In view of the characteristics of long course and mild disease development of breast cancer, a multi-task recurrent neural network banded regression model is proposed to analyze individual survival of breast cancer. First, a multi-task banded regression model based on recurrent neural network is proposed to optimize the individual survival analysis of patients by identifying the difference in the effects of various pathological features on different patients. Then, the form of the banded check matrix is expanded and its effect on the hazard distribution of patient is investigated. Finally, the survival analysis on the real datasets of breast cancer shows obvious differences among different patients, which verifies the validity of the model. The survival analysis on two real datasets of breast cancer shows that the C-index of the multi-task banded regression model based on recurrent neural network is greatly improved compared with the Cox regression model commonly used in medicine, and has a smaller 95% confidence interval.

Hepatobiliary stone disease is a common liver disease and has become the main cause of death from non-neoplastic biliary diseases in China, and it is important to achieve interpolated segmentation reconstruction between slices of hepatobiliary ducts. In this research, an end-to-end framework for super-resolution abdominal CT image processing is proposed based on deep correlation mechanism. The framework cascades an inter-slice interpolation network and a segmentation network, in which the ConvLSTM is introduced to enhance the extraction of high-dimensional feature information of hepatobiliary ducts between slices. A novel loss is designed by combining the loss of the interpolation network and the loss of the segmentation network. Experimental results show that the proposed framework is superior to the existing deep learning methods for the segmentation of hepatobiliary ducts, which is beneficial for the 3D reconstruction of hepatobiliary ducts.