Gebre, R.K., Hirvasniemi, J., van der Heijden, R.A. et al. Detecting hip osteoarthritis on clinical CT: a deep learning application based on 2-D summation images derived from CT. Osteoporos Int 33, 355–365 (2022). https://doi.org/10.1007/s00198-021-06130-y
Detecting hip osteoarthritis on clinical CT : a deep learning application based on 2-D summation images derived from CT
|Author:||Gebre, R. K.1; Hirvasniemi, J.2; van der Heijden, R. A.2;|
1Research Unit of Medical Imaging, Physics and Technology, University of Oulu, Oulu, Finland
2Department of Radiology & Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, the Netherlands
3Division of Orthopaedic and Trauma Surgery, Oulu University Hospital, Oulu, Finland
4Medical Research Center, University of Oulu and Oulu University Hospital, Oulu, Finland
5Diagnostic Radiology, Oulu University Hospital, Oulu, Finland
|Online Access:||PDF Full Text (PDF, 3.1 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2022030722164
|Publish Date:|| 2022-03-07
Summary: We developed and compared deep learning models to detect hip osteoarthritis on clinical CT. The CT-based summation images, CT-AP, that resemble X-ray radiographs can detect radiographic hip osteoarthritis and in the absence of large training data, a reliable deep learning model can be optimized by combining CT-AP and X-ray images.
Introduction: In this study, we aimed to investigate the applicability of deep learning (DL) to assess radiographic hip osteoarthritis (rHOA) on computed tomography (CT).
Methods: The study data consisted of 94 abdominopelvic clinical CTs and 5659 hip X-ray images collected from Cohort Hip and Cohort Knee (CHECK). The CT slices were sequentially summed to create radiograph-like 2-D images named CT-AP. X-ray and CT-AP images were classified as rHOA if they had osteoarthritic changes corresponding to Kellgren-Lawrence grade 2 or higher. The study data was split into 55% training, 30% validation, and 15% test sets. A pretrained ResNet18 was optimized for a classification task of rHOA vs. no-rHOA. Five models were trained using (1) X-rays, (2) downsampled X-rays, (3) combination of CT-AP and X-ray images, (4) combination of CT-AP and downsampled X-ray images, and (5) CT-AP images.
Results: Amongst the five models, Model-3 and Model-5 performed best in detecting rHOA from the CT-AP images. Model-3 detected rHOA on the test set of CT-AP images with a balanced accuracy of 82.2% and was able to discriminate rHOA from no-rHOA with an area under the receiver operating characteristic curve (ROC AUC) of 0.93 [0.75–0.99]. Model-5 detected rHOA on the test set at a balanced accuracy of 82.2% and classified rHOA from no-rHOA with an ROC AUC of 0.89 [0.67–0.97].
Conclusion: CT-based summation images that resemble radiographs can be used to detect rHOA. In addition, in the absence of large training data, a reliable DL model can be optimized by combining CT-AP and X-ray images.
|Pages:||355 - 365|
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
3126 Surgery, anesthesiology, intensive care, radiology
Open access funding provided by University of Oulu including Oulu University Hospital. This study was financially supported by CINOP Global (NICHE/ETH/246) funded by EP-Nuffic. The CHECK-cohort study is funded by the Dutch Arthritis Foundation. Involved are Erasmus Medical Center Rotterdam; Kennemer Gasthuis Haarlem; Leiden University Medical Center; Maastricht University Medical Center; Martini Hospital Groningen/Allied Health Care Center for Rheumatology and Rehabilitation Groningen; Medical Spectrum Twente Enschede /Ziekenhuisgroep Twente Almelo; Reade Center for Rehabilitation and Rheumatology; St. Maartens-kliniek Nijmegen; University Medical Center Utrecht and Wilhelmina Hospital Assen.
© The Author(s) 2021. This article is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License, which permits any non-commercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc/4.0/.