TY - JOUR
T1 - Prediction of total knee replacement and diagnosis of osteoarthritis by using deep learning on knee radiographs
T2 - Data from the osteoarthritis initiative
AU - Leung, Kevin
AU - Zhang, Bofei
AU - Tan, Jimin
AU - Shen, Yiqiu
AU - Geras, Krzysztof J.
AU - Babb, James S.
AU - Cho, Kyunghyun
AU - Chang, Gregory
AU - Deniz, Cem M.
N1 - Funding Information:
Study supported by National Institutes of Health (R01 AR074453). Conflicts of interest are listed at the end of this article. See also the editorial by Richardson in this issue.
Funding Information:
The Osteoarthritis Initiative (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 National Institutes of Health, and conducted by the OAI Study Investigators. Private funding partners include Merck Research Laboratories, Novartis Pharmaceuticals Corporation, GlaxoSmithKline, and Pfizer. Private-sector funding for the OAI is managed by the Foundation for the National Institutes of Health. This manuscript was prepared by using an OAI public use data set and does not necessarily reflect the opinions or views of the OAI investigators, the National Institutes of Health, or the private funding partners.
Publisher Copyright:
© RSNA 2020.
PY - 2020/9
Y1 - 2020/9
N2 - Background The methods for assessing knee osteoarthritis (OA) do not provide enough comprehensive information to make robust and accurate outcome predictions. Purpose To develop a deep learning (DL) prediction model for risk of OA progression by using knee radiographs in patients who underwent total knee replacement (TKR) and matched control patients who did not undergo TKR. Materials and Methods In this retrospective analysis that used data from the OA Initiative, a DL model on knee radiographs was developed to predict both the likelihood of a patient undergoing TKR within 9 years and Kellgren-Lawrence (KL) grade. Study participants included a case-control matched subcohort between 45 and 79 years. Patients were matched to control patients according to age, sex, ethnicity, and body mass index. The proposed model used a transfer learning approach based on the ResNet34 architecture with sevenfold nested cross-validation. Receiver operating characteristic curve analysis and conditional logistic regression assessed model performance for predicting probability and risk of TKR compared with clinical observations and two binary outcome prediction models on the basis of radiographic readings: KL grade and OA Research Society International (OARSI) grade. Results Evaluated were 728 participants including 324 patients (mean age, 64 years ± 8 [standard deviation]; 222 women) and 324 control patients (mean age, 64 years ± 8; 222 women). The prediction model based on DL achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (95% confidence interval [CI]: 0.85, 0.90), outperforming a baseline prediction model by using KL grade with an AUC of 0.74 (95% CI: 0.71, 0.77;
P < .001). The risk for TKR increased with probability that a person will undergo TKR from the DL model (odds ratio [OR], 7.7; 95% CI: 2.3, 25;
P < .001), KL grade (OR, 1.92; 95% CI: 1.17, 3.13;
P = .009), and OARSI grade (OR, 1.20; 95% CI: 0.41, 3.50;
P = .73). Conclusion The proposed deep learning model better predicted risk of total knee replacement in osteoarthritis than did binary outcome models by using standard grading systems. © RSNA, 2020
Online supplemental material is available for this article. See also the editorial by Richardson in this issue.
AB - Background The methods for assessing knee osteoarthritis (OA) do not provide enough comprehensive information to make robust and accurate outcome predictions. Purpose To develop a deep learning (DL) prediction model for risk of OA progression by using knee radiographs in patients who underwent total knee replacement (TKR) and matched control patients who did not undergo TKR. Materials and Methods In this retrospective analysis that used data from the OA Initiative, a DL model on knee radiographs was developed to predict both the likelihood of a patient undergoing TKR within 9 years and Kellgren-Lawrence (KL) grade. Study participants included a case-control matched subcohort between 45 and 79 years. Patients were matched to control patients according to age, sex, ethnicity, and body mass index. The proposed model used a transfer learning approach based on the ResNet34 architecture with sevenfold nested cross-validation. Receiver operating characteristic curve analysis and conditional logistic regression assessed model performance for predicting probability and risk of TKR compared with clinical observations and two binary outcome prediction models on the basis of radiographic readings: KL grade and OA Research Society International (OARSI) grade. Results Evaluated were 728 participants including 324 patients (mean age, 64 years ± 8 [standard deviation]; 222 women) and 324 control patients (mean age, 64 years ± 8; 222 women). The prediction model based on DL achieved an area under the receiver operating characteristic curve (AUC) of 0.87 (95% confidence interval [CI]: 0.85, 0.90), outperforming a baseline prediction model by using KL grade with an AUC of 0.74 (95% CI: 0.71, 0.77;
P < .001). The risk for TKR increased with probability that a person will undergo TKR from the DL model (odds ratio [OR], 7.7; 95% CI: 2.3, 25;
P < .001), KL grade (OR, 1.92; 95% CI: 1.17, 3.13;
P = .009), and OARSI grade (OR, 1.20; 95% CI: 0.41, 3.50;
P = .73). Conclusion The proposed deep learning model better predicted risk of total knee replacement in osteoarthritis than did binary outcome models by using standard grading systems. © RSNA, 2020
Online supplemental material is available for this article. See also the editorial by Richardson in this issue.
KW - Aged
KW - Arthroplasty, Replacement, Knee/statistics & numerical data
KW - Deep Learning
KW - Female
KW - Humans
KW - Image Interpretation, Computer-Assisted
KW - Knee Joint/diagnostic imaging
KW - Male
KW - Middle Aged
KW - Osteoarthritis, Knee/diagnostic imaging
KW - Radiography
KW - Retrospective Studies
KW - Risk Factors
UR - http://www.scopus.com/inward/record.url?scp=85089707641&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089707641&partnerID=8YFLogxK
U2 - 10.1148/radiol.2020192091
DO - 10.1148/radiol.2020192091
M3 - Article
C2 - 32573386
AN - SCOPUS:85089707641
SN - 0033-8419
VL - 296
SP - 584
EP - 593
JO - Radiology
JF - Radiology
IS - 3
ER -