Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet)

Chen-Han Tsai, Nahum Kiryati, Eli Konen, Iris Eshed, Arnaldo Mayer
; Proceedings of the Third Conference on Medical Imaging with Deep Learning, PMLR 121:784-794, 2020.

Abstract

Magnetic Resonance Imaging (MRI) is a widely-accepted imaging technique for knee injury analysis. Its advantage of capturing knee structure in three dimensions makes it the ideal tool for radiologists to locate potential tears in the knee. In order to better confront the ever growing workload of musculoskeletal (MSK) radiologists, automated tools for patients’ triage are becoming a real need, reducing delays in the reading of pathological cases. In this work, we present the Efficiently-Layered Network (ELNet), a convolutional neural network (CNN) architecture optimized for the task of initial knee MRI diagnosis for triage. Unlike past approaches, we train ELNet from scratch instead of using a transfer-learning approach. The proposed method is validated quantitatively and qualitatively, and compares favorably against state-of-the-art MRNet while using a single imaging stack (axial or coronal) as input. Additionally, we demonstrate our model’s capability to locate tears in the knee despite the absence of localization information during training. Lastly, the proposed model is extremely lightweight ($<$ 1MB) and therefore easy to train and deploy in real clinical settings.

Cite this Paper


BibTeX
@InProceedings{pmlr-v121-tsai20a, title = {Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet)}, author = {Tsai, Chen-Han and Kiryati, Nahum and Konen, Eli and Eshed, Iris and Mayer, Arnaldo}, pages = {784--794}, year = {2020}, editor = {Tal Arbel and Ismail Ben Ayed and Marleen de Bruijne and Maxime Descoteaux and Herve Lombaert and Christopher Pal}, volume = {121}, series = {Proceedings of Machine Learning Research}, address = {Montreal, QC, Canada}, month = {06--08 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v121/tsai20a/tsai20a.pdf}, url = {http://proceedings.mlr.press/v121/tsai20a.html}, abstract = {Magnetic Resonance Imaging (MRI) is a widely-accepted imaging technique for knee injury analysis. Its advantage of capturing knee structure in three dimensions makes it the ideal tool for radiologists to locate potential tears in the knee. In order to better confront the ever growing workload of musculoskeletal (MSK) radiologists, automated tools for patients’ triage are becoming a real need, reducing delays in the reading of pathological cases. In this work, we present the Efficiently-Layered Network (ELNet), a convolutional neural network (CNN) architecture optimized for the task of initial knee MRI diagnosis for triage. Unlike past approaches, we train ELNet from scratch instead of using a transfer-learning approach. The proposed method is validated quantitatively and qualitatively, and compares favorably against state-of-the-art MRNet while using a single imaging stack (axial or coronal) as input. Additionally, we demonstrate our model’s capability to locate tears in the knee despite the absence of localization information during training. Lastly, the proposed model is extremely lightweight ($<$ 1MB) and therefore easy to train and deploy in real clinical settings.} }
Endnote
%0 Conference Paper %T Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet) %A Chen-Han Tsai %A Nahum Kiryati %A Eli Konen %A Iris Eshed %A Arnaldo Mayer %B Proceedings of the Third Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2020 %E Tal Arbel %E Ismail Ben Ayed %E Marleen de Bruijne %E Maxime Descoteaux %E Herve Lombaert %E Christopher Pal %F pmlr-v121-tsai20a %I PMLR %J Proceedings of Machine Learning Research %P 784--794 %U http://proceedings.mlr.press %V 121 %W PMLR %X Magnetic Resonance Imaging (MRI) is a widely-accepted imaging technique for knee injury analysis. Its advantage of capturing knee structure in three dimensions makes it the ideal tool for radiologists to locate potential tears in the knee. In order to better confront the ever growing workload of musculoskeletal (MSK) radiologists, automated tools for patients’ triage are becoming a real need, reducing delays in the reading of pathological cases. In this work, we present the Efficiently-Layered Network (ELNet), a convolutional neural network (CNN) architecture optimized for the task of initial knee MRI diagnosis for triage. Unlike past approaches, we train ELNet from scratch instead of using a transfer-learning approach. The proposed method is validated quantitatively and qualitatively, and compares favorably against state-of-the-art MRNet while using a single imaging stack (axial or coronal) as input. Additionally, we demonstrate our model’s capability to locate tears in the knee despite the absence of localization information during training. Lastly, the proposed model is extremely lightweight ($<$ 1MB) and therefore easy to train and deploy in real clinical settings.
APA
Tsai, C., Kiryati, N., Konen, E., Eshed, I. & Mayer, A.. (2020). Knee Injury Detection using MRI with Efficiently-Layered Network (ELNet). Proceedings of the Third Conference on Medical Imaging with Deep Learning, in PMLR 121:784-794

Related Material