A Computation-Efficient CNN System for High-Quality Brain Tumor Segmentation

In this paper, a Convolutional Neural Network (CNN) system is proposed for brain tumor segmentation. The system consists of three parts, a pre-processing block to reduce the data volume, an application-specific CNN(ASCNN) to segment tumor areas precisely, and a refinement block to detect/remove false positive pixels. The CNN, designed specifically for the task, has 7 convolution layers, 16 channels per layer, requiring only 11716 parameters. The convolutions combined with max-pooling in the first half of the CNN are performed to localize tumor areas. Two convolution modes, namely depthwise convolution and standard convolution, are performed in parallel in the first 2 layers to extract elementary features efficiently. For a fine classification of pixel-wise precision in the second half of the CNN, the feature maps are modulated by adding the individually weighted local feature maps generated in the first half of the CNN. The performance of the proposed system has been evaluated by an online platform with dataset of Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) 2018. Requiring a very low computation volume, the proposed system delivers a high segmentation quality indicated by its average Dice scores of 0.75, 0.88 and 0.76 for enhancing tumor, whole tumor and tumor core, respectively, and also by the median Dice scores of 0.85, 0.92, and 0.86. The consistency in system performance has also been measured, demonstrating that the system is able to reproduce almost the same output to the same input after retraining. The simple structure of the proposed system facilitates its implementation in computation restricted environment, and a wide range of applications can thus be expected.