近日，美国哈佛医学院Kun-HsingYu和Sen Yang研究组报道了肿瘤诊断和预后预测的病理学基础模型。相关论文于2024年9月4日发表于国际顶尖学术期刊《自然》杂志上。

为了应对通用性受限的挑战，该团队设计了临床组织病理学成像评估基础(CHIEF)模型，这是一个通用的弱监督机器学习框架，用于提取病理成像特征以进行系统的癌症评估。CHIEF利用两种互补的预训练方法来提取不同的病理表征:用于切片水平特征识别的无监督预训练和用于整个片子模式识别的弱监督预训练。

该团队开发了60,530张横跨19个解剖部位的全片图像。通过对44tb高分辨率病理成像数据集的预训练，CHIEF提取了对癌细胞检测、肿瘤起源鉴定、分子谱表征和预后预测具有重要意义的微观表征。该课题组人员用来自于国际上24家医院的32个独立玻片样本组的19491张完整的玻片图像成功地验证了CHIEF。

总体而言，CHIEF的表现比最先进的深度学习方法高出36.1%，这表明它有能力解决来自不同人群的样本中观察到的域转移，并对不同的玻片制备方法进行加工计算。CHIEF为肿瘤患者的高效数字化病理评估提供了可推广的基础。

据了解，组织病理学图像评价是肿瘤诊断和分型不可缺少的手段。组织病理学图像分析的标准人工智能方法侧重于为每个诊断任务优化专门模型。虽然这些方法取得了一些成功，但它们通常对不同数字化步骤生成的图像或从不同人群收集的样本的通用性有限。

附：英文原文

Title: A pathology foundation model for cancer diagnosis and prognosis prediction

Author: Wang, Xiyue, Zhao, Junhan, Marostica, Eliana, Yuan, Wei, Jin, Jietian, Zhang, Jiayu, Li, Ruijiang, Tang, Hongping, Wang, Kanran, Li, Yu, Wang, Fang, Peng, Yulong, Zhu, Junyou, Zhang, Jing, Jackson, Christopher R., Zhang, Jun, Dillon, Deborah, Lin, Nancy U., Sholl, Lynette, Denize, Thomas, Meredith, David, Ligon, Keith L., Signoretti, Sabina, Ogino, Shuji, Golden, Jeffrey A., Nasrallah, MacLean P., Han, Xiao, Yang, Sen, Yu, Kun-Hsing

Issue&Volume: 2024-09-04

Abstract: Histopathology image evaluation is indispensable for cancer diagnoses and subtype classification. Standard artificial intelligence methods for histopathology image analyses have focused on optimizing specialized models for each diagnostic task1,2. Although such methods have achieved some success, they often have limited generalizability to images generated by different digitization protocols or samples collected from different populations3. Here, to address this challenge, we devised the Clinical Histopathology Imaging Evaluation Foundation (CHIEF) model, a general-purpose weakly supervised machine learning framework to extract pathology imaging features for systematic cancer evaluation. CHIEF leverages two complementary pretraining methods to extract diverse pathology representations: unsupervised pretraining for tile-level feature identification and weakly supervised pretraining for whole-slide pattern recognition. We developed CHIEF using 60,530 whole-slide images spanning 19 anatomical sites. Through pretraining on 44 terabytes of high-resolution pathology imaging datasets, CHIEF extracted microscopic representations useful for cancer cell detection, tumour origin identification, molecular profile characterization and prognostic prediction. We successfully validated CHIEF using 19,491 whole-slide images from 32 independent slide sets collected from 24 hospitals and cohorts internationally. Overall, CHIEF outperformed the state-of-the-art deep learning methods by up to 36.1%, showing its ability to address domain shifts observed in samples from diverse populations and processed by different slide preparation methods. CHIEF provides a generalizable foundation for efficient digital pathology evaluation for patients with cancer.

DOI: 10.1038/s41586-024-07894-z

Source: https://www.nature.com/articles/s41586-024-07894-z