Automatic Brain Tumour Subregion Segmentation from Multimodal MRIs Fusing Muti-channel and Spatial Features

Abstract It is very necessary for disease diagnosis, monitoring and treatment planning to locate and segment brain tumours from 3D MRI images accurately. 3D segmentation from MRIs means classifying each voxel in 3D space, it is very conducive to the relevant biological measurements and further analysis of the lesion. Until now, brain tumour segmentation from 3D biomedical images has been a challenging worldwide task due to the tumour features’ variousness, which varies part of U-Net and concatenates these features, which are upsampled to the same scale. To grasp the channel weight and ROIs, the bottleneck of the network is an improved dual path attention module, which convergence the advantages of channel attention and spatial attention. The proposed model has been validated in the online dataset of BraTS 2018. The mean dice score of enhancing tumours is 0.772. The mean dice score of the whole tumour is 0.907. The mean dice score of the tumour core is 0.819. The effectiveness of the proposed method is proved by quantitative and qualitative evaluation.