Academic Journal
Radiomics grading of hand osteoarthritis severity using standard radiographs: Results from the DIGICOD cohort.
| Τίτλος: | Radiomics grading of hand osteoarthritis severity using standard radiographs: Results from the DIGICOD cohort. |
|---|---|
| Συγγραφείς: | Perronne L; Université Paris Cité, PARCC UMRS 970, INSERM, Paris, France. Electronic address: laetitia.perronne@northwestern.edu., Decoux A; Université Paris Cité, PARCC UMRS 970, INSERM, Paris, France. Electronic address: antoine.decoux@laposte.net., Duron L; Université Paris Cité, PARCC UMRS 970, INSERM, Paris, France; Department of Neuroradiology, Hôpital Fondation Ophtalmologique Adolphe de Rothschild, Paris, France. Electronic address: lduron@for.paris., de Margerie-Mellon C; Université Paris Cité, AP-HP, Department of Radiology, Hôpital Saint Louis PARCC UMRS 970, INSERM, Paris, France. Electronic address: constance.de-margerie@aphp.fr., Saarakkala S; Research Unit of Health Sciences and Technology, Faculty of Medicine, University of Oulu, Oulu, Finland; Department of Diagnostic Radiology, Oulu University Hospital, Oulu, Finland. Electronic address: Simo.Saarakkala@oulu.fi., Maheu E; Sorbonne Université, APHP, Department of Rheumatology, Hôpital Saint-Antoine, Paris, France. Electronic address: emaheu@wanadoo.fr., Crema MD; Institute of Sports Imaging, French National Institute of Sports (INSEP), Paris, France; Sorbonne Université, APHP, Department of Radiology, Hôpital Saint-Antoine, Paris, France. Electronic address: michelcrema@gmail.com., Miquel A; Sorbonne Université, APHP, Department of Radiology, Hôpital Saint-Antoine, Paris, France. Electronic address: anne.miquel@aphp.fr., Berenbaum F; Sorbonne Université, APHP, Department of Rheumatology, Hôpital Saint-Antoine, Paris, France. Electronic address: francis.berenbaum@aphp.fr., Arnoux A; Université Paris Cité, AP-HP, Unité de Recherche Clinique / Centre d'Investigation Clinique 1418 - Épidémiologie Clinique, Hôpital Européen Georges-Pompidou, INSERM, Paris, France. Electronic address: armelle.arnoux@aphp.fr., Laredo JD; Université Paris Cité, AP-HP, Department of Radiology, Hôpital Lariboisière, Paris, France. Electronic address: laredojd@gmail.com., Sellam J; Sorbonne Université, APHP, Department of Rheumatology, Hôpital Saint-Antoine, Paris, France. Electronic address: jeremie.sellam@aphp.fr., Fournier L; Université Paris Cité, AP-HP, Department of Radiology, Hôpital Européen Georges Pompidou, PARCC UMRS 970, INSERM, Paris, France. Electronic address: laure.fournier@aphp.fr. |
| Πηγή: | Osteoarthritis and cartilage [Osteoarthritis Cartilage] 2026 Sep; Vol. 34 (9), pp. 1380-1389. Date of Electronic Publication: 2026 May 21. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: W.B. Saunders For The Osteoarthritis Research Society Country of Publication: England NLM ID: 9305697 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1522-9653 (Electronic) Linking ISSN: 10634584 NLM ISO Abbreviation: Osteoarthritis Cartilage Subsets: MEDLINE |
| Imprint Name(s): | Publication: London : W.B. Saunders For The Osteoarthritis Research Society Original Publication: London : Published for the Society by Baillère Tindall, c1993- |
| Ιατρικοί όροι (MeSH): | Osteoarthritis*/diagnostic imaging , Hand Joints*/diagnostic imaging, Humans ; Radiomics ; Severity of Illness Index ; Retrospective Studies ; Male ; Female ; Radiography ; Middle Aged ; Aged |
| Περίληψη: | Objective: This study evaluated whether radiomics analysis of standard hand radiographs could provide an automated and objective assessment of structural severity in hand osteoarthritis (HOA) compared to Kellgren-Lawrence (KL) scores, ranging from 0 (normal) to 4 (severe). Design: We conducted a retrospective study using baseline data from the DIGICOD (DIGital Cohort Osteoarthritis Design) cohort, including patients with HOA. Standard posteroanterior radiographs were segmented semi-automatically using a U-Net model with manual correction. Radiomics features describing intensity, shape, and texture were extracted for each joint and reduced after filtering and correlation suppression. The cohort was split into training (80%) and test sets (20%) using stratified sampling. Random Forest classifiers were trained to detect structural involvement (KL ≥2), severe disease (KL 3-4), and predict multiclass KL grades (0-1, 2, 3, 4) at the joint level. Results: 379 radiographs were analyzed. Detection of structural involvement (KL ≥2) achieved an AUC of 0.81 [95% CI: 0.79-0.83], with high sensitivity (89%) but low specificity (59%). Severe disease detection (KL 3-4) reached an AUC of 0.83 [95% CI: 0.81-0.85], with very good sensitivity (80%) and good specificity (70%). Multiclass KL prediction showed lower performance (macro-averaged AUC 0.76; accuracy 56%), reflecting challenges in distinguishing intermediate (KL 2-3) and severe (KL 4) grades. Conclusions: This is the first study applying radiomics to standard hand radiographs for automated and objective scoring of radiographic severity in HOA. The model showed good performance detecting structural damage, supporting radiomics as a potential tool to reduce reliance on subjective visual grading. (Copyright © 2026 The Authors. Published by Elsevier Ltd.. All rights reserved.) |
| Competing Interests: | Declaration of Competing Interest FB received consulting fees from Grunenthal, GSK, Eli Lilly, Novartis, Pfizer, Servier, 4 P Pharma; received payment or honoraria for lectures, presentations, speakers bureaus, manuscript writing or educational events from Viatris, Pfizer, Zoetis; received support for attending meetings and/or travel from Nordic Pharma; has patents planned, issued or pending with 4Moving Biotech, participated on a Data Safety Monitoring Board or Advisory Board with AstraZeneca, Sun Pharma, Nordic Bioscience; stock or stock options with 4 P Pharma, 4Moving Biotech. JS received consulting or conference fees from Grünenthal, Pfizer, Abbvie, Janssen, Novartis, AlfaSigma, Abbvie, Lilly, UCB, Fresenius Kabi, Guerbet, Axomove, IBSA and Nordic Pharma. LF received consulting fees from Keosys and Spire Sciences; speaker fees from General Electric Healthcare, Fujifilm, Median technologies; Research collaborations with Siemens Healthineers, General Electric Healthcare, Dassault Systems; Member of the scientific committee of the Institut Servier. |
| Contributed Indexing: | Keywords: Hand; Machine learning; Osteoarthritis; Radiograph; Radiomics |
| Entry Date(s): | Date Created: 20260522 Date Completed: 20260811 Latest Revision: 20260811 |
| Update Code: | 20260812 |
| DOI: | 10.1016/j.joca.2026.05.009 |
| PMID: | 42173234 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1522-9653 |
|---|---|
| DOI: | 10.1016/j.joca.2026.05.009 |