Beyond a single ratio: an adaptable deep learning approach to analyze the prognostic value of TSP distribution in ovarian cancer
Open Access
- 27 October 2026
- journal article
- Published by Wiley in The Journal of Pathology
Abstract
The tumor–stroma percentage (TSP) has been proposed as a prognostic factor in ovarian cancer. When assessed manually by pathologists, the TSP can be subject to significant inter‐rater variability. Automated methods for TSP determination have recently been developed. Existing approaches typically yield a single TSP value for a relatively small region of interest in the slide, introducing bias through region selection and potentially overlooking the TSP distribution across the entire histologically examined area. We present an adaptable deep learning pipeline, efficiently fine‐tuned for ovarian cancer tissue analysis using a few‐shot learning approach, requiring only minimal new training annotations. Instead of calculating a single TSP value, our method quantifies the global TSP distribution across the entire tumor and therefore captures its spatial heterogeneity. To identify a prognostic biomarker, we systematically evaluated a panel of metrics describing this distribution in 98 patients. Our analysis revealed that the mean–median difference of the TSP distribution [hazard ratio (HR) = 0.60, 95% CI = 0.46–0.79, p < 0.001], a quantitative measure of asymmetry, together with the mean TSP (HR = 0.65, 95% CI = 0.43–0.97, p = 0.03), are biomarkers significantly associated with recurrence‐free survival. By successfully adapting a pipeline for ovarian cancer, we demonstrate that automated analysis of the entire TSP distribution provides significant prognostic information superior to that obtained by manual assessment. Spatial heterogeneity of the TSP is a key prognostic factor. © 2026 Fraunhofer IIS and The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.Keywords
This publication has 31 references indexed in Scilit:
- Tumor clusters with divergent inflammation and human retroelement expression determine the clinical outcome of patients with serous ovarian cancerMolecular Oncology, 2025
- Tumor-Stroma Proportion to Predict Chemoresistance in Patients With Ovarian CancerJAMA Network Open, 2024
- Standardization of the tumor-stroma ratio scoring method for breast cancer researchBreast Cancer Research and Treatment, 2022
- Tumour-stroma ratio outperforms tumour budding as biomarker in colon cancer: a cohort studyInternational Journal of Colorectal Disease, 2021
- Automated assessment of CD8+ T-lymphocytes and stroma fractions complement conventional staging of colorectal cancerEBioMedicine, 2021
- Artificial intelligence quantified tumour-stroma ratio is an independent predictor for overall survival in resectable colorectal cancerEBioMedicine, 2020
- Computer aided quantification of intratumoral stroma yields an independent prognosticator in rectal cancerCellular Oncology, 2019
- The prognostic value of the tumour-stroma ratio in primary operable invasive cancer of the breast: a validation studyBreast Cancer Research and Treatment, 2017
- The prognostic value of tumour-stroma ratio in triple-negative breast cancerEuropean Journal of Surgical Oncology, 2012
- MULTIVARIABLE PROGNOSTIC MODELS: ISSUES IN DEVELOPING MODELS, EVALUATING ASSUMPTIONS AND ADEQUACY, AND MEASURING AND REDUCING ERRORSStatistics in Medicine, 1996