Deep learning model with pathological knowledge for detection of colorectal neuroendocrine tumor

作者：Ke Zheng, Jin‐Ling Duan, Ruixuan Wang, Haohua Chen, Haiyang He, Xueyi Zheng, Zihan Zhao, Bingzhong Jing, Yuqian Zhang, Shasha Liu, Dan Xie, Yuan Lin, Yan Sun, Ning Zhang, Muyan Cai · 发表于：Cell Reports Medicine · 年份：2024 · DOI：10.1016/j.xcrm.2024.101785 · 被引用次数：9 · 研究领域：Pancreatic and Hepatic Oncology Research、Radiomics and Machine Learning in Medical Imaging、AI in cancer detection

Colorectal neuroendocrine tumors (NETs) differ significantly from colorectal carcinoma (CRC) in terms of treatment strategy and prognosis, necessitating a cost-effective approach for accurate discrimination. Here, we propose an approach for distinguishing between colorectal NET and CRC based on pathological images by utilizing pathological prior information to facilitate the generation of robust slide-level features. By calculating the similarity between morphological descriptions and patches, our approach selects only 2% of the diagnostically relevant patches for both training and inference, achieving an area under the receiver operating characteristic curve (AUROC) of 0.9974 on the internal dataset, and AUROCs of 0.9724 and 0.9513 on two external datasets. Our model effectively identifies NETs from CRCs, reducing unnecessary immunohistochemical tests and enhancing the precise treatment for patients with colorectal tumors. Our approach also enables researchers to investigate methods with high accuracy and low computational complexity, thereby advancing the application of artificial intelligence in clinical settings. • Deep learning can discriminate between NET and CRC in biopsied and surgical sections • The model can identify diagnostically relevant areas akin to experienced pathologists • Region selection and pre-trained model can improve generalization capability Zheng et al. develop a deep learning model that accurately distinguishes between NET and CRC using a limited nu...