Contrastive multimodal deep learning for survival prediction in grade 2/3 gliomas
Menée à partir de données du projet "The Cancer Genome Atlas" portant sur 498 patients atteints d'un gliome de grade 2/3 et validée sur une cohorte de 61 patients, cette étude évalue la performance d'un algorithme d'apprentissage contrastif intégrant des données génomiques, cliniques et histopathologiques (issues d'images de lames histologiques) pour prédire la survie
Background : Accurate survival prediction for grade 2/3 glioma patients remains challenging due to tumor biological heterogeneity and limitations of current prognostic methods that rely on single-modality data.
Methods : We developed a multimodal deep learning framework integrating histopathology whole-slide images, somatic mutations, and clinical-demographic data. A three-stage training pipeline combined contrastive learning with survival-specific optimization to align cross-modal representations. The framework was trained on 498 grade 2/3 glioma patients from TCGA and evaluated using 5-fold cross-validation and an independent Dartmouth-Hitchcock Medical Center (DHMC) cohort (n = 61).
Results : The contrastive multimodal model achieved a c-index of 0.91 (95% CI: 0.84 to 0.96), significantly outperforming the unimodal models (image-only = 0.76; non-image-only = 0.87) and showing an improvement over the non-contrastive multimodal model (c-index = 0.89), although this difference was not statistically significant. Kaplan-Meier analysis demonstrated clear survival separation across risk strata (log-rank P = 4.4 × 10−5). Contrastive learning improved representation clustering quality, with silhouette scores increasing from 0.20 to 0.24 (P = 0.05). External evaluation on the DHMC cohort achieved a c-index of 0.87 (95% CI: 0.77 to 0.95) after domain adaptation.
Conclusion : Contrastive multimodal learning significantly enhances survival prediction in grade 2/3 gliomas by effectively integrating histopathology, genomics, and clinical data. This annotation-free approach enables early risk stratification using routinely collected data and shows promise for informing personalized treatment decisions and clinical trial stratification.
JNCI Cancer Spectrum , article en libre accès, 2026