SparseMorph: A weakly-supervised lightweight sparse transformer for mono- and multi-modal deformable image registration

• Published in: Computers in biology and medicine 2024-11, Vol.182, p.109205, Article 109205
• Main Authors: Bai, Xinhao, Wang, Hongpeng, Qin, Yanding, Han, Jianda, Yu, Ningbo
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Brain - diagnostic imaging; Complexity; Computational efficiency; Computed tomography; Datasets; Deep learning; Deformable image registration; Deformation effects; Efficiency; Formability; Humans; Image enhancement; Image Interpretation, Computer-Assisted - methods; Image Processing, Computer-Assisted - methods; Image registration; Lightweight; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Multi-branch multi-layer perception module; Multilayers; Performance enhancement; Probability distribution; Queries; Registration; Sparse multi-head self-attention mechanism; Weakly-supervised network; Weight reduction
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109205

Deformable image registration (DIR) is crucial for improving the precision of clinical diagnosis. Recent Transformer-based DIR methods have shown promising performance by capturing long-range dependencies. Nevertheless, these methods still grapple with high computational complexity. This work aims to enhance the performance of DIR in both computational efficiency and registration accuracy. We proposed a weakly-supervised lightweight Transformer model, named SparseMorph. To reduce computational complexity without compromising the representative feature capture ability, we designed a sparse multi-head self-attention (SMHA) mechanism. To accumulate representative features while preserving high computational efficiency, we constructed a multi-branch multi-layer perception (MMLP) module. Additionally, we developed an anatomically-constrained weakly-supervised strategy to guide the alignment of regions-of-interest in mono- and multi-modal images. We assessed SparseMorph in terms of registration accuracy and computational complexity. Within the mono-modal brain datasets IXI and OASIS, our SparseMorph outperforms the state-of-the-art method TransMatch with improvements of 3.2 % and 2.9 % in DSC scores for MRI-to-CT registration tasks, respectively. Moreover, in the multi-modal cardiac dataset MMWHS, our SparseMorph shows DSC score improvements of 9.7 % and 11.4 % compared to TransMatch in MRI-to-CT and CT-to-MRI registration tasks, respectively. Notably, SparseMorph attains these performance advantages while utilizing 33.33 % of the parameters of TransMatch. The proposed weakly-supervised deformable image registration model, SparseMorph, demonstrates efficiency in both mono- and multi-modal registration tasks, exhibiting superior performance compared to state-of-the-art algorithms, and establishing an effective DIR method for clinical applications. •We propose SparseMorph, a weakly-supervised lightweight Transformer for mono- and multi-modal deformable image registration.•SparseMorph with advantages in large field-of-view extraction ability and low computational complexity.•We constructed a sparse multi-head self-attention to reduce computational complexity without sacrificing efficiency.•We designed a multi-branch MLP to accumulate representative features while preserving high computational efficiency.•We developed an anatomically-constrained weakly-supervised strategy to guide the alignment between image pairs.