卷积神经网络
微转移
工作流程
计算机科学
淋巴结
医学
接收机工作特性
人工智能
放射科
转移
癌症
模式识别(心理学)
病理
机器学习
内科学
数据库
作者
Shih‐Chiang Huang,Chi‐Chung Chen,Jui Lan,Tsan-Yu Hsieh,Huei‐Chieh Chuang,Meng-Yao Chien,Tao-Sheng Ou,Kuang-Hua Chen,Ren‐Chin Wu,Yu‐Jen Liu,Chi‐Tung Cheng,Yen-Hsiang Huang,Liang-Wei Tao,An-Fong Hwu,I-Chieh Lin,Shih-Hao Hung,Chao‐Yuan Yeh,Tse‐Ching Chen
标识
DOI:10.1038/s41467-022-30746-1
摘要
Abstract The pathological identification of lymph node (LN) metastasis is demanding and tedious. Although convolutional neural networks (CNNs) possess considerable potential in improving the process, the ultrahigh-resolution of whole slide images hinders the development of a clinically applicable solution. We design an artificial-intelligence-assisted LN assessment workflow to facilitate the routine counting of metastatic LNs. Unlike previous patch-based approaches, our proposed method trains CNNs by using 5-gigapixel images, obviating the need for lesion-level annotations. Trained on 5907 LN images, our algorithm identifies metastatic LNs in gastric cancer with a slide-level area under the receiver operating characteristic curve (AUC) of 0.9936. Clinical experiments reveal that the workflow significantly improves the sensitivity of micrometastasis identification (81.94% to 95.83%, P < .001) and isolated tumor cells (67.95% to 96.15%, P < .001) in a significantly shorter review time (−31.5%, P < .001). Cross-site evaluation indicates that the algorithm is highly robust (AUC = 0.9829).
科研通智能强力驱动
Strongly Powered by AbleSci AI