3D Convolutional Neural Networks for Detection and Severity Staging of Meniscus and PFJ Cartilage Morphological Degenerative Changes in Osteoarthritis and Anterior Cruciate Ligament Subjects

Overview

Journal J Magn Reson Imaging

Date 2018 Oct 12

PMID 30306701

Citations 48

Authors

Valentina Pedoia

Berk Norman

Sarah N Mehany

Matthew D Bucknor

Thomas M Link

Sharmila Majumdar

Affiliations

Soon will be listed here.

Abstract

Background: Semiquantitative assessment of MRI plays a central role in musculoskeletal research; however, in the clinical setting MRI reports often tend to be subjective and qualitative. Grading schemes utilized in research are not used because they are extraordinarily time-consuming and unfeasible in clinical practice.

Purpose: To evaluate the ability of deep-learning models to detect and stage severity of meniscus and patellofemoral cartilage lesions in osteoarthritis and anterior cruciate ligament (ACL) subjects.

Study Type: Retrospective study aimed to evaluate a technical development.

Population: In all, 1478 MRI studies, including subjects at various stages of osteoarthritis and after ACL injury and reconstruction.

Field Strength/sequence: 3T MRI, 3D FSE CUBE.

Assessment: Automatic segmentation of cartilage and meniscus using 2D U-Net, automatic detection, and severity staging of meniscus and cartilage lesion with a 3D convolutional neural network (3D-CNN).

Statistical Tests: Receiver operating characteristic (ROC) curve, specificity and sensitivity, and class accuracy.

Results: Sensitivity of 89.81% and specificity of 81.98% for meniscus lesion detection and sensitivity of 80.0% and specificity of 80.27% for cartilage were achieved. The best performances for staging lesion severity were obtained by including demographics factors, achieving accuracies of 80.74%, 78.02%, and 75.00% for normal, small, and complex large lesions, respectively.

Data Conclusion: In this study we provide a proof of concept of a fully automated deep-learning pipeline that can identify the presence of meniscal and patellar cartilage lesions. This pipeline has also shown potential in making more in-depth examinations of lesion subjects for multiclass prediction and severity staging.

Level Of Evidence: 2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:400-410.

Citing Articles

Considerations on Image Preprocessing Techniques Required by Deep Learning Models. The Case of the Knee MRIs.

Botnari A, Kadar M, Patrascu J Maedica (Bucur). 2024; 19(3):526-535.

PMID: 39553362 PMC: 11565144. DOI: 10.26574/maedica.2024.19.3.526.

Deep Learning for Automatic Knee Osteoarthritis Severity Grading and Classification.

Kinger S Indian J Orthop. 2024; 58(10):1458-1473.

PMID: 39324090 PMC: 11420401. DOI: 10.1007/s43465-024-01259-4.

Achieving high accuracy in meniscus tear detection using advanced deep learning models with a relatively small data set.

Gungor E, Vehbi H, Cansin A, Ertan M Knee Surg Sports Traumatol Arthrosc. 2024; 33(2):450-456.

PMID: 39015056 PMC: 11792105. DOI: 10.1002/ksa.12369.

Radiomics analysis using magnetic resonance imaging of bone marrow edema for diagnosing knee osteoarthritis.

Li X, Chen W, Liu D, Chen P, Li P, Li F Front Bioeng Biotechnol. 2024; 12:1368188.

PMID: 38933540 PMC: 11199411. DOI: 10.3389/fbioe.2024.1368188.

Artificial intelligence in musculoskeletal imaging: realistic clinical applications in the next decade.

Ruitenbeek H, Oei E, Visser J, Kijowski R Skeletal Radiol. 2024; 53(9):1849-1868.

PMID: 38902420 DOI: 10.1007/s00256-024-04684-6.

References

Lee H, Tajmir S, Lee J, Zissen M, Yeshiwas B, Alkasab T . Fully Automated Deep Learning System for Bone Age Assessment. J Digit Imaging. 2017; 30(4):427-441. PMC: 5537090. DOI: 10.1007/s10278-017-9955-8. View

Liu F, Zhou Z, Samsonov A, Blankenbaker D, Larison W, Kanarek A . Deep Learning Approach for Evaluating Knee MR Images: Achieving High Diagnostic Performance for Cartilage Lesion Detection. Radiology. 2018; 289(1):160-169. PMC: 6166867. DOI: 10.1148/radiol.2018172986. View

Chaudhari A, Fang Z, Kogan F, Wood J, Stevens K, Gibbons E . Super-resolution musculoskeletal MRI using deep learning. Magn Reson Med. 2018; 80(5):2139-2154. PMC: 6107420. DOI: 10.1002/mrm.27178. View

Kim M, Banerjee S, Park S, Pathak J . Improving risk prediction for depression via Elastic Net regression - Results from Korea National Health Insurance Services Data. AMIA Annu Symp Proc. 2017; 2016:1860-1869. PMC: 5333336. View

Shelhamer E, Long J, Darrell T . Fully Convolutional Networks for Semantic Segmentation. IEEE Trans Pattern Anal Mach Intell. 2016; 39(4):640-651. DOI: 10.1109/TPAMI.2016.2572683. View

Crawford R, Walley G, Bridgman S, Maffulli N . Magnetic resonance imaging versus arthroscopy in the diagnosis of knee pathology, concentrating on meniscal lesions and ACL tears: a systematic review. Br Med Bull. 2007; 84:5-23. DOI: 10.1093/bmb/ldm022. View

Liu W, Li Q . An Efficient Elastic Net with Regression Coefficients Method for Variable Selection of Spectrum Data. PLoS One. 2017; 12(2):e0171122. PMC: 5289531. DOI: 10.1371/journal.pone.0171122. View

Caner M, Zhang H . Adaptive Elastic Net for Generalized Methods of Moments. J Bus Econ Stat. 2014; 32(1):30-47. PMC: 3932067. DOI: 10.1080/07350015.2013.836104. View

Norman B, Pedoia V, Majumdar S . Use of 2D U-Net Convolutional Neural Networks for Automated Cartilage and Meniscus Segmentation of Knee MR Imaging Data to Determine Relaxometry and Morphometry. Radiology. 2018; 288(1):177-185. PMC: 6013406. DOI: 10.1148/radiol.2018172322. View

10.

Litjens G, Kooi T, Bejnordi B, Setio A, Ciompi F, Ghafoorian M . A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42:60-88. DOI: 10.1016/j.media.2017.07.005. View

11.

Link T, Steinbach L, Ghosh S, Ries M, Lu Y, Lane N . Osteoarthritis: MR imaging findings in different stages of disease and correlation with clinical findings. Radiology. 2003; 226(2):373-81. DOI: 10.1148/radiol.2262012190. View

12.

Dolz J, Desrosiers C, Ben Ayed I . 3D fully convolutional networks for subcortical segmentation in MRI: A large-scale study. Neuroimage. 2017; 170:456-470. DOI: 10.1016/j.neuroimage.2017.04.039. View

13.

Fang L, Zhang L, Nie D, Cao X, Bahrami K, He H . Brain Image Labeling Using Multi-atlas Guided 3D Fully Convolutional Networks. Patch Based Tech Med Imaging (2017). 2017; 10530:12-19. PMC: 5669261. DOI: 10.1007/978-3-319-67434-6_2. View

14.

Joseph G, Hou S, Nardo L, Heilmeier U, Nevitt M, McCulloch C . MRI findings associated with development of incident knee pain over 48 months: data from the osteoarthritis initiative. Skeletal Radiol. 2016; 45(5):653-60. PMC: 4815898. DOI: 10.1007/s00256-016-2343-5. View

15.

Waldmann P, Meszaros G, Gredler B, Fuerst C, Solkner J . Evaluation of the lasso and the elastic net in genome-wide association studies. Front Genet. 2013; 4:270. PMC: 3850240. DOI: 10.3389/fgene.2013.00270. View

16.

Kallenberg M, Petersen K, Nielsen M, Ng A, Diao P, Igel C . Unsupervised Deep Learning Applied to Breast Density Segmentation and Mammographic Risk Scoring. IEEE Trans Med Imaging. 2016; 35(5):1322-1331. DOI: 10.1109/TMI.2016.2532122. View

17.

Zhao G, Liu F, Oler J, Meyerand M, Kalin N, Birn R . Bayesian convolutional neural network based MRI brain extraction on nonhuman primates. Neuroimage. 2018; 175:32-44. PMC: 6095475. DOI: 10.1016/j.neuroimage.2018.03.065. View

18.

Liu F, Zhou Z, Jang H, Samsonov A, Zhao G, Kijowski R . Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging. Magn Reson Med. 2017; 79(4):2379-2391. PMC: 6271435. DOI: 10.1002/mrm.26841. View

19.

Huang L, Xia W, Zhang B, Qiu B, Gao X . MSFCN-multiple supervised fully convolutional networks for the osteosarcoma segmentation of CT images. Comput Methods Programs Biomed. 2017; 143:67-74. DOI: 10.1016/j.cmpb.2017.02.013. View

20.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View