Abstract: The present invention relates to methods for predicting the recurrence risk of hepatocellular carcinoma (HCC). Specifically, it proposes a deep learning model capable of integrating information from different phases of CT images and clinical data to predict the risk of HCC recurrence within 1 to 5 years after treatment. Experimental results demonstrate that these models outperform traditional prediction methods based on histological microvascular invasion (MVI) in predicting HCC recurrence risk.

Abstract: A novel medical image generation approach synthesizes thin-cut computerized tomography (CT) images from thick-cut CT ones as inputs. First thick-cut CT images are obtained by maximizing the pixel-wise intensity of five or more than five continuous thin-cut ones after image registration. Second, the obtained thick-cut CT images are fed into a generator block which adopts an encoder-decoder architecture, where each thick-cut image is encoded into low-dimensional embedding space before decoding into multiple thin-cut ones. Third, a discriminator focuses on distinguishing original real thin-cut images from synthetic thin-cut images. An adversarial mechanism between the generator and discriminator causes the discriminator's output to provide an effective gradient update of the network parameters for the generator to increasingly improve the generator's ability to synthesize higher-quality thin-cut images and in turn promotes the discriminator's discriminating capability.

Abstract: A three dimensional classification system for recognizing cross-sectional images automatically contains a processor that executes: (1) rescaling of a plurality of cross-sectional images; and feeding the rescaled plurality of cross-sectional images into two branches; (2) feeding the rescaled plurality of cross-sectional images into a first branch for performing a plurality of convolutions on the rescaled plurality of cross-sectional images directly to learn features for distinguishing phases; (3) feeding the rescaled plurality of cross-sectional images into a second branch for reducing resolution, and then performing a plurality of convolutions on the reduced resolution plurality of cross-sectional images to learn features for distinguishing phases; and (4) concatenating convolutional output channels from the two branches to fuse global and local features, on which two fully-connected layers are stacked as a classifier to recognize cross-sectional volumetric images accurately and quickly.