Dataset Information

Deep Learning for Hierarchical Severity Staging of Anterior Cruciate Ligament Injuries from MRI.

ABSTRACT: Purpose:To evaluate the diagnostic utility of two convolutional neural networks (CNNs) for severity staging of anterior cruciate ligament (ACL) injuries. Materials and Methods:In this retrospective study, 1243 knee MR images (1008 intact, 18 partially torn, 77 fully torn, and 140 reconstructed ACLs) from 224 patients (mean age, 47 years ± 14 [standard deviation]; 54% women) were analyzed. The MRI examinations were performed between 2011 and 2014. A modified scoring metric was used. Classification of ACL injuries using deep learning involved use of two types of CNN, one with three-dimensional (3D) and the other with two-dimensional (2D) convolutional kernels. Performance metrics included sensitivity, specificity, weighted Cohen κ, and overall accuracy, and the McNemar test was used to compare the performance of the CNNs. Results:The overall accuracies for ACL injury classification using the 3D CNN and 2D CNN were 89% (225 of 254) and 92% (233 of 254), respectively (P = .27), and both CNNs had a weighted Cohen κ of 0.83. The 2D CNN and 3D CNN performed similarly in classifying intact ACLs (2D CNN, sensitivity of 93% [188 of 203] and specificity of 90% [46 of 51] vs 3D CNN, sensitivity of 89% [180 of 203] and specificity of 88% [45 of 51]). Classification of full tears by both networks was also comparable (2D CNN, sensitivity of 82% [14 of 17] and specificity of 94% [222 of 237] vs 3D CNN, sensitivity of 76% [13 of 17] and specificity of 100% [236 of 237]). The 2D CNN classified all reconstructed ACLs correctly. Conclusion:Two-dimensional and 3D CNNs applied to ACL lesion classification had high sensitivity and specificity, suggesting that these networks could be used to help nonexperts grade ACL injuries. Supplemental material is available for this article. © RSNA, 2020.

SUBMITTER: Namiri NK

PROVIDER: S-EPMC7392061 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Purpose: To develop and evaluate a deep learning-based method to localize and classify anterior cruciate ligament (ACL) ruptures on knee MR images by using arthroscopy as the reference standard. Methods: We proposed a fully automated ACL rupture localization system to localize and classify ACL ruptures. The classification of ACL ruptures was based on the projection coordinates of the ACL rupture point on the line connecting the center coordinates of the femoral and tibial footprints. The line was divided into three equal parts and the position of the projection coordinates indicated the classification of the ACL ruptures (femoral side, middle and tibial side). In total, 85 patients (mean age: 27; male: 56) who underwent ACL reconstruction surgery under arthroscopy were included. Three clinical readers evaluated the datasets separately and their diagnostic performances were compared with those of the model. The performance metrics included the accuracy, error rate, sensitivity, specificity, precision, and F1-score. A one-way ANOVA was used to evaluate the performance of the convolutional neural networks (CNNs) and clinical readers. Intraclass correlation coefficients (ICC) were used to assess interobserver agreement between the clinical readers. Results: The accuracy of ACL localization was 3.77 ± 2.74 and 4.68 ± 3.92 (mm) for three-dimensional (3D) and two-dimensional (2D) CNNs, respectively. There was no significant difference in the ACL rupture location performance between the 3D and 2D CNNs or among the clinical readers (Accuracy, p < 0.01). The 3D CNNs performed best among the five evaluators in classifying the femoral side (sensitivity of 0.86 and specificity of 0.79), middle side (sensitivity of 0.71 and specificity of 0.84) and tibial side ACL rupture (sensitivity of 0.71 and specificity of 0.99), and the overall accuracy for sides classifying of ACL rupture achieved 0.79. Conclusion: The proposed deep learning-based model achieved high diagnostic performances in locating and classifying ACL fractures on knee MR images.

Project description:PurposeTo assess failure rate, outcomes, and patient satisfaction in patients who underwent anterior cruciate ligament (ACL) repair with suture augmentation for clinical instability and proximal avulsion of the ACL.MethodsWe retrospectively reviewed consecutive suture-augmented ACL repairs performed by a single surgeon between January 2014 and June 2016 for proximal ACL avulsion. Patients were included if they were at least 24 months postoperative from repair surgery. Patients were excluded from the study if they underwent primary ACL reconstruction instead of repair or if they had a concomitant multiligamentous knee injury. Knee Injury and Osteoarthritis Outcome Score (KOOS), visual analog scale (VAS), Veterans RAND-12 (VR-12), Marx Activity, and Single Assessment Numeric Evaluation data were collected.ResultsOf 172 patients who underwent ACL surgery between January 2014 and June 2016, 28 (16%) with Sherman type I or II ACL tears or high-grade partial avulsion with clinical instability underwent ACL repair with suture augmentation. One patient was not available for follow-up. The 27 patients were age 27.4 ± 8.6 years, 18 males (66.7%), and 2.8 ± 0.7 years follow-up (range, 2.0-3.8 years). Of these 27 patients, 4 recurrent ACL injuries (14.8%) required revision to reconstruction. The remaining 23 patients had successful ACL repair with no clinical instability and no subjective complaints at final follow-up. Final scores were KOOS 83.7 ± 12.8, Marx 8.6 ± 4.0, VAS 1.1 ± 1.8, physical VR-12 53.6 ± 5.2, mental VR-12 53.1 ± 8.1, and Single Assessment Numeric Evaluation 83.0 ± 12.9. In the 11 patients with baseline data, significant improvements were observed in composite KOOS (50.4 ± 11.5 to 85.7 ± 8.4; P < .001; VAS: 3.9 ± 2.6 to 0.8 ± 0.8; P = .002; and physical VR-12: 39.9 ± 6.5 to 55.5 ± 3.3; P < .001). All 11 patients (100%) met or exceeded the KOOS composite minimum clinically important difference (mean 34.0 increase).ConclusionsIn patients with proximal ACL avulsion, arthroscopic primary ACL repair with suture augmentation demonstrated high functional outcome and improved patient-reported outcomes at 2-year follow-up. The rate of graft failure was 15%.Level of evidenceLevel IV, therapeutic case series.

Project description:PurposeTo investigate the feasibility of using a deep learning-based approach to detect an anterior cruciate ligament (ACL) tear within the knee joint at MRI by using arthroscopy as the reference standard.Materials and methodsA fully automated deep learning-based diagnosis system was developed by using two deep convolutional neural networks (CNNs) to isolate the ACL on MR images followed by a classification CNN to detect structural abnormalities within the isolated ligament. With institutional review board approval, sagittal proton density-weighted and fat-suppressed T2-weighted fast spin-echo MR images of the knee in 175 subjects with a full-thickness ACL tear (98 male subjects and 77 female subjects; average age, 27.5 years) and 175 subjects with an intact ACL (100 male subjects and 75 female subjects; average age, 39.4 years) were retrospectively analyzed by using the deep learning approach. Sensitivity and specificity of the ACL tear detection system and five clinical radiologists for detecting an ACL tear were determined by using arthroscopic results as the reference standard. Receiver operating characteristic (ROC) analysis and two-sided exact binomial tests were used to further assess diagnostic performance.ResultsThe sensitivity and specificity of the ACL tear detection system at the optimal threshold were 0.96 and 0.96, respectively. In comparison, the sensitivity of the clinical radiologists ranged between 0.96 and 0.98, while the specificity ranged between 0.90 and 0.98. There was no statistically significant difference in diagnostic performance between the ACL tear detection system and clinical radiologists at P < .05. The area under the ROC curve for the ACL tear detection system was 0.98, indicating high overall diagnostic accuracy.ConclusionThere was no significant difference between the diagnostic performance of the ACL tear detection system and clinical radiologists for determining the presence or absence of an ACL tear at MRI.© RSNA, 2019Supplemental material is available for this article.

Dataset Information

Deep Learning for Hierarchical Severity Staging of Anterior Cruciate Ligament Injuries from MRI.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets