Rethinking Deep Supervision for Brain Tumor Segmentation
Jiale Li, Aiping Liu, Yu Li, Wei Wei, Ruobing Qian, Qingguo Xie, Bensheng Qiu, Xun Chen · IEEE Transactions on Artificial Intelligence · 2023
Accurate segmentation of brain tumors is crucial for diagnostic evaluation and clinical planning. Convolutional-based and Transformer-based models have shown promising results in automatic brain tumor segmentation. In these models, a deep supervision strategy has been widely adopted for parameter optimization. As a key part of this strategy, the segmentation head is responsible for generating early segmentation in the training phase. However, although containing informative cues valuable for decoder refinement, the segmentation head is usually discarded during inference. In this work, we propose a novel approach called Deep Supervision Guided Transformer (DSGT) for brain tumor segmentation. DSGT leverages informative cues within the segmentation head to guide decoding by developing Guided Heads upon a Transformer-based decoder. Specifically, we first extract semantic features from the segmentation head and then design two guided modules for feature refinement and noisy removal to generate sample- wise guiding maps. The resulting maps are fed back to the decoder for auxiliary guidance. Our experiments on two publicly available brain tumor segmentation datasets, BraTS2019 and BraTS2020, demonstrate that DSGT achieves superior segmentation performance compared to state-of-the-art approaches.