Adaptive feature recombination and recalibration for semantic segmentation with Fully Convolutional Networks

Abstract

Fully Convolutional Networks have been achieving remarkable results in image semantic segmentation, while being efficient. Such efficiency results from the capability of segmenting several voxels in a single forward pass. So, there is a direct spatial correspondence between a unit in a feature map and the voxel in the same location. In a convolutional layer, the kernel spans over all channels and extracts information from them. We observe that linear recombination of feature maps by increasing the number of channels followed by compression may enhance their discriminative power. Moreover, not all feature maps have the same relevance for the classes being predicted. In order to learn the inter-channel relationships and recalibrate the channels to suppress the less relevant ones, Squeeze and Excitation blocks were proposed in the context of image classification with Convolutional Neural Networks. However, this is not well adapted for segmentation with Fully Convolutional Networks since they segment several objects simultaneously, hence a feature map may contain relevant information only in some locations. In this paper, we propose recombination of features and a spatially adaptive recalibration block that is adapted for semantic segmentation with Fully Convolutional Networks - the SegSE block. Feature maps are recalibrated by considering the cross-channel information together with spatial relevance. Experimental results indicate that Recombination and Recalibration improve the results of a competitive baseline, and generalize across three different problems: brain tumor segmentation, stroke penumbra estimation, and ischemic stroke lesion outcome prediction. The obtained results are competitive or outperform the state of the art in the three applications.

arXiv commentPublished in IEEE Transactions on Medical Imaging (TMI)

References in corpus (7)

• A Survey on Deep Learning in Medical Image Analysis
• Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation
• Brain Tumor Segmentation with Deep Neural Networks
• A deep learning model integrating FCNNs and CRFs for brain tumor segmentation
• Automatic Brain Tumor Segmentation using Cascaded Anisotropic Convolutional Neural Networks
• Enhancing clinical MRI Perfusion maps with data-driven maps of complementary nature for lesion outcome prediction
• Adaptive feature recombination and recalibration for semantic segmentation: application to brain tumor segmentation in MRI

Cited by in corpus (7)

• Cross-Modality Deep Feature Learning for Brain Tumor Segmentation
• Combining unsupervised and supervised learning for predicting the final stroke lesion
• A Computation-Efficient CNN System for High-Quality Brain Tumor Segmentation
• Recalibrating 3D ConvNets with Project & Excite
• Transformers-based architectures for stroke segmentation: A review
• Online Continual Learning via the Knowledge Invariant and Spread-out Properties
• Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation