aiqbench analysis
This study introduces a two-stage AI framework that infers transcriptomic data directly from histopathology images to predict therapy response in breast cancer, addressing the critical scarcity of labeled genomic datasets. By decoupling expression inference from clinical prediction, the model achieves robust performance across diverse cohorts while minimizing reliance on invasive genomic assays. The approach demonstrates how biologically informed compression can enhance precision oncology tools in data-sparse environments.
Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies
arXiv:2610.03693v1 Announce Type: new Abstract: Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model predicting pathological complete response (pCR) to neoadjuvant therapy in breast cancer. The first stage learns the transcriptome from histopathology using 8,742 patients across 32 cancer types, corroborated by pathologist review and spatial agreement with measured expression. This simplifies the second stage to predicting pCR from inferred expression and clinical variables. Developed using 1,080 patients (five cohorts) and evaluated in 1,412 patients (nine cohorts), the model achieves a pooled AUROC of 0.79 (95% CI, 0.73-0.85), discriminating responders within molecular subtypes. It outperforms histopathological biomarkers, remaining stable across intratumoral sampling and with minimal biopsy tissue. Ablations show transcriptome-wide inference improves discrimination over clinical variables alone or one-stage pathology models, and robustness by avoiding genomic assays' gene selection constraints. These results indicate that biologically informed compression may generalize to data-sparse applications in precision oncology.
Authors:Jungkyu Park, Dhruva Biswas, Joseph Cappadona, Cerise Tang, Ken G. Zeng, Bartosz Machura, Chuwen Liu, Paolo Tarantino, Coral Omene, Francisco J. Esteva, Rohit Bhargava, Marcin Braun, Kamila Paździerz, Jakub Czerwiński, Hanna Romańska-Knight, Albert Grinshpun, Bareket Daniel, Michele Buchinger, Frederick Howard, Piotr Wysocki, Brie Chun, Freya Schnabel, Rich Caruana, Jan Witowski, Krzysztof J. Geras
Abstract:Scarcity of labeled data limits development of deep learning biomarkers in oncology. We develop a two-stage AI model predicting pathological complete response (pCR) to neoadjuvant therapy in breast cancer. The first stage learns the transcriptome from histopathology using 8,742 patients across 32 cancer types, corroborated by pathologist review and spatial agreement with measured expression. This simplifies the second stage to predicting pCR from inferred expression and clinical variables. Developed using 1,080 patients (five cohorts) and evaluated in 1,412 patients (nine cohorts), the model achieves a pooled AUROC of 0.79 (95% CI, 0.73-0.85), discriminating responders within molecular subtypes. It outperforms histopathological biomarkers, remaining stable across intratumoral sampling and with minimal biopsy tissue. Ablations show transcriptome-wide inference improves discrimination over clinical variables alone or one-stage pathology models, and robustness by avoiding genomic assays' gene selection constraints. These results indicate that biologically informed compression may generalize to data-sparse applications in precision oncology.
Artificial Intelligence (cs.AI)
arXiv:2610.03693 [cs.AI]
(or arXiv:2610.03693v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.03693 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 220 words
Related coverage
Early Prediction of Pathological Complete Response to Neoadjuvant Chemotherapy Using Temporal Deep Learning on DWI
arXiv · Sep 24, 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · Aug 26, 2026
Six Principles of Voice Design: Designing for the Ear and Encoding It into Agent Script
Salesforce Blog · Oct 8, 2026
Benchmarking Machine Learning Models for Multi-Omics-Based Breast Cancer Prediction
arXiv · Jul 21, 2026