What question did this study set out to answer?

The aim is to develop a method utilizing computer vision to analyze tumor-infiltrating lymphocytes and improve predictions of neoadjuvant systemic therapy response in breast cancer.

February 22, 2026Open Access

A computer vision method to evaluate tumor-infiltrating lymphocytes and multiparametric modeling of neoadjuvant systemic therapy response in breast cancer

Key Points

The aim is to develop a method utilizing computer vision to analyze tumor-infiltrating lymphocytes and improve predictions of neoadjuvant systemic therapy response in breast cancer.
Performed a retrospective analysis of 411 breast cancer patients.
Used machine learning to process clinical and histopathological data.
Applied convolutional neural networks to classify invasive carcinoma and tumor-infiltrating lymphocytes.
Extracted spatial features from TILs to support multiparametric modeling.
Tested multiple machine learning classification models to predict pathological complete response.
Machine learning models achieved high predictive accuracy for NST response.
Best graph feature model reached an AUC of 0.924 for predictive accuracy.
Ensemble models combining clinical and graph features showed the highest performance with an AUC of 0.955.
Significant predictive performance differences for triple-negative breast cancer between various model types were noted.

Abstract

Background: Neoadjuvant systemic therapy (NST) is often used to treat locally advanced breast cancer (BC) or patients with early-stage BC at high risk for micrometastatic spread. Pathological complete response (pCR) to NST in BC is associated with excellent prognostic outcomes; however, rates vary significantly. Tumor-infiltrating lymphocytes (TILs) are associated with NST response, suggesting potential as predictive biomarkers. Objective: To develop a computer vision approach to quantify spatial TIL parameters and a multiparametric machine learning (ML) model for predicting NST response. Design: Retrospective, single institution study of 411 BC patients, combining clinical and graph-level pre-treatment histopathology data to predict response to NST using ML. Methods: Pre-treatment core needle biopsies were prepared, stained with hematoxylin and eosin, and digitized into whole slide images. Convolutional neural networks were applied to segment and classify regions of invasive carcinoma and TILs. Spatial features were extracted based on the coordinates of the TILs within invasive regions, including metrics from Delaunay triangulation, Voronoi diagram analysis, and minimum spanning trees, as well as features capturing cell density and nuclear count. Clinicopathological features were incorporated to support multiparametric modeling. Multiple ML classification models were trained to predict pCR. Logistic regression, K-nearest neighbor, support vector, random forest, Gaussian Naïve Bayes, and extreme gradient boosting models were tested, and model performances were reported. Results: ML models using clinical and graph-based features achieved high predictive accuracy. The best performing graph feature model reached an area under the receiver operating characteristic curve (AUC) of 0.924. Ensemble models integrating clinical and graph features showed the highest performance, with an AUC of 0.955. Notably, for triple-negative BC, significant differences in predictive performance were demonstrated between clinical and graph feature models ( p = 0.026) and between clinical and ensemble models ( p = 0.006). Conclusion: Multiparametric modeling utilizing clinicopathological and graph features obtained from TILs is associated with pCR in BC patients treated with NST.

Read Full Paperexternally

Ask AI

Helpful

Bookmark

View Full Paper