Background: Brain tumor segmentation plays an important role in assisting diagnosis of disease, treatment plan planning, and surgical navigation.
Objective: This study aims to improve the accuracy of tumor boundary segmentation using the multi-scale U-Net network.
Methods: In this study, a novel U-Net with dilated convolution (DCU-Net) structure is proposed for brain tumor segmentation based on the classic U-Net structure. First, the MR brain tumor images are pre-processed to alleviate the class imbalance problem by reducing the input of the background pixels. Then, the multi-scale spatial pyramid pooling is used to replace the max pooling at the end of the down-sampling path. It can expand the feature receptive field while maintaining image resolution. Finally, a dilated convolution residual block is combined to improve the skip connections in the training networks to improve the network's ability to recognize the tumor details.
Results: The proposed model has been evaluated using the Brain Tumor Segmentation (BRATS) 2018 Challenge training dataset and achieved the dice similarity coefficients (DSC) score of 0.91, 0.78 and 0.83 for whole tumor, core tumor and enhancing tumor segmentation, respectively.
Conclusions: The experiment results indicate that the proposed model yields a promising performance in automated brain tumor segmentation.
Keywords: Brain tumor segmentation; DCU-Net; U-Net; dilated convolution; multi-scale spatial pyramid pooling.