Deep Learning Diagnosis and Classification of Rotator Cuff Tears on Shoulder MRI
BACKGROUND:Detection of rotator cuff tears, a common cause of shoulder disability, can be time-consuming and subject to reader variability. Deep learning (DL) has the potential to increase radiologist accuracy and consistency. PURPOSE:The aim of this study was to develop a prototype DL model for detection and classification of rotator cuff tears on shoulder magnetic resonance imaging into no tear, partial-thickness tear, or full-thickness tear. MATERIALS AND METHODS:This Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included a total of 11,925 noncontrast shoulder magnetic resonance imaging scans from 2 institutions, with 11,405 for development and 520 dedicated for final testing. A DL ensemble algorithm was developed that used 4 series as input from each examination: fluid-sensitive sequences in 3 planes and a sagittal oblique T1-weighted sequence. Radiology reports served as ground truth for training with categories of no tear, partial tear, or full-thickness tear. A multireader study was conducted for the test set ground truth, which was determined by the majority vote of 3 readers per case. The ensemble comprised 4 parallel 3D ResNet50 convolutional neural network architectures trained via transfer learning and then adapted to the targeted domain. The final tear-type prediction was determined as the class with the highest probability, after averaging the class probabilities of the 4 individual models. RESULTS:The AUC overall for supraspinatus, infraspinatus, and subscapularis tendon tears was 0.93, 0.89, and 0.90, respectively. The model performed best for full-thickness supraspinatus, infraspinatus, and subscapularis tears with AUCs of 0.98, 0.99, and 0.95, respectively. Multisequence input demonstrated higher AUCs than single-sequence input for infraspinatus and subscapularis tendon tears, whereas coronal oblique fluid-sensitive and multisequence input showed similar AUCs for supraspinatus tendon tears. Model accuracy for tear types and overall accuracy were similar to that of the clinical readers. CONCLUSIONS:Deep learning diagnosis of rotator cuff tears is feasible with excellent diagnostic performance, particularly for full-thickness tears, with model accuracy similar to subspecialty-trained musculoskeletal radiologists.
Deep Learning Reconstruction Enables Prospectively Accelerated Clinical Knee MRI
Background MRI is a powerful diagnostic tool with a long acquisition time. Recently, deep learning (DL) methods have provided accelerated high-quality image reconstructions from undersampled data, but it is unclear if DL image reconstruction can be reliably translated to everyday clinical practice. Purpose To determine the diagnostic equivalence of prospectively accelerated DL-reconstructed knee MRI compared with conventional accelerated MRI for evaluating internal derangement of the knee in a clinical setting. Materials and Methods A DL reconstruction model was trained with images from 298 clinical 3-T knee examinations. In a prospective analysis, patients clinically referred for knee MRI underwent a conventional accelerated knee MRI protocol at 3 T followed by an accelerated DL protocol between January 2020 and February 2021. The equivalence of the DL reconstruction of the images relative to the conventional images for the detection of an abnormality was assessed in terms of interchangeability. Each examination was reviewed by six musculoskeletal radiologists. Analyses pertaining to the detection of meniscal or ligament tears and bone marrow or cartilage abnormalities were based on four-point ordinal scores for the likelihood of an abnormality. Additionally, the protocols were compared with use of four-point ordinal scores for each aspect of image quality: overall image quality, presence of artifacts, sharpness, and signal-to-noise ratio. Results A total of 170 participants (mean age ± SD, 45 years ± 16; 76 men) were evaluated. The DL-reconstructed images were determined to be of diagnostic equivalence with the conventional images for detection of abnormalities. The overall image quality score, averaged over six readers, was significantly better (P < .001) for the DL than for the conventional images. Conclusion In a clinical setting, deep learning reconstruction enabled a nearly twofold reduction in scan time for a knee MRI and was diagnostically equivalent with the conventional protocol. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Roemer in this issue.
Artificial Intelligence-Driven Ultra-Fast Superresolution MRI: 10-Fold Accelerated Musculoskeletal Turbo Spin Echo MRI Within Reach
Magnetic resonance imaging (MRI) is the keystone of modern musculoskeletal imaging; however, long pulse sequence acquisition times may restrict patient tolerability and access. Advances in MRI scanners, coil technology, and innovative pulse sequence acceleration methods enable 4-fold turbo spin echo pulse sequence acceleration in clinical practice; however, at this speed, conventional image reconstruction approaches the signal-to-noise limits of temporal, spatial, and contrast resolution. Novel deep learning image reconstruction methods can minimize signal-to-noise interdependencies to better advantage than conventional image reconstruction, leading to unparalleled gains in image speed and quality when combined with parallel imaging and simultaneous multislice acquisition. The enormous potential of deep learning-based image reconstruction promises to facilitate the 10-fold acceleration of the turbo spin echo pulse sequence, equating to a total acquisition time of 2-3 minutes for entire MRI examinations of joints without sacrificing spatial resolution or image quality. Current investigations aim for a better understanding of stability and failure modes of image reconstruction networks, validation of network reconstruction performance with external data sets, determination of diagnostic performances with independent reference standards, establishing generalizability to other centers, scanners, field strengths, coils, and anatomy, and building publicly available benchmark data sets to compare methods and foster innovation and collaboration between the clinical and image processing community. In this article, we review basic concepts of deep learning-based acquisition and image reconstruction techniques for accelerating and improving the quality of musculoskeletal MRI, commercially available and developing deep learning-based MRI solutions, superresolution, denoising, generative adversarial networks, and combined strategies for deep learning-driven ultra-fast superresolution musculoskeletal MRI. This article aims to equip radiologists and imaging scientists with the necessary practical knowledge and enthusiasm to meet this exciting new era of musculoskeletal MRI.
New-Generation Low-Field Magnetic Resonance Imaging of Hip Arthroplasty Implants Using Slice Encoding for Metal Artifact Correction: First In Vitro Experience at 0.55 T and Comparison With 1.5 T
OBJECTIVES/OBJECTIVE:Despite significant progress, artifact-free visualization of the bone and soft tissues around hip arthroplasty implants remains an unmet clinical need. New-generation low-field magnetic resonance imaging (MRI) systems now include slice encoding for metal artifact correction (SEMAC), which may result in smaller metallic artifacts and better image quality than standard-of-care 1.5 T MRI. This study aims to assess the feasibility of SEMAC on a new-generation 0.55 T system, optimize the pulse protocol parameters, and compare the results with those of a standard-of-care 1.5 T MRI. MATERIALS AND METHODS/METHODS:Titanium (Ti) and cobalt-chromium total hip arthroplasty implants embedded in a tissue-mimicking American Society for Testing and Materials gel phantom were evaluated using turbo spin echo, view angle tilting (VAT), and combined VAT and SEMAC (VAT + SEMAC) pulse sequences. To refine an MRI protocol at 0.55 T, the type of metal artifact reduction techniques and the effect of various pulse sequence parameters on metal artifacts were assessed through qualitative ranking of the images by 3 expert readers while taking measured spatial resolution, signal-to-noise ratios, and acquisition times into consideration. Signal-to-noise ratio efficiency and artifact size of the optimized 0.55 T protocols were compared with the 1.5 T standard and compressed-sensing SEMAC sequences. RESULTS:Overall, the VAT + SEMAC sequence with at least 6 SEMAC encoding steps for Ti and 9 for cobalt-chromium implants was ranked higher than other sequences for metal reduction (P < 0.05). Additional SEMAC encoding partitions did not result in further metal artifact reductions. Permitting minimal residual artifacts, low magnetic susceptibility Ti constructs may be sufficiently imaged with optimized turbo spin echo sequences obviating the need for SEMAC. In cross-platform comparison, 0.55 T acquisitions using the optimized protocols are associated with 45% to 64% smaller artifacts than 1.5 T VAT + SEMAC and VAT + compressed-sensing/SEMAC protocols at the expense of a 17% to 28% reduction in signal-to-noise ratio efficiency. B1-related artifacts are invariably smaller at 0.55 T than 1.5 T; however, artifacts related to B0 distortion, although frequently smaller, may appear as signal pileups at 0.55 T. CONCLUSIONS:Our results suggest that new-generation low-field SEMAC MRI reduces metal artifacts around hip arthroplasty implants to better advantage than current 1.5 T MRI standard of care. While the appearance of B0-related artifacts changes, reduction in B1-related artifacts plays a major role in the overall benefit of 0.55 T.
How does a "Dry Tap" Impact the Accuracy of Preoperative Aspiration Results in Predicting Chronic PJI?
INTRODUCTION/BACKGROUND:Periprosthetic joint infection (PJI) after total hip arthroplasty (THA) is challenging to diagnose. We aimed to evaluate the impact of dry taps requiring saline lavage during preoperative intraarticular hip aspiration on the accuracy of diagnosing PJI before revision surgery. METHODS:A retrospective review was conducted for THA patients with suspected PJI who received an image-guided hip aspiration from May 2016 to February 2020. Musculoskeletal Infection Society (MSIS) diagnostic criteria for PJI were compared between patients who had dry tap (DT) versus successful tap (ST). Sensitivity and specificity of synovial markers were compared between the DT and ST groups. Concordance between preoperative and intraoperative cultures was determined for the two groups. RESULTS:In total, 335 THA patients met inclusion criteria. A greater proportion of patients in the ST group met MSIS criteria preoperatively (30.2%vs.8.3%, p<0.001). Patients in the ST group had higher rates of revision for PJI (28.4%vs.17.5%, p=0.026) and for any indication (48.4%vs.36.7%, p=0.039). MSIS synovial WBC count thresholds were more sensitive in the ST group (90.0%vs.66.7%). There was no difference in culture concordance (67.9%vs.65.9%,p=0.709), though the DT group had a higher rate of negative preoperative cultures followed by positive intraoperative cultures (85.7%vs.41.1%, p=0.047). CONCLUSION/CONCLUSIONS:Our results indicate that approximately one-third of patients have dry hip aspiration, and in these patients cultures are less predictive of intraoperative findings. This suggests that surgeons considering potential PJI after THA should apply extra scrutiny when interpreting negative results in patients who require saline lavage for hip joint aspiration.
Factors predicting hip joint aspiration yield or "dry taps" in patients with total hip arthroplasty
BACKGROUND:Image-guided joint aspirations used to assist the diagnosis of periprosthetic joint infection (PJI) may commonly result in a dry tap-or insufficient fluid for culture and cell count analysis. Dry tap aspirations are painful and invasive for patients and often utilize a subsequent saline lavage to obtain a microbiology sample. Currently, there is a paucity of the literature addressing predictors that could suggest whether a dry tap will occur. The purpose of this study was to examine the effects of various factors on "dry tap" occurrence in patients with suspected PJI following total hip arthroplasty (THA). METHODS:A retrospective review was performed among THA patients suspected for PJI who received image-guided joint aspiration procedures at our institution from May 2016 to February 2020. The procedural factors included the imaging modality used for aspiration, anatomic approach, needle gauge size used, and the presence of a trainee. The patient-specific factors included number of prior ipsilateral hip surgeries, femoral head size, ESR/CRP values, and BMI. RESULTS:In total, 336 patients met our inclusion criteria. One hundred and twenty hip aspirations resulted in a dry tap (35.7%) where the patients underwent a saline lavage. Among the procedural and patient-specific factors, none of the factors were found to be statistically different between the two cohorts nor conferred any greater odds of a dry tap occurring. CONCLUSION/CONCLUSIONS:No associations with dry tap occurrence were found among the procedural and patient-specific factors studied. Further research is needed to identify additional factors that may be more predictive of dry taps.
Machine learning risk prediction of mortality for patients undergoing surgery with perioperative SARS-CoV-2: the COVIDSurg mortality score
To support the global restart of elective surgery, data from an international prospective cohort study of 8492 patients (69 countries) was analysed using artificial intelligence (machine learning techniques) to develop a predictive score for mortality in surgical patients with SARS-CoV-2. We found that patient rather than operation factors were the best predictors and used these to create the COVIDsurg Mortality Score (https://covidsurgrisk.app). Our data demonstrates that it is safe to restart a wide range of surgical services for selected patients.
Artificial Intelligence for MR Image Reconstruction: An Overview for Clinicians
Artificial intelligence (AI) shows tremendous promise in the field of medical imaging, with recent breakthroughs applying deep-learning models for data acquisition, classification problems, segmentation, image synthesis, and image reconstruction. With an eye towards clinical applications, we summarize the active field of deep-learning-based MR image reconstruction. We review the basic concepts of how deep-learning algorithms aid in the transformation of raw k-space data to image data, and specifically examine accelerated imaging and artifact suppression. Recent efforts in these areas show that deep-learning-based algorithms can match and, in some cases, eclipse conventional reconstruction methods in terms of image quality and computational efficiency across a host of clinical imaging applications, including musculoskeletal, abdominal, cardiac, and brain imaging. This article is an introductory overview aimed at clinical radiologists with no experience in deep-learning-based MR image reconstruction and should enable them to understand the basic concepts and current clinical applications of this rapidly growing area of research across multiple organ systems.
Anterior shoulder instability in the aging population: MRI injury pattern and management
Background: Literature on glenohumeral dislocations has focused on younger patient populations due to high recurrence rates. However, the spectrum of injuries sustained in younger versus older patient populations is reported to be quite different. Objective: To describe MRI findings and management of anterior shoulder instability in the aging (â‰¥60 years) population. Methods: Shoulder MRIs of anterior glenohumeral dislocators aged â‰¥40 were subdivided into <60 or â‰¥60 age groups, and reviewed by two musculoskeletal radiologists for: Hill-Sachs lesion, other fracture, glenoid injury, capsulolabral injury, rotator cuff tear, muscle atrophy, and axillary nerve injury. Fischer exact and logistic regression evaluated for significant differences between cohorts, and inter-reader agreement was assessed. Surgical management was recorded, if available. Results: 104 shoulder MRIs (40-79 years, mean=58.3, 52 females, 52 males) were reviewed (N=54 age <60, N=50 age â‰¥60). Acute high-grade or full-thickness supraspinatus (64.0% vs. 37.0%, p=0.001), infraspinatus (28.0% vs. 14.8%, p=0.028), and subscapularis tears (22.0% vs. 3.7%, p=0.003) were more common in the â‰¥60 group. Hill-Sachs lesions were more common in the <60 group (81.5% vs. 62.0%, p=0.046). Greater tuberosity fractures were seen in 15.3% of the overall cohort, coracoid fractures in 4.8%, and axillary nerve injuries in 16.3%. Inter-reader concordance was 88.5-89.4% for rotator cuff tears, and 89.4-97.1% for osseous injury. The <60 group had rotator cuff repair in 11/37 subjects (29.7%), and labral repair in 11/37 (29.7%), while the â‰¥60 group underwent rotator cuff repair in 17/36 (47.2%), reverse shoulder arthroplasty in 6/36 (16.7%), and labral repair in 6/36 (16.7%). Conclusion: Radiologists should have a high index of suspicion for acute rotator cuff tears in anterior shoulder instability, especially in aging populations. Greater tuberosity or coracoid fractures and axillary nerve injury occur across all ages, while Hill-Sachs injuries are more common in younger patients. Clinical Impact: Acute, high-grade or full-thickness rotator cuff tears are seen with higher frequency in older populations after anterior glenohumeral dislocation in the elderly. Osseous and nerve injuries are important causes of patient morbidity that, if not carefully sought out, may be overlooked by the interpreting radiologist on routine imaging.
Using Deep Learning to Accelerate Knee MRI at 3T: Results of an Interchangeability Study
OBJECTIVE:Deep Learning (DL) image reconstruction has the potential to disrupt the current state of MR imaging by significantly decreasing the time required for MR exams. Our goal was to use DL to accelerate MR imaging in order to allow a 5-minute comprehensive examination of the knee, without compromising image quality or diagnostic accuracy. METHODS:A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multi-sequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. Following 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 1.88-fold acceleration compared to our standard two-fold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of 6 readers to detect internal derangement of the knee was compared for the clinical and DL-accelerated images. RESULTS:The study demonstrated a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would result in 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. CONCLUSIONS:An optimized DL model allowed for acceleration of knee images which performed interchangeably with standard images for the detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.