Adaptive feature recombination and recalibration for semantic segmentation: application to brain tumor segmentation in MRI
This work addresses the challenge of accurate brain tumor segmentation in medical imaging, which is crucial for diagnosis and treatment planning, but it is incremental as it builds upon existing SE blocks and FCN architectures.
The paper tackled the problem of suboptimal feature map recalibration in fully convolutional networks for semantic segmentation by proposing feature recombination and a segmentation-specific SE block, achieving improved performance on brain tumor segmentation in MRI with a reported Dice score increase of 2-3% over baseline methods.
Convolutional neural networks (CNNs) have been successfully used for brain tumor segmentation, specifically, fully convolutional networks (FCNs). FCNs can segment a set of voxels at once, having a direct spatial correspondence between units in feature maps (FMs) at a given location and the corresponding classified voxels. In convolutional layers, FMs are merged to create new FMs, so, channel combination is crucial. However, not all FMs have the same relevance for a given class. Recently, in classification problems, Squeeze-and-Excitation (SE) blocks have been proposed to re-calibrate FMs as a whole, and suppress the less informative ones. However, this is not optimal in FCN due to the spatial correspondence between units and voxels. In this article, we propose feature recombination through linear expansion and compression to create more complex features for semantic segmentation. Additionally, we propose a segmentation SE (SegSE) block for feature recalibration that collects contextual information, while maintaining the spatial meaning. Finally, we evaluate the proposed methods in brain tumor segmentation, using publicly available data.