Weighted Monte Carlo augmented spherical Fourier-Bessel convolutional layers for 3D abdominal organ segmentation

arXiv:2402.16825v2 Announce Type: replace
Abstract: Filter-decomposition-based group equivariant convolutional neural networks show promising stability and data efficiency for 3D image feature extraction. However, the existing filter-decomposition-based 3D group equivariant neural networks rely on parameter-sharing designs and are mostly limited to rotation transform groups, where the chosen spherical harmonic filter bases consider only angular orthogonality. These limitations hamper its application to deep neural network architectures for medical image segmentation. To address these issues, this paper describes a non-parameter-sharing affine group equivariant …

arxiv cs.cv fourier segmentation type