BackgroundMagnetic resonance imaging (MRI) of the knee is the preferred method for diagnosing knee injuries. However, interpretation of knee MRI is time-intensive and subject to diagnostic error and variability. An automated system for interpreting knee MRI could prioritize high-risk patients and assist clinicians in making diagnoses. Deep learning methods, in being able to automatically learn layers of features, are well suited for modeling the complex relationships between medical images and their interpretations. In this study we developed a deep learning model for detecting general abnormalities and specific diagnoses (anterior cruciate ligament [ACL] tears and meniscal tears) on knee MRI exams. We then measured the effect of providing the model’s predictions to clinical experts during interpretation.Methods and findingsOur dataset consisted of 1,370 knee MRI exams performed at Stanford University Medical Center between January 1, 2001, and December 31, 2012 (mean age 38.0 years; 569 [41.5%] female patients). The majority vote of 3 musculoskeletal radiologists established reference standard labels on an internal validation set of 120 exams. We developed MRNet, a convolutional neural network for classifying MRI series and combined predictions from 3 series per exam using logistic regression. In detecting abnormalities, ACL tears, and meniscal tears, this model achieved area under the receiver operating characteristic curve (AUC) values of 0.937 (95% CI 0.895, 0.980), 0.965 (95% CI 0.938, 0.993), and 0.847 (95% CI 0.780, 0.914), respectively, on the internal validation set. We also obtained a public dataset of 917 exams with sagittal T1-weighted series and labels for ACL injury from Clinical Hospital Centre Rijeka, Croatia. On the external validation set of 183 exams, the MRNet trained on Stanford sagittal T2-weighted series achieved an AUC of 0.824 (95% CI 0.757, 0.892) in the detection of ACL injuries with no additional training, while an MRNet trained on the rest of the external data achieved an AUC of 0.911 (95% CI 0.864, 0.958). We additionally measured the specificity, sensitivity, and accuracy of 9 clinical experts (7 board-certified general radiologists and 2 orthopedic surgeons) on the internal validation set both with and without model assistance. Using a 2-sided Pearson’s chi-squared test with adjustment for multiple comparisons, we found no significant differences between the performance of the model and that of unassisted general radiologists in detecting abnormalities. General radiologists achieved significantly higher sensitivity in detecting ACL tears (p-value = 0.002; q-value = 0.019) and significantly higher specificity in detecting meniscal tears (p-value = 0.003; q-value = 0.019). Using a 1-tailed t test on the change in performance metrics, we found that providing model predictions significantly increased clinical experts’ specificity in identifying ACL tears (p-value < 0.001; q-value = 0.006). The primary limitations of our study include lack of surgical ground truth and the small size of ...
The purpose of this in vivo study was to analyze the short-term tissue response of joint capsule to monopolar radiofrequency energy and to compare the effects of five power settings at 65 degrees C on heat distribution in joint capsule. In 12 mature Hampshire sheep, the medial and lateral aspects of both stifles were treated with monopolar radiofrequency energy under arthroscopic control in a single uniform pass to the synovial surface. The radiofrequency generator power settings were 0, 10, 15, 20, 25, and 30 watts (N = 8/group). The electrode tip temperature was 65 degrees C. Histologic analysis at 7 days after surgery revealed thermal damage of capsule at all radiofrequency power settings. The lesion's cross-sectional area, depth, vascularity, and inflammation were commensurate with radiofrequency power. Tissue damage was indicated by variable inflammatory cell infiltration, fusion of collagen, pyknosis of fibroblasts, myonecrosis, and vascular thrombosis, whereas synovial hyperplasia, fibroblast proliferation, and rowing of sarcolemmal nuclei demonstrated regenerative processes. This study revealed that radiofrequency power settings and heat loss through lavage solution play a significant role in heat distribution and morphologic alterations in joint capsule after arthroscopic application of monopolar radiofrequency energy.
Eighteen males and two females (mean age, 26.5 years) underwent biomechanical assessment and Cybex evaluation prior to ACL reconstruction. Clinically, all patients had at least a 1+ grade with the Lachman, anterior drawer, and pivot shift tests, the majority being graded as 2+. Footswitch, high speed photography, force plate, and indwelling wire electrode data were collected while each subject performed free and fast walking, running, cutting, and stair climbing activities. During walking, single limb support times did not differ between the subject's involved and uninvolved limbs. Knee joint angles were similar between limbs during walking, running, and stair climbing maneuvers. Dynamic EMG tracings during walking demonstrated similar quadriceps and calf activity between limbs, while greater variation in hamstring firing was evident among subjects. During running, the involved limb had a longer duration of medial hamstring activity compared to the lateral hamstring. No significant differences were seen in either vertical or sagittal shear forces during free walking. During fast walking, higher midstance vertical forces (F2) were present in the involved limb (P less than 0.05). During running, the involved limb experienced lower vertical forces (P less than 0.05), while both anterior and posterior sagittal shear differences were insignificant. Straight cut maneuvers demonstrated significantly lower lateral shear and vertical forces in the involved limb (P less than 0.05). Lower lateral and sagittal shear forces in the involved limb (P less than 0.01 and P less than 0.05, respectively), combined with a reduced angle of the cut during the cross-cut maneuver, may be the first means to assess the functional pivot shift phenomenon ever documented.(ABSTRACT TRUNCATED AT 250 WORDS)
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.