Interpretable 2.5D network by hierarchical attention and consistency learning for 3D MRI classification

Shuting Pang, Yidi Chen, Xiaoshuang Shi, Rui Wang, Mingzhe Dai, Xiaofeng Zhu, Bin Song, Kang Li

Abstract: Highlights•An interpretable dual-branch framework for 3D MRI classification.•A hierarchical attention to learn more robust feature representations.•A consistency learning module to enhance attention semantics and promote 2D and 3D interaction.