Deep Learning Combined with Radiologist's Intervention Achieves Accurate Segmentation of Hepatocellular Carcinoma in Dual-Phase Magnetic Resonance Images.

Deep learning using dual-phase MRI shows great potential for HCC lesion segmentation. The radiologist-aided semiautomated method (DFN-R) achieved improved performance compared to manual contouring by the radiologist with moderate experience, although the difference was not statistically significant.