Lightweight Medical Image Restoration via Integrating Reliable Lesion-Semantic Driven Prior
Zheng, Pengcheng Chen, Kecheng Huang, Jiaxin Chen, Bohao Liu, Ju Ren, Yazhou Pu, Xiaorong
Zheng, Pengcheng
Chen, Kecheng
Huang, Jiaxin
Chen, Bohao
Liu, Ju
Ren, Yazhou
Pu, Xiaorong
Author
Supervisor
Department
Machine Learning
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Medical image restoration tasks aim to recover high-quality images from degraded observations, exhibiting emergent desires in many clinical scenarios, such as low-dose CT image denoising, MRI super-resolution, and MRI artifact removal. Despite the success achieved by existing deep learning-based restoration methods with sophisticated modules, they struggle with rendering computationally-efficient reconstruction results. Moreover, they usually ignore the reliability of the restoration results, which is much more urgent in medical systems. To alleviate these issues, we present LRformer, a Lightweight Transformer-based method via Reliability-guided learning in the frequency domain. Specifically, inspired by the uncertainty quantification in Bayesian neural networks (BNNs), we develop a Reliable Lesion-Semantic Prior Producer (RLPP). RLPP leverages Monte Carlo (MC) estimators with stochastic sampling operations to generate sufficiently-reliable priors by performing multiple inferences on the foundational medical image segmentation model, MedSAM. Additionally, instead of directly incorporating the priors in the spatial domain, we decompose the cross-attention (CA) mechanism into real symmetric and imaginary anti-symmetric parts via fast Fourier transform (FFT), resulting in the design of the Guided Frequency Cross-Attention (GFCA) solver. By leveraging the conjugated symmetric property of FFT, GFCA reduces the computational complexity of naive CA by nearly half. Extensive experimental results in various tasks demonstrate the superiority of the proposed LRformer in both effectiveness and efficiency.
Citation
P. Zheng et al., “Lightweight Medical Image Restoration via Integrating Reliable Lesion-Semantic Driven Prior,” Proceedings of the 33rd ACM International Conference on Multimedia, pp. 2977–2986, Oct. 2025, doi: 10.1145/3746027.3754934
Source
MSMA '25: Proceedings of the 1st International Workshop on Multi-Sensorial Media and Applications
Conference
The 33rd ACM International Conference on Multimedia
Keywords
Medical Image Restoration, Bayesian Neural Network, Monte Carlo Dropout, Frequency Domain
Subjects
Source
The 33rd ACM International Conference on Multimedia
Publisher
Association for Computing Machinery