Risk score stratification of cutaneous melanoma patients based on whole slide images analysis by deep learning
Journal of the European Academy of Dermatology and Venereology · 2025-08 · 39 (8) · 1500-1509
DOI: 10.1111/jdv.20538 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the European Academy of Dermatology and Venereology, online erschienen am 24.01.2025. Verfasst von Céline Bossard und 7 weiteren Autor:innen. Beteiligte Einrichtung: Pathology Department, IHP Group, Nantes, France. Hauptthemen laut MEDLINE: Melanoma, Deep Learning, Skin Neoplasms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 25 Literaturangaben.
Abstract (Originalsprache)
Background
There is a need to improve risk stratification of primary cutaneous melanomas to better guide adjuvant therapy. Taking into account that haematoxylin and eosin (HE)‐stained tumour tissue contains a huge amount of clinically unexploited morphological informations, we developed a weakly‐supervised deep‐learning approach, SmartProg‐MEL, to predict survival outcomes in stages I to III melanoma patients from HE‐stained whole slide image (WSI).
Methods
We designed a deep neural network that extracts morphological features from WSI to predict 5‐y overall survival (OS), and assign a survival risk score to each patient. The model was trained and validated on a discovery cohort of primary cutaneous melanomas (IHP‐MEL‐1, n = 342). Performance was tested on two external and independent datasets (IHP‐MEL‐2, n = 161; and TCGA cohort n = 63). It was compared with well‐established prognostic factors. Concordance index (c‐index) was used as a metric.
Results
On the discovery cohort, the SmartProg‐MEL predicts the 5‐y OS with a c‐index of 0.78 on the cross‐validation data and of 0.72 on the cross‐testing series. In the external cohorts, the model achieved a c‐index of 0.71 and 0.69 for the IHP‐MEL‐2 and TCGA dataset respectively. Furthermore, SmartProg‐MEL was an independent and the most powerful prognostic factor in multivariate analysis (HR = 1.84, p ‐value < 0.005). Finally, the model was able to dichotomize patients in two groups—a low and a high‐risk group—each associated with a significantly different 5‐y OS ( p ‐value < 0.001 for IHP‐MEL‐1 and p ‐value = 0.01 for IHP‐MEL‐2).
Conclusions
The performance of our fully automated SmartProg‐MEL model outperforms the current clinicopathological factors in terms of prediction of 5‐y OS and risk stratification of cutaneous melanoma patients. Incorporation of SmartProg‐MEL in the clinical workflow could guide the decision‐making process by improving the identification of patients that may benefit from adjuvant therapy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Pathology Department, IHP Group, Nantes, France.
- DiaDeep, Lyon, France.
- Nantes University, Dermatology Department CHU Nantes CIC 1413, INCIT UMR, Nantes, France.
- Pathology Department, IHP Group, Angers, France.
- Dermatology Department, University Hospital of Angers, Angers, France.
ORCID-Profile: Céline Bossard
Zitieren
APA
Bossard, C., Salhi, Y., Khammari, A., Brousseau, M., Le Corre, Y., Salhi, S., Quéreux, G., & Chetritt, J. J. (2025). Risk score stratification of cutaneous melanoma patients based on whole slide images analysis by deep learning. Journal of the European Academy of Dermatology and Venereology, 39(8), 1500-1509. https://doi.org/10.1111/jdv.20538
Vancouver
Bossard C, Salhi Y, Khammari A, Brousseau M, Le Corre Y, Salhi S, et al. Risk score stratification of cutaneous melanoma patients based on whole slide images analysis by deep learning. Journal of the European Academy of Dermatology and Venereology. 2025;39(8):1500-1509. doi:10.1111/jdv.20538
BibTeX
@article{Bossard2025,
author = {Bossard, Céline and Salhi, Yahia and Khammari, Amir and Brousseau, Maud and Le Corre, Yannick and Salhi, Sanae and Quéreux, Gaëlle and Chetritt, Jérôme J},
title = {Risk score stratification of cutaneous melanoma patients based on whole slide images analysis by deep learning},
journal = {Journal of the European Academy of Dermatology and Venereology},
year = {2025},
volume = {39},
number = {8},
pages = {1500--1509},
doi = {10.1111/jdv.20538}
}
EUVIMED