 0.98) and 3D SRR Dixon TSE (κ = 0.87). For menisci, the interreader agreement was substantial for 3D SRR Dixon TSE (κ = 0.70–0.80) and substantial to almost perfect for standard 2D TSE (κ = 0.80–0.99) and DL-enhanced 2D TSE (κ = 0.87–1.00). Moreover, the total acquisition time was reduced by 44% when using the DL-enhanced accelerated 2D TSE or 3D SRR Dixon TSE protocol instead of the conventional 2D TSE protocol. Conclusions The presented DL-enhanced 4-fold accelerated 2D TSE protocol provides image quality and diagnostic performance similar to the standard 2D protocol. Moreover, the 3D SRR of DL-enhanced 6-fold accelerated 2D Dixon TSE MRI is feasible for multicontrast 3D knee MRI as its diagnostic performance is comparable to standard 2-fold accelerated 2D knee MRI. However, reconstruction and aliasing artifacts need to be further addressed to guarantee a more reliable visualization and assessment of cartilage, tendons, and bone. Both the 2D and 3D SRR DL-enhanced protocols enable a 44% faster examination compared with conventional 2-fold accelerated routine 2D TSE knee MRI and thus open new paths for more efficient clinical 2D and 3D knee MRI.

Purpose: The purpose of this study is to investigate the potential of deep learning (DL) techniques to enhance the image quality of low-field knee MR images, with the ultimate goal of approximating the standards of high-field knee MR imaging. Methods: We analyzed knee MR images collected from 45 patients with knee disorders and six normal subjects using a 3T MR scanner and those collected from 25 patients with knee disorders using a 0.4T MR scanner. Two DL models were developed: a fat-suppression contrast-generation model and a super-resolution model. These DL models were trained using 3T knee MR imaging data and applied to 0.4T knee MR imaging data. Visual assessments of anatomical structures and image noise and abnormality detection with diagnostic confidence levels on the original 0.4T MR images and those after DL enhancement were conducted by two board-certified radiologists. Statistical analyses were performed using McNemar’s test and the Wilcoxon signed-rank test. Results: DL-enhanced MR images significantly improved the depiction of anatomical structures and reduced image noise compared to the original MR images. The number of abnormal findings detected and the diagnostic confidence levels were higher in the DL-enhanced MR images, indicating the potential for more accurate diagnoses. Conclusion: DL techniques effectively enhance the image quality of low-field knee MR images by leveraging 3T MR imaging data. This enhancement significantly improves image quality and diagnostic confidence levels, making low-field MR images much more reliable for detecting abnormalities. This advancement offers a useful alternative for clinical settings, especially in resource-limited environments, without compromising diagnostic accuracy.

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast for clinical diagnoses and research which underpin many recent breakthroughs in medicine and biology. The post-processing of reconstructed MR images is often automated for incorporation into MRI scanners by the manufacturers and increasingly plays a critical role in the final image quality for clinical reporting and interpretation. For image enhancement and correction, the post-processing steps include noise reduction, image artefact correction, and image resolution improvements. With the recent success of deep learning in many research fields, there is great potential to apply deep learning for MR image enhancement, and recent publications have demonstrated promising results. Motivated by the rapidly growing literature in this area, in this review paper, we provide a comprehensive overview of deep learning-based methods for post-processing MR images to enhance image quality and correct image artefacts. We aim to provide researchers in MRI or other research fields, including computer vision and image processing, a literature survey of deep learning approaches for MR image enhancement. We discuss the current limitations of the application of artificial intelligence in MRI and highlight possible directions for future developments. In the era of deep learning, we highlight the importance of a critical appraisal of the explanatory information provided and the generalizability of deep learning algorithms in medical imaging.

… time, the resolution of MR imaging is low. The previous … In this paper, we proposed DMN, a blind super-resolution … The experimental results on the MR images of the knee joint …

… The experimental results on the MR images of the knee joint and brain in the FastMRI … on two different MR imaging devices. So, we use the blind super-resolution method to solve the …

… MRI blind super resolution to improve the capability of estimating the blur kernel, thus effectively reconstructing HR-MRI … The FastMRI dataset contains knee MRI and brain MRI, and in …

… a self-supervised superresolution GAN and a probabilistic diffusion inpainting model to enhance anisotropic knee MRI images and facilitate 3D isotropic detection of knee abnormalities. …

Accelerating musculoskeletal magnetic resonance imaging (MRI) while preserving diagnostic detail remains challenging because acquiring fully‑isotropic ground‑truth volumes is clinically costly. In routine practice, anisotropic scans with reduced through-plane resolution degrade multiplanar visualization and slice-by-slice review in reformatted planes, obscure subtle abnormalities spanning only a few slices, and limit automated three-dimensional (3D) analyses that assume comparable spatial resolution across axes. We present a two‑stage, fully self‑supervised pipeline that learns directly from anisotropic scans-obviating any paired high‑resolution data-and converts highly anisotropic (8:1) turbo‑spin‑echo volumes into isotropic images and 3D abnormality maps. Unlike prior self-supervised super-resolution methods, Stage 1 uses a single forward multi-view generative adversarial network (GAN) with patch-based contrastive and adversarial objectives rather than a backward/cycle-consistency approach. Stage 2 leverages an anatomy-conditioned denoising-diffusion model for healthy counterfactual generation, yielding voxel-wise lesion maps without external annotations. On 2225 Osteoarthritis Initiative knee scans from five different imaging centres, the framework reduced Fréchet inception distance from 407.4 → 254.4 (coronal) and 429.9 → 266.9 (axial), achieved the best Kernel Inception Distance (KID) / Learned Perceptual Image Patch Similarity (LPIPS) scores among competing unsupervised methods, and was preferred in 65-67% of blinded orthopedist comparisons. Crucially, isotropic enhancement propagated to downstream tasks: femur-tibia segmentation F1 scores increased and previously confluent bone‑marrow lesions were separated into discrete entities, enabling precise volumetric quantification. Robustness experiments demonstrated consistent gains across five imaging centers, synthetic noise/contrast perturbations, and transfer of the resolution-enhancement module to two additional MRI protocols, supporting robustness across sites and acquisition protocols. By eliminating the need for ground‑truth isotropic images while surpassing state‑of‑the‑art unsupervised super‑resolution in both perceptual quality and clinical utility, our method may facilitate retrospective cohort studies and prospective scan-time reduction in heterogeneous knee MRI settings, with preliminary transferability to additional protocols.

Magnetic Resonance Imaging (MRI) serves as a pivotal medical diagnostic technique widely deployed in clinical practice, yet high-resolution reconstruction frequently introduces motion artifacts and degrades signal-to-noise ratios. To enhance imaging efficiency and improve reconstruction quality, this study proposes a Transformer network-based super-resolution framework for MRI images. The methodology integrates Nonuniform Fast Fourier Transform (NUFFT) with a hybrid-attention Transformer network to achieve high-fidelity reconstruction. The embedded NUFFT module adaptively applies density compensation to k-space data based on sampling trajectories, while the Mixed Attention Block (MAB) activates broader pixel engagement to amplify feature extraction capabilities. The Interactive Attention Block (IAB) facilitates cross-window information fusion via overlapping windows, effectively suppressing artifacts. Evaluated on the fastMRI dataset under 4× radial undersampling, the network demonstrates 3.52 dB higher PSNR and 0.21 SSIM improvement over baselines, outperforming state-of-the-art methods across quantitative metrics. Visual assessments further confirm superior detail preservation and artifact suppression. This work establishes an effective pipeline for high-quality radial MRI reconstruction, providing a novel technical pathway for low-field MRI systems with significant research and application value.

… We conducted a comprehensive literature review to synthesize recent progress in self-supervised DL for MRI reconstruction. The analysis focused on methods and architectures …

Multi-contrast MRI (MC-MRI) captures multiple complementary imaging modalities to aid in radiological decision-making. Given the need for lowering the time cost of multiple acquisitions, current deep accelerated MRI reconstruction networks focus on exploiting the redundancy between multiple contrasts. However, existing works are largely supervised with paired data and/or prohibitively expensive fully-sampled MRI sequences. Further, reconstruction networks typically rely on convolutional architectures which are limited in their capacity to model long-range interactions and may lead to suboptimal recovery of fine anatomical detail. To these ends, we present a dual-domain self-supervised transformer (DSFormer) for accelerated MC-MRI reconstruction. DSFormer develops a deep conditional cascade transformer (DCCT) consisting of cascaded Swin transformer reconstruction networks (SwinRN) trained under two deep conditioning strategies to enable MC-MRI information sharing. We further use a dual-domain (image and k-space) self-supervised learning strategy for DCCT to alleviate the costs of acquiring fully sampled training data. DSFormer generates high-fidelity reconstructions which outperform current fully-supervised baselines and approach the performance of full supervision.

Deep learning (DL) has emerged as a leading approach in accelerating MRI. It employs deep neural networks to extract knowledge from available datasets and then applies the trained networks to reconstruct accurate images from limited measurements. Unlike natural image restoration problems, MRI involves physics‐based imaging processes, unique data properties, and diverse imaging tasks. This domain knowledge needs to be integrated with data‐driven approaches. Our review will introduce the significant challenges faced by such knowledge‐driven DL approaches in the context of fast MRI along with several notable solutions, which include learning neural networks and addressing different imaging application scenarios. The traits and trends of these techniques have also been given which have shifted from supervised learning to semi‐supervised learning, and finally, to unsupervised learning methods. In addition, MR vendors' choices of DL reconstruction have been provided along with some discussions on open questions and future directions, which are critical for the reliable imaging systems.

Most deep learning (DL) magnetic resonance imaging (MRI) reconstruction approaches rely on supervised training algorithms, which require access to high-quality, fully-sampled ground truth datasets. In MRI, acquiring fully-sampled data is time-consuming, expensive, and, in some cases, impossible due to limitations on data acquisition speed. We present a DL framework for MRI reconstruction that does not require any fully-sampled data using unsupervised generative adversarial networks. We test our proposed method on 2D knee MRI data and 2D+time abdominal dynamic contrast enhanced (DCE) MRI data. In the DCE-MRI dataset, as is the case with many dynamic MRI sequences, ground truth was not possible to acquire and therefore, supervised DL reconstruction was not feasible. We show that our unsupervised method produces reconstructions which are better than compressed sensing in terms of image metrics and the recovery of anatomical structure, with faster inference time. In contrast to most deep learning reconstruction techniques, which are supervised, this method does not need any fully-sampled data. With the proposed method, accelerated imaging and accurate reconstruction can be performed in applications in cases where fully-sampled datasets are difficult to obtain or unavailable.

In this work, novel denoising and super resolution (SR) approaches for magnetic resonance (MR) images are addressed, and are integrated in a unified framework, which do not require example low resolution (LR)/high resolution (HR)/cross-modality/noise-free images and prior information of noise–noise variance. The proposed method categorizes the patches as either smooth or textured and then denoises them by deploying different denoising strategies for efficient denoising. The denoising algorithm is integrated into the SR approach, which uses a gradient profile-based constraint in a sparse representation-based framework to improve the resolution of MR images with reduced smearing of image details. This constraint regularizes the estimation of HR images such that the estimated HR image has gradient profiles similar to the gradient profiles of the original HR image. For this, the gradient profile sharpness (GPS) values of an unknown HR image are estimated using an approximated piece-wise linear relation among GPS values of LR and upsampled LR images. The experiments are performed on three different publicly available datasets. The proposed SR approach outperforms the existing unsupervised SR approach addressed for real MR images that exploits low rank and total variation (LRTV) regularization, by an average peak signal to noise ratio (PSNR) of 0.73 dB and 0.38 dB for upsampling factors 2 and 3, respectively. For the super resolution of noisy real MR images (degraded with 2% noise), the proposed approach outperforms the LRTV approach by an average PSNR of 0.54 dB and 0.46 dB for upsampling factors 2 and 3, respectively. The qualitative analysis is shown for real MR images from healthy subjects and subjects with Alzheimer’s disease and structural deformity, i.e., cavernoma.

Background Deep learning (DL) reconstructions can enhance image quality while decreasing MRI acquisition time. However, DL reconstruction methods combined with compressed sensing for prostate MRI have not been well studied. Purpose To use an industry-developed DL algorithm to reconstruct low-resolution T2-weighted turbo spin-echo (TSE) prostate MRI scans and compare these with standard sequences. Materials and Methods In this prospective study, participants with suspected prostate cancer underwent prostate MRI with a Cartesian standard-resolution T2-weighted TSE sequence (T2C) and non-Cartesian standard-resolution T2-weighted TSE sequence (T2NC) between August and November 2022. Additionally, a low-resolution Cartesian DL-reconstructed T2-weighted TSE sequence (T2DL) with compressed sensing DL denoising and resolution upscaling reconstruction was acquired. Image sharpness was assessed qualitatively by two readers using a five-point Likert scale (from 1 = nondiagnostic to 5 = excellent) and quantitatively by calculating edge rise distance. The Friedman test and one-way analysis of variance with post hoc Bonferroni and Tukey tests, respectively, were used for group comparisons. Prostate Imaging Reporting and Data System (PI-RADS) score agreement between sequences was compared by using Cohen κ. Results This study included 109 male participants (mean age, 68 years ± 8 [SD]). Acquisition time of T2DL was 36% and 29% lower compared with that of T2C and T2NC (mean duration, 164 seconds ± 20 vs 257 seconds ± 32 and 230 seconds ± 28; P < .001 for both). T2DL showed improved image sharpness compared with standard sequences using both qualitative (median score, 5 [IQR, 4-5] vs 4 [IQR, 3-4] for T2C and 4 [IQR, 3-4] for T2NC; P < .001 for both) and quantitative (mean edge rise distance, 0.75 mm ± 0.39 vs 1.15 mm ± 0.68 for T2C and 0.98 mm ± 0.65 for T2NC; P < .001 and P = .01) methods. PI-RADS score agreement between T2NC and T2DL was excellent (κ range, 0.92-0.94 [95% CI: 0.87, 0.98]). Conclusion DL reconstruction of low-resolution T2-weighted TSE sequences enabled accelerated acquisition times and improved image quality compared with standard acquisitions while showing excellent agreement with conventional sequences for PI-RADS ratings. Clinical trial registration no. NCT05820113 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Turkbey in this issue.

As the quantity and significance of digital pictures in the medical industry continue to increase, Image Quality Assessment (IQA) has recently become a prevalent subject in the research community. Due to the wide range of distortions that Magnetic Resonance Images (MRI) can experience and the wide variety of information they contain, No-Reference Image Quality Assessment (NR-IQA) has always been a challenging study issue. In an attempt to address this issue, a novel hybrid Artificial Intelligence (AI) is proposed to analyze NR-IQ in massive MRI data. First, the features from the denoised MRI images are extracted using the gray level run length matrix (GLRLM) and EfficientNet B7 algorithm. Next, the Multi-Objective Reptile Search Algorithm (MRSA) was proposed for optimal feature vector selection. Then, the Self-evolving Deep Belief Fuzzy Neural network (SDBFN) algorithm was proposed for the effective NR-IQ analysis. The implementation of this research is executed using MATLAB software. The simulation results are compared with the various conventional methods in terms of correlation coefficient (PLCC), Root Mean Square Error (RMSE), Spearman Rank Order Correlation Coefficient (SROCC) and Kendall Rank Order Correlation Coefficient (KROCC), and Mean Absolute Error (MAE). In addition, our proposed approach yielded a quality number approximately we achieved significant 20% improvement than existing methods, with the PLCC parameter showing a notable increase compared to current techniques. Moreover, the RMSE number decreased by 12% when compared to existing methods. Graphical representations indicated mean MAE values of 0.02 for MRI knee dataset, 0.09 for MRI brain dataset, and 0.098 for MRI breast dataset, showcasing significantly lower MAE values compared to the baseline models.

In clinical diagnosis, magnetic resonance imaging (MRI) allows different contrast images to be obtained. High‐resolution (HR) MRI presents fine anatomical structures, which is important for improving the efficiency of expert diagnosis and realising smart healthcare. However, due to the cost of scanning equipment and the time required for scanning, obtaining an HR brain MRI is quite challenging. Therefore, to improve the quality of images, reference‐based super‐resolution technology has come into existence. Nevertheless, the existing methods still have some drawbacks: (1) The advantages of different contrast images are not fully utilised. (2) The slice‐by‐slice scanning nature of magnetic resonance imaging is not considered. (3) The ability to capture contextual information and to match and fuse multi‐scale, multi‐contrast features is lacking. In this paper, we propose the multi‐slice aware matching and fusion (MSAMF) network, which makes full use of multi‐slice reference images information by introducing a multi‐slice aware module and multi‐scale matching strategy to capture corresponding contextual information in reference features at other scales. To further integrate matching features, a multi‐scale fusion mechanism is also designed to progressively fuse multi‐scale matching features, thereby generating more detailed super‐resolution images. The experimental results support the benefits of our network in enhancing the quality of brain MRI reconstruction.

… in both full-reference and no-reference metrics and subjective visual … knee MRI. Similarly, Song et al. [27] developed a CNN-based SR approach for PET, leveraging high-resolution MRI …

Objectives: To evaluate the feasibility of combining compressed sense (CS) with a newly developed deep learning-based algorithm (CS-AI) using convolutional neural networks to accelerate 2D MRI of the knee. Methods: In this prospective study, 20 healthy volunteers were scanned with a 3T MRI scanner. All subjects received a fat-saturated sagittal 2D proton density reference sequence without acceleration and four additional acquisitions with different acceleration levels: 2, 3, 4 and 6. All sequences were reconstructed with the conventional CS and a new CS-AI algorithm. Two independent, blinded readers rated all images by seven criteria (overall image impression, visible artifacts, delineation of anterior ligament, posterior ligament, menisci, cartilage, and bone) using a 5-point Likert scale. Signal- and contrast-to-noise ratios were calculated. Subjective ratings and quantitative metrics were compared between CS and CS-AI with similar acceleration levels and between all CS/CS-AI images and the non-accelerated reference sequence. Friedman and Dunn´s multiple comparison tests were used for subjective, ANOVA and the Tukey Kramer test for quantitative metrics. Results: Conventional CS images at the lowest acceleration level (CS2) were already rated significantly lower than reference for 6/7 criteria. CS-AI images maintained similar image quality to the reference up to CS-AI three for all criteria, which would allow for a reduction in scan time of 64% with unchanged image quality compared to the unaccelerated sequence. SNR and CNR were significantly higher for all CS-AI reconstructions compared to CS (all p < 0.05). Conclusions AI-based image reconstruction showed higher image quality than CS for 2D knee imaging. Its implementation in the clinical routine yields the potential for faster MRI acquisition but needs further validation in non-healthy study subjects. Advances in knowledge Combining compressed SENSE with a newly developed deep learning-based algorithm using convolutional neural networks allows a 64% reduction in scan time for 2D imaging of the knee. Implementation of the new deep learning-based algorithm in clinical routine in near future should enable better image quality/resolution with constant scan time, or reduced acquisition times while maintaining diagnostic quality.

To investigate the potential of combining compressed sensing (CS) and artificial intelligence (AI), in particular deep learning (DL), for accelerating three-dimensional (3D) magnetic resonance imaging (MRI) sequences of the knee. Twenty healthy volunteers were examined using a 3-T scanner with a fat-saturated 3D proton density sequence with four different acceleration levels (10, 13, 15, and 17). All sequences were accelerated with CS and reconstructed using the conventional and a new DL-based algorithm (CS-AI). Subjective image quality was evaluated by two blinded readers using seven criteria on a 5-point-Likert-scale (overall impression, artifacts, delineation of the anterior cruciate ligament, posterior cruciate ligament, menisci, cartilage, and bone). Using mixed models, all CS-AI sequences were compared to the clinical standard (sense sequence with an acceleration factor of 2) and CS sequences with the same acceleration factor. 3D sequences reconstructed with CS-AI achieved significantly better values for subjective image quality compared to sequences reconstructed with CS with the same acceleration factor (p ≤ 0.001). The images reconstructed with CS-AI showed that tenfold acceleration may be feasible without significant loss of quality when compared to the reference sequence (p ≥ 0.999). For 3-T 3D-MRI of the knee, a DL-based algorithm allowed for additional acceleration of acquisition times compared to the conventional approach. This study, however, is limited by its small sample size and inclusion of only healthy volunteers, indicating the need for further research with a more diverse and larger sample. DRKS00024156. Using a DL-based algorithm, 54% faster image acquisition (178 s versus 384 s) for 3D-sequences may be possible for 3-T MRI of the knee. • Combination of compressed sensing and DL improved image quality and allows for significant acceleration of 3D knee MRI. • DL-based algorithm achieved better subjective image quality than conventional compressed sensing. • For 3D knee MRI at 3 T, 54% faster image acquisition may be possible.

OBJECTIVE Deep learning (DL) image reconstruction has the potential to disrupt the current state of MRI by significantly decreasing the time required for MRI examinations. Our goal was to use DL to accelerate MRI to allow a 5-minute comprehensive examination of the knee without compromising image quality or diagnostic accuracy. MATERIALS AND METHODS. A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multisequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. After training, data from 108 patients were retrospectively undersampled in a manner that would correspond with a net 3.49-fold acceleration of fully sampled data acquisition and a 1.88-fold acceleration compared with our standard twofold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of six readers to detect internal derangement of the knee was compared for clinical and DL-accelerated images. RESULTS. We found a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would produce discordant clinical opinions no more than 4% of the time for any feature evaluated. Moreover, the accelerated sequence was judged by all six readers to have better quality than the clinical sequence. CONCLUSION. An optimized DL model allowed acceleration of knee images that performed interchangeably with standard images for detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.

Objectives: To assess diagnostic performance of standard radial k-space (PROPELLER) MRI sequences and compare with accelerated acquisitions combined with a deep learning-based convolutional neural network (DL-CNN) reconstruction for evaluation of the knee joint. Methods: Thirty-five patients undergoing MR imaging of the knee at 1.5 T were prospectively included. Two readers evaluated image quality and diagnostic confidence of standard and DL-CNN accelerated PROPELLER MR sequences using a four-point Likert scale. Pathological findings of bone, cartilage, cruciate and collateral ligaments, menisci, and joint space were analyzed. Inter-reader agreement (IRA) for image quality and diagnostic confidence was assessed using intraclass coefficients (ICC). Cohen’s Kappa method was used for evaluation of IRA and consensus between sequences in assessing different structures. In addition, image quality was quantitatively evaluated by signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) measurements. Results: Mean acquisition time of standard vs. DL-CNN sequences was 10 min 3 s vs. 4 min 45 s. DL-CNN sequences showed significantly superior image quality and diagnostic confidence compared to standard MR sequences. There was moderate and good IRA for assessment of image quality in standard and DL-CNN sequences with ICC of 0.524 and 0.830, respectively. Pathological findings of the knee joint could be equally well detected in both sequences (κ-value of 0.8). Retropatellar cartilage could be significantly better assessed on DL-CNN sequences. SNR and CNR was significantly higher for DL-CNN sequences (both p < 0.05). Conclusions: In MR imaging of the knee, DL-CNN sequences showed significantly higher image quality and diagnostic confidence compared to standard PROPELLER sequences, while reducing acquisition time substantially. Both sequences perform comparably in the detection of knee-joint pathologies, while DL-CNN sequences are superior for evaluation of retropatellar cartilage lesions.

Background Knee joint diseases such as meniscal injuries are highly prevalent, affecting over 100 million people worldwide and impairing mobility and quality of life. Magnetic resonance imaging (MRI) is the gold standard for diagnosing meniscal injuries due to its non-invasiveness, multi-parametric imaging, and excellent tissue contrast. However, conventional knee MRI sequences [T1-weighted imaging (T1WI) and proton density-weighted imaging (PDWI)] on 1.5 T scanners require 7–9 minutes, reducing equipment efficiency and causing patient discomfort or motion artifacts. Accelerated techniques such as GeneRalized Autocalibrating Partial Parallel Acquisition (GRAPPA) shorten scan time but compromise image quality [e.g., reduced signal-to-noise ratio (SNR), increased artifacts]. This study aimed to investigate whether a hybrid pipeline combining three-dimensional (3D) iterative reconstruction and deep learning (DL) improves image quality of fast knee MRI while maintaining diagnostic performance for meniscal injuries via Stoller grading. Methods This retrospective study included 116 patients with suspected knee lesions (53 males, 63 females; mean age 53.7±16.9 years). All underwent conventional T1WI and PDWI, and accelerated sequences (GRAPPA factor: T1WI =3, PDWI =2). Accelerated data were processed with standard GRAPPA reconstruction (‘Fast’ group) and with a commercial software (iQMR™) integrating iterative reconstruction and a DL enhancement module (‘After Processing’ group). Two radiologists qualitatively evaluated overall image quality using a 5-point Likert scale. SNR and contrast-to-noise ratio (CNR) were quantitatively compared. Meniscal injuries were graded using the Stoller classification. Inter-reader agreement was assessed using weighted Kappa and intraclass correlation coefficient (ICC). Results Scan times for fast T1WI and PDWI were reduced by 66.3% (from 92 to 31 s, P<0.001) and 66.5% (from 158 to 53 s, P<0.001), respectively. The ‘After Processing’ group showed significantly higher qualitative image quality scores compared to the ‘Fast’ group (P<0.05), and was comparable to conventional sequences. Quantitatively, SNR in the ‘After Processing’ group was significantly improved over the ‘Fast’ group (e.g., Patellar cartilage T1WI-SNR: 84.9 vs. 70.3, P<0.05) and reached levels comparable to conventional sequences. No significant differences in CNR were found among the three groups (P>0.05). For the 85 patients with meniscal tears, Stoller grading showed almost perfect inter-reader agreement between conventional and ‘After Processing’ images (Kappa: 0.767–0.914). No statistically significant differences in Stoller classification distributions were observed among the three groups (P>0.05). Conclusions The hybrid 3D iterative reconstruction and DL pipeline significantly improves image quality of accelerated knee MRI, achieving a ~66% scan time reduction while maintaining SNR/CNR and diagnostic consistency with conventional sequences. This approach enhances workflow efficiency and optimizes healthcare resource utilization, supporting its clinical application.

Image reconstruction in magnetic resonance imaging (MRI) and computed tomography (CT) is a mathematical process that generates images at many different angles around the patient. Image reconstruction has a fundamental impact on image quality. In recent years, the literature has focused on deep learning and its applications in medical imaging, particularly image reconstruction. Due to the performance of deep learning models in a wide variety of vision applications, a considerable amount of work has recently been carried out using image reconstruction in medical images. MRI and CT appear as the ultimate scientifically appropriate imaging mode for identifying and diagnosing different diseases in this ascension age of technology. This study demonstrates a number of deep learning image reconstruction approaches and a comprehensive review of the most widely used different databases. We also give the challenges and promising future directions for medical image reconstruction.

A publicly available dataset containing k-space data as well as Digital Imaging and Communications in Medicine image data of knee images for accelerated MR image reconstruction using machine learning is presented.

Abstract Medical image reconstruction aims to acquire high-quality medical images for clinical usage at minimal cost and risk to the patients. Deep learning and its applications in medical imaging, especially in image reconstruction have received considerable attention in the literature in recent years. This study reviews records obtained electronically through the leading scientific databases (Magnetic Resonance Imaging journal, Google Scholar, Scopus, Science Direct, Elsevier, and from other journal publications) searched using three sets of keywords: (1) Deep learning, image reconstruction, medical imaging; (2) Medical imaging, Deep learning, Image reconstruction; (3) Open science, Open imaging data, Open software. The articles reviewed revealed that deep learning-based reconstruction methods improve the quality of reconstructed images qualitatively and quantitatively. However, deep learning techniques are generally computationally expensive, require large amounts of training datasets, lack decent theory to explain why the algorithms work, and have issues of generalization and robustness. The challenge of lack of enough training datasets is currently being addressed by using transfer learning techniques.