i-manager Publications

Deep Learning MRI Analysis for Automated Knee Injury Diagnosis

Akshath Kamath*, Ambar Gharat**, Supriya Alavala***, Snehal Patil****

* PwC, India.

** Capgemini, India.

*** HashedIn by Deloitte, Bengaluru, Karnataka, India.

**** Department of Computer Science Engineering, Pimpri Chinchwad College of Engineering and Research, Ravet, Pune, Maharashtra, India.

Periodicity:July - September'2023
DOI : https://doi.org/10.26634/jcom.11.2.20132

Abstract

Magnetic Resonance Imaging (MRI) plays a pivotal role in non-invasively diagnosing knee injuries. This research focuses on cost-effective, efficient solutions for enhancing automated knee injury detection in MRI scans. The study aims to boost diagnostic accuracy for abnormalities, Anterior Cruciate Ligament (ACL) tears, and meniscal tears using advanced deep learning techniques. Transfer learning is employed, combining pretrained neural networks with transfer models. AlexNet and SqueezeNet are explored as feature extraction architectures, assessing the attention mechanism and maxpooling for sequence reduction. This yields four models, MRNet, MRNet-Squeeze, MRNet-Attend, and MRNet- SqueezeAttend. The primary evaluation metric is the Area Under the ROC Curve (AUC), providing a comprehensive assessment by averaging AUC scores for abnormal, ACL tear, and meniscus tear labels. The initial MRNet achieves the highest AUC (0.940) for anomaly detection, while MRNet-Squeeze excels in diagnosing ACL damage. MRNet- SqueezeAttend achieves the highest AUC (0.885) for meniscus tears. The ensemble of all four models outperforms individual models with an outstanding average AUC of 0.931. Each model exhibits unique strengths. MRNet excels at spotting anomalies, MRNet-Squeeze accurately detects ACL tears, and MRNet-SqueezeAttend excels in identifying meniscal tears. Notably, the ensemble leverages these diverse strengths to deliver cutting-edge results for all injury types. Further investigation reveals varying correlations between model-specific predictions and different diagnosis or sequence combinations. Scrutinizing the MRI sequence frames capturing the models' attention identifies key contributors to the diagnosis.

Keywords

Deep Learning, MRI Analysis, Knee Injury Diagnosis, Automated Diagnosis, Pre-trained Neural Networks, MRI Scan.

How to Cite this Article?

Kamath, A., Gharat, A., Alavala, S., and Patil, S. (2023). Deep Learning MRI Analysis for Automated Knee Injury Diagnosis. i-manager’s Journal on Computer Science, 11(2), 19-29. https://doi.org/10.26634/jcom.11.2.20132

References

[1]. Agoes, A. S., Hu, Z., & Matsunaga, N. (2017, August). Fine tuning based squeezenet for vehicle classification. In Proceedings of the International Conference on Advances in Image Processing (pp. 14-18).

[2]. Alkadi, R., El-Baz, A., Taher, F., & Werghi, N. (2018). A 2.5 D deep learning-based approach for prostate cancer detection on T2-weighted magnetic resonance imaging. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops.

[3]. Bien, N., Rajpurkar, P., Ball, R. L., Irvin, J., Park, A., Jones, E., & Lungren, M. P. (2018). Deep-learning-assisted diagnosis for knee magnetic resonance imaging: Development and retrospective validation of MRNet. Plos Medicine, 15(11), e1002699.

[4]. Boeve, B. F., Davidson, R. A., & Staab Jr, E. V. (1991). Magnetic resonance imaging in the evaluation of knee injuries. Southern Medical Journal, 84(9), 1123-1127.

[5]. Deng, J., Dong, W., Socher, R., Li, L. J., Li, K., & Fei-Fei, L. (2009, June). Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition (pp. 248-255). IEEE.

[6]. Durmuş, H., Güneş, E. O., & Kırcı, M. (2017, August). Disease detection on the leaves of the tomato plants by using deep learning. In 2017 6th International Conference on Agro-Geoinformatics (pp. 1-5). IEEE.

[7]. Felli, L., Garlaschi, G., Muda, A., Tagliafico, A., Formica, M., Zanirato, A., & Alessio-Mazzola, M. (2016). Comparison of clinical, MRI and arthroscopic assessments of chronic ACL injuries, meniscal tears and cartilage defects. Musculoskeletal Surgery, 100(3), 231-238.

[8]. Figueiredo, S., Castelo, L. S., Pereira, A. D., Machado, L., Silva, J. A., & Sa, A. (2018). Use of MRI by radiologists and orthopaedic surgeons to detect intra-articular injuries of the knee. Revista Brasileira de Ortopedia, 53(1), 28-32.

[9]. Grøvik, E., Yi, D., Iv, M., Tong, E., Rubin, D., & Zaharchuk, G. (2020). Deep learning enables automatic detection and segmentation of brain metastases on multisequence MRI. Journal of Magnetic Resonance Imaging, 51(1), 175-182.

[10]. Han, L., & Kamdar, M. R. (2018). MRI to MGMT: Predicting methylation status in glioblastoma patients using convolutional recurrent neural networks. In Pacific Symposium on Biocomputing 2018: Proceedings of the Pacific Symposium (pp. 331-342).

[11]. Hosseini-Asl, E., Gimel'farb, G., & El-Baz, A. (2016). Alzheimer's disease diagnostics by a deeply supervised adaptable 3D convolutional network. arXiv.

[12]. Iandola, F. N., Han, S., Moskewicz, M. W., Ashraf, K., Dally, W. J., & Keutzer, K. (2016). SqueezeNet: AlexNetlevel accuracy with 50x fewer parameters and < 0.5 MB model size. arXiv.

[13]. Júnior, N.O., Leão, M. G. D. S., & Oliveira, N. H. C. D. (2015). Diagnosis of knee injuries: Comparison of the physical examination and magnetic resonance imaging with the findings from arthroscopy. Revista Brasileira De Ortopedia, 50(6), 712-719.

[14]. Khvostikov, A., Aderghal, K., Benois-Pineau, J., Krylov, A., & Catheline, G. (2018). 3D CNN-based classification using sMRI and MD-DTI images for Alzheimer disease studies. arXiv.

[15]. Kolata, G. (2011, October 28). Sports medicine said to overuse MRI's. The New York Times (pp. 1-2).

[16]. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25.

[17]. Lin, M., Chen, Q., & Yan, S. (2013). Network in network. arXiv.

[18]. Luong, M. T., Pham, H., & Manning, C. D. (2015). Effective approaches to attention-based neural machine translation. arXiv.

[19]. Oliphant, T. E. (2006). Guide to NumPy. Trelgol Publishing, USA.

[20]. Qian, X., Patton, E. W., Swaney, J., Xing, Q., & Zeng, T. (2018, October). Machine learning on cataracts classification using SqueezeNet. In 2018 4th International Conference on Universal Village (UV) (pp. 1-3). IEEE.

[21]. Qin, C., Schlemper, J., Caballero, J., Price, A. N., Hajnal, J. V., & Rueckert, D. (2018). Convolutional recurrent neural networks for dynamic MR image reconstruction. IEEE Transactions on Medical Imaging, 38(1), 280-290.

[22]. Roth, H. R., Lu, L., Liu, J., Yao, J., Seff, A., Cherry, K., & Summers, R. M. (2015). Improving computer-aided detection using convolutional neural networks and random view aggregation. IEEE Transactions on Medical Imaging, 35(5), 1170-1181.

[23]. Smith, T. O., Lewis, M., Song, F., Toms, A. P., Donell, S. T., & Hing, C. B. (2012). The diagnostic accuracy of anterior cruciate ligament rupture using magnetic resonance imaging: A meta-analysis. European Journal of Orthopaedic Surgery & Traumatology, 22, 315-326.

[24]. Tan, Z., Wang, M., Xie, J., Chen, Y., & Shi, X. (2018, April). Deep semantic role labeling with self-attention. In Proceedings of the AAAI Conference on Artificial Intelligence, 32(1).

[25]. Wei, W., Poirion, E., Bodini, B., Durrleman, S., Colliot, O., Stankoff, B., & Ayache, N. (2018, June). FLAIR MR Image synthesis by using 3D fully convolutional networks for multiple sclerosis. In ISMRM-ESMRMB 2018-Joint Annual Meeting (pp. 1-6).

[26]. Yaqoob, J., Alam, M. S., & Khalid, N. (2015). Diagnostic accuracy of Magnetic Resonance Imaging in assessment of Meniscal and ACL tear: Correlation with arthroscopy. Pakistan Journal of Medical Sciences, 31(2), 263.

[27]. Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016). Learning deep features for discriminative localization. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2921-2929).

[28]. Zou, L., Zheng, J., Miao, C., Mckeown, M. J., & Wang, Z. J. (2017). 3D CNN based automatic diagnosis of attention deficit hyperactivity disorder using functional and structural MRI. IEEE Access, 5, 23626-23636.

Deep Learning MRI Analysis for Automated Knee Injury Diagnosis

Abstract

Keywords

How to Cite this Article?

References

If you have access to this article please login to view the article or kindly login to purchase the article

Purchase Instant Access

Options for accessing this content:

	North Americas,UK, Middle East,Europe		India	Rest of world
	USD	EUR	INR	USD-ROW
Pdf	35	35	200	20
Online	35	35	200	15
Pdf & Online	35	35	400	25