Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
February 22, 2026Clinical Cancer Research

Abstract PS3-04-01: Prediction of pathologic complete response from histopathology images of HER2+ breast cancer using an AI foundation model

View Full Paper
Ask AI
Bookmark
Share

Authors

RBReva BashoLarry Ellison FoundationEHE. HerediaAdvanced Medical Research InstituteHMH. McArthurThe University of Texas Southwestern Medical Center

Discussion

Loading...

Member takes

Overview

This predictive model evaluates pathologic complete response in HER2+ breast cancer patients, suggesting enhanced patient selection for therapy.

Key Points

  • To predict pathologic complete response (pCR) using histopathology images in HER2+ breast cancer patients.
  • Utilized baseline H&E-stained biopsy images from publicly available and institutional datasets.
  • Developed an AI/ML model using CanvOI, focusing on HR status differences.
  • Employed logistic regression for vector-data classification and evaluated performance using cross-validation.
  • Implemented sample trimming to address pCR rate imbalances within HR+ and HR- cohorts.
  • Overall pCR rates were 40.4% for HR+ and 64.1% for HR- patients.
  • Model showed a mean AUC of 0.69 (95% CI: 0.66-0.73) for HER2+/HR+ and 0.65 (95% CI: 0.61-0.69) for HER2+/HR- patients.
  • Improved model performance with mean AUC of 0.70 for HER2+/HR+ after data balancing techniques.

Cite This Study

Basho et al. (2026) studied this question.

synapsesocial.com/papers/699a9e0e482488d673cd46bbhttps://doi.org/10.1158/1557-3265.sabcs25-ps3-04-01
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Predicting Pathological Complete Response in HER2+ Breast Cancer: An AI-Driven Model Using Standard Clinical Practice Parameters2025
  2. 2Abstract PD11-03: Predicting treatment outcomes in breast cancer from H&E slides using pathology foundation models with multiple instance learning2026
  3. 3Abstract PS3-10-30: A clinical model to predict pathologic complete response using early peripheral absolute lymphocyte dynamics in HER2+ breast cancer2026
  4. 4Abstract PO4-01-10: Multi-modal artificial intelligence models from baseline histopathology predict prognosis in HR+ HER2- early breast cancer2024 · 1 citations
  5. 5Clinicopathology-based machine learning model for prediction of pathologic complete response to neoadjuvant chemotherapy in breast cancer.2026