Prognostic prediction in soft-tissue sarcomas using deep learning and digital pathology of tumor and margin areas

The histological FNCLCC grade is the primary prognostic factor in soft-tissue sarcoma (STS) but fails to fully capture high risk patients. This study aimed to develop and validate a deep learning (DL) model to predict metastatic relapse-free survival (MFS) using digital hematoxylin and eosin-stained...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Scientific reports Jg. 15; H. 1; S. 38534 - 17
Hauptverfasser: Michot, Audrey, Le, Van-Linh, Coindre, Jean-Michel, Velasco, Valérie, Soussi, Malika, Mesli, Nouria, Italiano, Antoine, Toulmonde, Maud, Le Cesne, Axel, Bonvalot, Sylvie, Vanhersecke, Lucile, Honoré, Charles, Ngo, Carine, Le Loarer, François, Saut, Olivier, Crombé, Amandine
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group UK 04.11.2025
Nature Publishing Group
Nature Portfolio
Schlagworte:
631/114
631/67
639/705/1041
692/4028
692/53
Adult
Aged
Artificial intelligence
Data collection
Deep Learning
Digital pathology
Female
Histologic grading
Humanities and Social Sciences
Humans
Liposarcoma
Male
Margins of Excision
Medical prognosis
Metastases
Metastasis
Middle Aged
multidisciplinary
Neoplasm Grading
Neural networks
Pathology
Patients
Prognosis
Prognosis prediction
Retrospective Studies
Risk groups
Sarcoma
Sarcoma - diagnosis
Sarcoma - mortality
Sarcoma - pathology
Science
Science (multidisciplinary)
Soft-tissue sarcoma
Software
Surgery
Tumors
France
Japan
Deep learning
Digital pathology
Histologic grading
Prognosis prediction
Artificial intelligence
Soft-tissue sarcoma
ISSN:2045-2322, 2045-2322
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The histological FNCLCC grade is the primary prognostic factor in soft-tissue sarcoma (STS) but fails to fully capture high risk patients. This study aimed to develop and validate a deep learning (DL) model to predict metastatic relapse-free survival (MFS) using digital hematoxylin and eosin-stained whole-slide images. A retrospective analysis was conducted on 308 STS patients from two cancer centers, divided into a training cohort (149 patients) and two independent validation cohorts (64 and 95 patients). Supervised multi-instance learning convolutional neural network models were trained on distinct tumor regions—center (C), periphery (P), and margins (R)—to optimize predictive performance. Univariable analysis showed DL models using tumor center (DL-C), periphery (DL-P), and their combination (DL-CP) were consistently associated with MFS across cohorts, while models incorporating margins (DL-R and DL-CPR) demonstrated less reliable associations. Multivariable Cox regression confirmed that high risk scores from DL models were independent predictors of MFS. The DL-CP model outperformed FNCLCC grading in prognostic accuracy, with c-indices ≥ 0.74 in validation cohorts. Adding tumor margin information did not improve predictions.DL models focusing on tumor center and periphery provide superior prognostic value in STS, offering a streamlined, effective approach for digital pathology-based risk stratification.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-025-20804-1