Wu Zhou1, Shangxuan Li1, Wanwei Jian1, Guangyi Wang2, Lijuan Zhang3, and Honglai Zhang1
1School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou, China, 2Department of Radiology, Guangdong General Hospital, Guangzhou, China, 3Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
1School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou, China, 2Department of Radiology, Guangdong General Hospital, Guangzhou, China, 3Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
The purpose is to address the problem of multimodal fusion with contrast-enhanced MR for grading hepatocellular carcinoma(HCC). We proposed a discriminative feature learning and adaptive fusion method in the framework of deep learning architecture for improving the fusion performance.
Figure 2. The framework of the proposed multimodal fusion method.
Figure 1. Contrast-enhanced MR images of a 59-year-old man with pathologically confirmed low-grade HCCs (grade II, white arrow) (a) the pre-contrast phase (b) the arterial phase (c) the portal vein phase (d) the delayed phase.