Purpose
To calculate the diagnostic accuracy from the confusion matrix using deep learning
(DL) on ultrasound (US) images of Palmer 1B triangular fibrocartilage complex (TFCC)
injury.
Methods
Twenty-nine wrists of 15 healthy volunteers (11 men; mean age, 34.9 years ± 9.7) (control
group) and 20 wrists of 17 patients (11 men; mean age 41.0 years ± 12.2) with TFCC
injury (Palmer type IB) (injury group) were included in the study. The diagnosis of
Palmer 1B TFCC injury was made using magnetic resonance imaging, computed tomography
arthrography, and intraoperative arthroscopic findings. In total, 2,000 images were
provided to each group, 80% of which were randomly selected by AI and used as training
data; the remaining data were used as test data. Transfer learning was conducted using
a pretrained 3 separate models (GoogLeNet, ResNet50, ResNet101). Model evaluation
was performed using a confusion matrix. The area under a receiver operating characteristic
curve was also calculated. The occlusion sensitivity was used to visualize the important
features.
Results
For the prediction of TFCC injury by the DL model, the best score of accuracy was
0.85 in GoogLeNet, a recall was 1.0 in ResNet50 and ResNet101, and a specificity was
0.78 in GoogLeNet. In predicting the TFCC injury for the test data, the best score
of the AUC was 0.97 on ResNet101. Visualization of important features showed that
AI predicted the presence of injury by focusing on the morphology of the articular
disc.
Conclusions
US images using the DL model predicted Palmer 1B TFCC injury with high accuracy, with
the best scores of 0.85 for accuracy on GoogLeNet, 1.00 for sensitivity on ResNet50
and ResNet101, and 0.78 for specificity on GoogLeNet. The use of DL for US imaging
of Palmer 1B TFCC injury predicted the injury as well as magnetic resonance imaging
and computed tomography arthrography
Level of Evidence
IV; retrospective case series study.
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to ArthroscopyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- The triangular fibrocartilage complex of the wrist—Anatomy and function.J Hand Surg. 1981; 6: 153-162
- New advances in wrist arthroscopy.Arthroscopy. 2008; 24: 355-367
- TFCC injuries: Meta-Analysis and comparison of diagnostic imaging modalities.J Wrist Surg. 2018; 7: 267-272
- Ultrasound measurement of median nerve cross-sectional area at the inlet and outlet of carpal tunnel after carpal tunnel release compared to electrodiagnostic findings.Arch Orthop Trauma Surg. 2016; 136: 1325-1330
- Ulnar wrist pain revisited: Ultrasound diagnosis and guided injection for triangular fibrocartilage complex injuries.J Clin Med. 2019; 8: 1540
- Motion analysis of triangular fibrocartilage complex by using ultrasonography images: Preliminary analysis.Sensors (Basel). 2022; 22
- Clinical and research medical applications of artificial intelligence.Arthroscopy. 2021; 37: 1694-1697
- Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning.IEEE Trans Med Imaging. 2016; 35: 1285-1298
- A survey of deep-learning applications in ultrasound: Artificial intelligence-powered ultrasound for improving clinical workflow.J Am Coll Radiol. 2019; 16: 1318-1328
- Diagnostic performance of artificial intelligence for detection of anterior cruciate ligament and meniscus tears: A systematic review.Arthroscopy. 2021; 37: 771-781
- Precise proximal femur fracture classification for interactive training and surgical planning.Int J Comput Assist Radiol Surg. 2020; 15: 847-857
- Covid-19 detection via deep neural network and occlusion sensitivity maps.Alexandria Engineering J. 2021; 60: 4829-4855
- Magician’s corner: 6. TensorFlow and TensorBoard.Radiol Artif Intell. 2020; 2e200012
- Learning deep features for discriminative localization.in: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016: 2921-2929
- Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: discriminating malignant parotid tumors in MRI.Sci Rep. 2020; 10: 19388
- A comparison of CT arthrography of the wrist to findings during wrist arthroscopy.J Hand Surg Am. 2007; 32: 834-841
- Comparison of 3-T MRI and arthroscopy of intrinsic wrist ligament and TFCC tears.AJR Am J Roentgenol. 2009; 192: 80-85
- Intrinsic ligament and triangular fibrocartilage complex (TFCC) tears of the wrist: Comparison of isovolumetric 3D-THRIVE sequence MR arthrography and conventional MR image at 3 T.Magn Reson Imaging. 2013; 31: 221-226
- Chronic wrist pain: Spin-echo and short tau inversion recovery MR imaging and conventional and MR arthrography.Radiology. 1992; 182: 205-211
- Automated abdominal segmentation of CT scans for body composition analysis using deep learning.Radiology. 2019; 290: 669-679
- Editorial Commentary: Personalized hip arthroscopy outcome prediction using machine learning—the future is here.Arthroscopy. 2021; 37: 1498-1502
- Deep learning with non-medical training used for chest pathology identification.in: Proc. SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis. 20 March 2015: 94140V
- Covid-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks.Phys Eng Sci Med. 2020; 43: 635-640
- Artificial intelligence for analyzing orthopedic trauma radiographs.Acta Orthop. 2017; 88: 581-586
- Deep convolutional neural network-based diagnosis of anterior cruciate ligament tears: Performance comparison of homogenous versus heterogeneous knee MRI cohorts with different pulse sequence protocols and 1.5-T and 3-T magnetic field strengths.Invest Radiol. 2020; 55: 499-506
- A pre-trained convolutional neural network based method for thyroid nodule diagnosis.Ultrasonics. 2017; 73: 221-230
- Diagnostic efficiency of the breast ultrasound computer-aided prediction model based on convolutional neural network in breast cancer.J Digit Imaging. 2020; 33: 1218-1223
- Deep learning approach for anterior cruciate ligament lesion detection: Evaluation of diagnostic performance using arthroscopy as the reference standard.J Magn Reson Imaging. 2020; 52: 1745-1752
- Artifact removal using improved GoogLeNet for sparse-view CT reconstruction.Sci Rep. 2018; 8: 6700
Keles A, Keles MB, Keles A. COV19-CNNet and COV19-ResNet: Diagnostic inference engines for early detection of COVID-19 [published online January 1, 2021]. Cognit Comput. doi: 10.1007/s12559-020-09795-5
- Weakly-supervised deep learning for ultrasound diagnosis of breast cancer.Sci Rep. 2021; 11: 24382
- EfficientNet: Rethinking model scaling for convolutional neural networks.arXiv, 2019, 2019 (ICML)
- Grad-CAM: Visual explanations from deep networks via gradient-based localization.IEEE I Conf Comp Vis. 2017; : 618-626
- Detection of COVID-19 patients from CT scan and chest x-ray data using modified MobileNetV2 and LIME.Healthcare (Basel). 2021; 9
- A reliable, ultrasound-based method for the diagnosis of discoid lateral meniscus.Arthroscopy. 2021; 37: 882-890
Article info
Publication history
Published online: May 09, 2022
Accepted:
March 28,
2022
Received:
September 30,
2021
Footnotes
See commentary on page 2425
The authors report the following potential conflicts of interest or sources of funding: R.K. reports personal fees from Medacta International, personal fees from Arthrex, personal fees from Japan Tissue Engineering Co., Ltd., personal fees from Hirosaki Life Science Innovation, grants and personal fees from Stryker Japan K.K., grants and personal fees from Zimmer Biomet G.K., grants and personal fees from Smith & Nephew K.K., grants and personal fees from Johnson & JohnsonJohnson & Johnson K.K., and grants from Japan Medical Dynamic Marketing, outside the submitted work. ICMJE author disclosure forms are available for this article online, as supplementary material.
Identification
Copyright
© 2022 by the Arthroscopy Association of North America
