A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis
Abstract Currently X‐ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence (KL) scoring method. However, individual scoring is subjective and error prone. This study proposes an approach for automated knee osteoarthritis classification based on deep neural networ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-09-01
|
| Series: | CAAI Transactions on Intelligence Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cit2.12079 |
| _version_ | 1817999077515722752 |
|---|---|
| author | Yu Wang Shibo Li Baoliang Zhao Jianwei Zhang Yuanyuan Yang Bing Li |
| author_facet | Yu Wang Shibo Li Baoliang Zhao Jianwei Zhang Yuanyuan Yang Bing Li |
| author_sort | Yu Wang |
| collection | DOAJ |
| description | Abstract Currently X‐ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence (KL) scoring method. However, individual scoring is subjective and error prone. This study proposes an approach for automated knee osteoarthritis classification based on deep neural networks. The knee X‐ray images are first pre‐processed with frequency‐domain filtering and histogram normalisation, making the trabecular bone texture more obvious and benefiting the subsequent classification task. Then, a two‐step classification strategy is proposed by extracting the joint centre based on the VGG network and classifying osteoarthritis grades based on the ResNet‐50 network. In addition, a rebalance operation is proposed to deal with the dataset unbalance problem, and a quick search technique is proposed to improve the iterative search efficiency for the joint centre. With all of these techniques, a classification accuracy of 81.41% is obtained, which is higher compared to the state‐of‐the‐art approaches. |
| first_indexed | 2024-04-14T03:03:10Z |
| format | Article |
| id | doaj.art-d208ddf11428401a94ece2572667291d |
| institution | Directory Open Access Journal |
| issn | 2468-2322 |
| language | English |
| last_indexed | 2024-04-14T03:03:10Z |
| publishDate | 2022-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | CAAI Transactions on Intelligence Technology |
| spelling | doaj.art-d208ddf11428401a94ece2572667291d2022-12-22T02:15:51ZengWileyCAAI Transactions on Intelligence Technology2468-23222022-09-017351252110.1049/cit2.12079A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritisYu Wang0Shibo Li1Baoliang Zhao2Jianwei Zhang3Yuanyuan Yang4Bing Li5School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen ChinaShenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen ChinaShenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen ChinaTAMS Department of Informatics University of Hamburg Hamburg GermanyShenzhen Key Laboratory of Minimally Invasive Surgical Robotics and System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen ChinaSchool of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen ChinaAbstract Currently X‐ray images are clinically graded by experienced clinicians using the Kellgren and Lawrence (KL) scoring method. However, individual scoring is subjective and error prone. This study proposes an approach for automated knee osteoarthritis classification based on deep neural networks. The knee X‐ray images are first pre‐processed with frequency‐domain filtering and histogram normalisation, making the trabecular bone texture more obvious and benefiting the subsequent classification task. Then, a two‐step classification strategy is proposed by extracting the joint centre based on the VGG network and classifying osteoarthritis grades based on the ResNet‐50 network. In addition, a rebalance operation is proposed to deal with the dataset unbalance problem, and a quick search technique is proposed to improve the iterative search efficiency for the joint centre. With all of these techniques, a classification accuracy of 81.41% is obtained, which is higher compared to the state‐of‐the‐art approaches.https://doi.org/10.1049/cit2.12079AMSGradknee osteoarthritis recognitionResNetVGG |
| spellingShingle | Yu Wang Shibo Li Baoliang Zhao Jianwei Zhang Yuanyuan Yang Bing Li A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis CAAI Transactions on Intelligence Technology AMSGrad knee osteoarthritis recognition ResNet VGG |
| title | A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis |
| title_full | A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis |
| title_fullStr | A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis |
| title_full_unstemmed | A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis |
| title_short | A ResNet‐based approach for accurate radiographic diagnosis of knee osteoarthritis |
| title_sort | resnet based approach for accurate radiographic diagnosis of knee osteoarthritis |
| topic | AMSGrad knee osteoarthritis recognition ResNet VGG |
| url | https://doi.org/10.1049/cit2.12079 |
| work_keys_str_mv | AT yuwang aresnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT shiboli aresnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT baoliangzhao aresnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT jianweizhang aresnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT yuanyuanyang aresnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT bingli aresnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT yuwang resnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT shiboli resnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT baoliangzhao resnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT jianweizhang resnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT yuanyuanyang resnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis AT bingli resnetbasedapproachforaccurateradiographicdiagnosisofkneeosteoarthritis |