TY - GEN
T1 - Attention-based CNN for KL Grade Classification
T2 - 17th IEEE International Symposium on Biomedical Imaging, ISBI 2020
AU - Zhang, Bofei
AU - Tan, Jimin
AU - Cho, Kyunghyun
AU - Chang, Gregory
AU - Deniz, Cem M.
N1 - Funding Information:
This work was supported in part by NIH R01 AR074453. The OAI is a public-private partnership comprised of five contracts (N01-AR-2-2258; N01-AR-2-2259; N01-AR-2-2260; N01-AR-2-2261; N01-AR-2-2262) funded by the NIH, a branch of the Department of Health and Human Services, and conducted by the OAI Study Investigators. Private funding partners include Merck Research Laboratories; No-vartis Pharmaceuticals Corporation, GlaxoSmithKline; and Pfizer, Inc. Private sector funding for the OAI is managed by the Foundation for the National Institutes of Health. This manuscript was prepared using an OAI public use data set and does not necessarily reflect the opinions or views of the OAI investigators, the NIH, or the private funding partners.
Publisher Copyright:
© 2020 IEEE.
PY - 2020/4
Y1 - 2020/4
N2 - Knee osteoarthritis (OA) is a chronic degenerative disorder of joints and it is the most common reason leading to total knee joint replacement. Diagnosis of OA involves subjective judgment on symptoms, medical history, and radiographic readings using Kellgren-Lawrence grade (KL-grade). Deep learning-based methods such as Convolution Neural Networks (CNN) have recently been applied to automatically diagnose radiographic knee OA. In this study, we applied Residual Neural Network (ResNet) to first detect knee joint from radiographs and later combine ResNet with Convolutional Block Attention Module (CBAM) to make a prediction of the KL-grade automatically. The proposed model achieved a multi-class average accuracy of 74.81%, mean squared error of 0.36, and quadratic Kappa score of 0.88, which demonstrates a significant improvement over the published results. The attention maps were analyzed to provide insights on the decision process of the proposed model11Code is available at https://github.com/denizlab/OAI-KL-Grade-Classification.
AB - Knee osteoarthritis (OA) is a chronic degenerative disorder of joints and it is the most common reason leading to total knee joint replacement. Diagnosis of OA involves subjective judgment on symptoms, medical history, and radiographic readings using Kellgren-Lawrence grade (KL-grade). Deep learning-based methods such as Convolution Neural Networks (CNN) have recently been applied to automatically diagnose radiographic knee OA. In this study, we applied Residual Neural Network (ResNet) to first detect knee joint from radiographs and later combine ResNet with Convolutional Block Attention Module (CBAM) to make a prediction of the KL-grade automatically. The proposed model achieved a multi-class average accuracy of 74.81%, mean squared error of 0.36, and quadratic Kappa score of 0.88, which demonstrates a significant improvement over the published results. The attention maps were analyzed to provide insights on the decision process of the proposed model11Code is available at https://github.com/denizlab/OAI-KL-Grade-Classification.
KW - convolutional neural networks
KW - deep learning
KW - knee
KW - osteoarthritis
KW - radiography
UR - http://www.scopus.com/inward/record.url?scp=85085506450&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85085506450&partnerID=8YFLogxK
U2 - 10.1109/ISBI45749.2020.9098456
DO - 10.1109/ISBI45749.2020.9098456
M3 - Conference contribution
AN - SCOPUS:85085506450
T3 - Proceedings - International Symposium on Biomedical Imaging
SP - 731
EP - 735
BT - ISBI 2020 - 2020 IEEE International Symposium on Biomedical Imaging
PB - IEEE Computer Society
Y2 - 3 April 2020 through 7 April 2020
ER -