Low‐Dose Computed Tomography Image Denoising Vision Transformer Model Optimization Using Space State Method
Open Access
- 1 October 2025
- journal article
- Published by Wiley in International Journal of Imaging Systems and Technology
- Vol. 35 (6)
Abstract
Low‐dose computed tomography (LDCT) is widely used to promote reduction of patient radiation exposure, but the associated increase in image noise poses challenges for diagnostic accuracy. In this study, we propose a Vision Transformer (ViT)‐based denoising framework enhanced with a State Space Optimizing Block (SSOB) to improve both image quality and computational efficiency. The SSOB upgrades the multihead self‐attention mechanism by reducing spatial redundancy and optimizing contextual feature fusion, thereby strengthening the transformer's ability to capture long‐range dependencies and preserve fine anatomical structures under severe noise. Extensive evaluations on randomized and categorized datasets demonstrate that the proposed model consistently outperforms existing state‐of‐the‐art denoising approaches. It achieved the highest average SSIM (up to 6.10% improvement), PSNR values (36.51 ± 0.37 dB on randomized and 36.30 ± 0.36 dB on categorized datasets), and the lowest RMSE, surpassing recent CNN‐transformer‐based denoising hybrid models by approximately 12%. Intensity profile analysis further confirmed its effectiveness, showing sharper edge transitions and more accurate gray‐level distributions across anatomical boundaries, closely aligning with ground truth and retaining subtle diagnostic features often lost in competing models. In addition to improved reconstruction quality, the SSOB‐empowered ViT achieved notable computational gains. It delivered the fastest inference (0.42 s per image), highest throughput (2.38 images/s), lowest GPU memory usage (750 MB), and smallest model size (7.6 MB), alongside one of the shortest training times (6.5 h). Compared to legacy architectures, which required up to 16 h of training and substantially more resources, the proposed model offers both accuracy and deployability. Collectively, these findings establish the SSOB as a key component for efficient transformer‐based LDCT denoising, addressing memory and convergence challenges while preserving global contextual advantages.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada (RGPIN‐2020‐04441)
This publication has 41 references indexed in Scilit:
- SEANet: Rethinking Skip-Connections Design in Encoder-Decoder Networks via Synergistic Spatial-Spectral Fusion for LDCT Denoising2024
- Efficient Long-Range Context Modeling for Motion Forecasting with State Space Models2024
- Denoising and segmentation in medical image analysis: A comprehensive review on machine learning and deep learning approachesMultimedia Tools and Applications, 2024
- Pure Vision Transformer (CT-ViT) with Noise2Neighbors Interpolation for Low-Dose CT Image DenoisingJournal of Imaging Informatics in Medicine, 2024
- Low-Dose CT Denoising Algorithm Based on Image Cartoon Texture DecompositionCircuits, Systems, and Signal Processing, 2024
- A multi-attention Uformer for low-dose CT image denoisingSignal, Image and Video Processing, 2023
- Traditional and deep-learning-based denoising methods for medical imagesMultimedia Tools and Applications, 2023
- TED-Net: Convolution-Free T2T Vision Transformer-Based Encoder-Decoder Dilation Network for Low-Dose CT Denoising2021
- A guide to state–space modeling of ecological time seriesEcological Monographs, 2021
- PSNR vs SSIM: imperceptibility quality assessment for image steganographyMultimedia Tools and Applications, 2020