Neuromorphic Neural Network for Multimodal Brain Image Segmentation and Overall Survival Analysis

Image analysis of brain tumors is one of key elements for clinical decision, while manual segmentation is time consuming and known to be subjective to clinicians or radiologists. In this paper, we examined the neuromorphic convolutional neural network on this task of multimodal images, using a down-up resizing network structure. The controlled rectifier neuron function was incorporated in neuromorphic neural network, for introducing the efficiency of segmentation and saliency map generation used in noisy image processing of X-ray CT data and dark road video data. The neuromorphic neural network is proposed to the brain imaging analytic, based on the visual cortex-inspired deep neural network developed for 3 dimensional tooth segmentation and robust visual object detection. Experiment results illustrated the effectiveness and feasibility of our proposed method with flexible requirements of clinical diagnostic decision data, from segmentation to overall survival analysis. The survival prediction was 71% accuracy for the data with true result and 50.6% accuracy of predicting survival days for the individual challenge data without any clinical diagnostic data.