Implicit U-Net for volumetric medical image segmentation
This work addresses efficiency issues in volumetric medical image segmentation for healthcare applications, but it is incremental as it builds on existing U-Net and implicit representation methods.
The paper tackles the computational challenges of extending U-Net to 3D medical image segmentation by proposing Implicit U-Net, which reduces parameters by 40% and inference/training time by 30% while achieving comparable results on abdominal CT scan datasets.
U-Net has been the go-to architecture for medical image segmentation tasks, however computational challenges arise when extending the U-Net architecture to 3D images. We propose the Implicit U-Net architecture that adapts the efficient Implicit Representation paradigm to supervised image segmentation tasks. By combining a convolutional feature extractor with an implicit localization network, our implicit U-Net has 40% less parameters than the equivalent U-Net. Moreover, we propose training and inference procedures to capitalize sparse predictions. When comparing to an equivalent fully convolutional U-Net, Implicit U-Net reduces by approximately 30% inference and training time as well as training memory footprint while achieving comparable results in our experiments with two different abdominal CT scan datasets.