EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Estimating time-to-total knee replacement on radiographs and MRI: a multimodal approach using self-supervised deep learning

Ozkan Cigdem iD, Shengjia Chen iD, Chaojie Zhang iD, Kyunghyun Cho iD, Richard Kijowski, Cem M Deniz iD

Radiology Advances · 01.01.2022 · 1 (4)

DOI: 10.1093/radadv/umae030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology Advances, online erschienen am 15.11.2024. Verfasst von Ozkan Cigdem und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, New York University Grossman School of Medicine, New York, NY 10016, United States. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIAMS NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Accurately predicting the expected duration of time until total knee replacement (time-to-TKR) is crucial for patient management and health care planning. Predicting when surgery may be needed, especially within shorter windows like 3 years, allows clinicians to plan timely interventions and health care systems to allocate resources more effectively. Existing models lack the precision for such time-based predictions. A survival analysis model for predicting time-to-TKR was developed using features from medical images and clinical measurements.

Methods

From the Osteoarthritis Initiative dataset, all knees with clinical variables, MRI scans, radiographs, and quantitative and semiquantitative assessments from images were identified. This resulted in 895 knees that underwent TKR within the 9-year follow-up period, as specified by the Osteoarthritis Initiative study design, and 786 control knees that did not undergo TKR (right-censored, indicating their status beyond the 9-year follow-up is unknown). These knees were used for model training and testing. Additionally, 518 and 164 subjects from the Multi-Center Osteoarthritis Study and internal hospital data were used for external testing, respectively. Deep learning models were utilized to extract features from radiographs and MR scans. Extracted features, clinical variables, and image assessments were used in survival analysis with Lasso Cox feature selection and a random survival forest model to predict time-to-TKR.

Results

The proposed model exhibited strong discrimination power by integrating self-supervised deep learning features with clinical variables (eg, age, body mass index, pain score) and image assessment measurements (eg, Kellgren-Lawrence grade, joint space narrowing, bone marrow lesion size, cartilage morphology) from multiple modalities. The model achieved an area under the curve of 94.5 (95% CI, 94.0-95.1) for predicting the time-to-TKR.

Conclusions

The proposed model demonstrated the potential of self-supervised learning and multimodal data fusion in accurately predicting time-to-TKR that may assist physicians to develop personalize treatment strategies.

Schlagwörter

Stichwörter der Autor:innen

deep learningknee osteoarthritismultimodal learningself-supervised learningtime-to-TKR prediction

Autor:innen und Institutionen

  • Department of Radiology, New York University Grossman School of Medicine, New York, NY 10016, United States.
  • Center of Data Science, New York University, New York, NY 10011, United States.
  • Courant Institute of Mathematical Sciences, New York University, New York, NY 10012-1185, United States.

ORCID-Profile: Ozkan Cigdem, Shengjia Chen, Chaojie Zhang, Kyunghyun Cho, Cem M Deniz

Förderung

  • NIAMS NIH HHS
  • National Institutes of Health

Zitieren

APA

Cigdem, O., Chen, S., Zhang, C., Cho, K., Kijowski, R., & Deniz, C. M. (2022). Estimating time-to-total knee replacement on radiographs and MRI: a multimodal approach using self-supervised deep learning. Radiology Advances, 1(4). https://doi.org/10.1093/radadv/umae030

Vancouver

Cigdem O, Chen S, Zhang C, Cho K, Kijowski R, Deniz CM. Estimating time-to-total knee replacement on radiographs and MRI: a multimodal approach using self-supervised deep learning. Radiology Advances. 2022;1(4). doi:10.1093/radadv/umae030

BibTeX
@article{Cigdem2022,
  author = {Cigdem, Ozkan and Chen, Shengjia and Zhang, Chaojie and Cho, Kyunghyun and Kijowski, Richard and Deniz, Cem M},
  title = {Estimating time-to-total knee replacement on radiographs and MRI: a multimodal approach using self-supervised deep learning},
  journal = {Radiology Advances},
  year = {2022},
  volume = {1},
  number = {4},
  doi = {10.1093/radadv/umae030}
}
Kostenlos starten →