肝癌診療決策支援系統

肝癌AI診療發展里程碑

平台技術與研究

HFS-Net

Hierarchical Fusion Strategy Network for Tumor Segmentation from Computed Tomography Imaging of Liver Tumors

In the independent test, HFS-Net achieved the dice score of 63.9% in segmentation, and sensitivity and F1-score of 91.8% and 85.5% in tumor detection, respectively.

演化學習建立的臨床放射學模型-預測肝癌切除後早期復發

Evolutionary Learning Derived Clinical-Radiomic Models for Predicting Early Recurrence of Hepatocellular Carcinoma After Resection

Liver Cancer, Accepted (31 July. 2021). IF=11.740

本期刊第一篇AI預測論文

miRNA的AI預測

SY Sathipati and S-Y Ho*, Novel miRNA signature for predicting the stage of hepatocellular carcinoma, Scientific reports 10 (1), 1-12, 2020/9/2.

SVM-HCC identified a 23-miRNA signature that achieved a CV, sensitivity, specificity, Matthews correlation coefficient, and AUC of 92.59%, 0.98, 0.74, 0.80, and 0.86, respectively; and test accuracy and AUC of 74.28% and 0.73, respectively.

在精準醫療的趨勢下miRNA的AI預測在未來有機會成為新的標準

Onishi M, Ochiya T, Tanaka Y. MicroRNA and liver cancer. Cancer Drug Resist 2020;3:385-400.