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

<div>An example of discrepancy between ground truth (GT) and segmentation by the radiologist with moderate experience. The original hepatobiliary phase- (HBP-) magnetic resonance imaging (MRI) image was presented (a). (b) GT and (c) segmentation by the radiologist with moderate experience were presented in indigo and blue, respectively. The radiologist with moderate experience tended to contour a smaller border when the hepatocellular carcinoma (HCC) lesion had unclear margins.</div>

BioMed Research International

fig5

Figure 5

Figure 5: Deep Learning Combined with Radiologist’s Intervention Achieves Accurate Segmentation of Hepatocellular Carcinoma in Dual-Phase Magnetic Resonance Images 

Figure 5 | Deep Learning Combined with Radiologist’s Intervention Achieves Accurate Segmentation of Hepatocellular Carcinoma in Dual-Phase Magnetic Resonance Images 