Diffraction Block in Extended nn-UNet for Brain Tumor Segmentation

Automatic brain tumor segmentation based on 3D mpMRI is highly significant for brain diagnosis, monitoring, and treatment planning. Due to the limitation of manual delineation, automatic and accurate segmentation based on a deep learning network has a tremendous practical necessity. The BraTS2022 challenge provides many data to develop our network. In this work, we proposed a diffraction block based on the Fraunhofer single-slit diffraction principle, which emphasizes the effect of associated features and suppresses isolated features. We added the diffraction block to nn-UNet, which took first place in the BraTS 2020 competition. We also improved nn-UNet by referring to the solution proposed by the 2021 winner, including using a larger network and replacing the batch with a group normalization. In the final unseen test data, our method is ranked first for Pediatric population data and third for BraTS continuous evaluation data.