转录组信息驱动的多模态 AI 从乳腺癌活检预测新辅助治疗反应
Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsies
研究团队开发两阶段 AI 模型，从乳腺癌活检组织病理图像预测新辅助治疗病理完全缓解（pCR）。第一阶段用 8,742 名、32 种癌症患者数据从病理图像学习转录组，第二阶段基于推断表达与临床变量预测 pCR，在 1,412 名患者（九个队列）中取得 0.79 的汇总 AUROC（95% CI 0.73-0.85），优于组织病理学生物标志物，且在瘤内采样和少量活检组织下保持稳定。
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | 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) |
Submission history
From: Jungkyu Park [view email]
[v1]
Fri, 2 Oct 2026 17:52:57 UTC (7,476 KB)
来源：arXiv：cs.AI · arxiv.org