跳到正文
原文
Medical Xpress·· 29 天前AI 评分60

AI 模型 HRDPath 通过组织图像识别卵巢癌 HRD 状态

AI model detects signs of faulty DNA repair in ovarian cancer using tissue images

AI 导读

King's College London 研究人员开发的 AI 模型 HRDPath 可通过卵巢癌组织病理图像识别同源重组修复缺陷(HRD),在纳入同一患者多张图像时对 HRD 阳性病例的识别率约为 91%,研究发表于 Nature Communications。

正文
AI model detects signs of faulty DNA repair in ovarian cancer using tissue images
Ovarian cancer tissue image. Credit: Heba Sailem/King's College London

An AI model created by researchers at King's can detect signs of faulty repair mechanisms in ovarian cancer cells, potentially leading to a low-cost, widely accessible diagnostic tool in the future. By analyzing tissue images, the model could accurately recognize tumors that contained broken DNA repair mechanisms. This could enable clinicians to choose treatments that exploit this flaw. The findings are published in Nature Communications.

"We are unlocking information hidden in microscopic images of cancer tissue that could transform how we match patients to treatments. By using AI to reveal defects in DNA repair, we could make precision cancer medicine faster, more affordable and accessible to more women with ovarian cancer, not just in the U.K. but around the world," said Dr. Heba Sailem, reader in computational pathology at King's College London.

DNA repair defects guide treatment choices

The study focused on high-grade serous tubo-ovarian carcinoma (HGSOC), an aggressive form of cancer that arises in the ovaries or fallopian tubes. One of the most important characteristics of this cancer is something called homologous recombination deficiency, or HRD.

Cancer cells with HRD, which can arise from mutations in genes such as BRCA1 and BRCA2, have an impaired ability to repair DNA damage. This weakness can make cancer cells more vulnerable to certain treatments—in particular, platinum-based chemotherapy and a class of drugs called PARP inhibitors.

This makes HRD a valuable biomarker, as it helps doctors decide which treatments are likely to be effective. However, current HRD tests require sophisticated genetic analysis, which can be expensive, time-consuming and difficult to access in health care settings with fewer resources.

HRDPath reads clues in tissue images

In the study led by Sailem, the researchers developed a model called HRDPath. Rather than looking at DNA, HRDPath analyzed high-resolution digital images of tissue samples under a microscope. The model was trained to recognize HRD-positive and negative cancers using tissue images from patients whose HRD status was already known through genomic analysis.

AI model detects signs of faulty DNA repair in ovarian cancer using tissue images
HRDPath pipeline, including patch extraction, feature embedding via RetCCL, model training, and prediction. Credit: Nature Communications (2026). DOI: 10.1038/s41467-026-78430-y

HRDPath demonstrated promising accuracy in identifying HRD-positive cancers, especially when considering several images from the same patient, correctly identifying approximately 91% of HRD-positive cases.

The researchers also identified subtle differences in the appearance and organization of cancer cells associated with HRD. For example, HRD-positive cancers tended to have rounder cell nuclei and more densely packed cancer cells in certain tumor regions. The findings suggest that defects in DNA repair are associated with physical changes in tumor tissue that can be recognized by AI, and may be difficult to recognize through conventional examination.

Wider access hinges on further validation

The researchers believe HRDPath has the potential to make precision cancer medicine more accessible. If HRD status can be reliably identified using tissue images that hospitals already acquire for diagnosis, the technology could reduce reliance on expensive genetic testing and help clinicians identify patients who may benefit from treatments such as platinum-based chemotherapy and PARP inhibitors.

While further research is needed to validate the model in larger patient populations, HRDPath represents a promising step toward making personalized cancer treatment more widely available, helping more patients access therapies tailored to their individual tumors.

Publication details

Chun-I Wu et al., HRDPath: an explainable multi-model deep learning architecture for predicting homologous recombination deficiency from histopathology images, Nature Communications (2026). DOI: 10.1038/s41467-026-78430-y

Journal information: Nature Communications

Clinical categories

Oncology

Who's behind this story?

Lisa Lock

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →

Robert Egan

Robert Egan

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

Citation: AI model detects signs of faulty DNA repair in ovarian cancer using tissue images (2026, October 21) retrieved 21 October 2026 from https://medicalxpress.com/news/2026-10-ai-faulty-dna-ovarian-cancer.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

来源:Medical Xpress · medicalxpress.com