Deep convolutional neural network for preoperative prediction of microvascular invasion and clinical outcomes in patients with HCCs.

Xinming LiZhendong QiHaiyan DuZhijun GengZhipeng LiShuping QinXuhui ZhangJianye LiangXiao ZhangWen LiangWei YangChuanmiao XieXian-Yue Quan

Published in: European radiology (2021)

• A combined nomogram based on clinical information, preoperative CECT, and DCNN can predict MVI and clinical outcomes of patients with HCC. • DCNN provides added diagnostic ability to predict MVI. • The AUCs of the combined nomogram are 0.940 and 0.897 in the training and validation cohorts, respectively.

Keyphrases

convolutional neural network
patients undergoing
deep learning
lymph node metastasis
cell migration
squamous cell carcinoma
health information
machine learning
social media