TC-KANRecon: High-Quality and Accelerated MRI Reconstruction via Adaptive KAN Mechanisms and Intelligent Feature Scaling

2024-08-11

arXiv.org

AI Summary

To address challenges in accelerated MRI reconstruction—including prolonged scan times, slow inference, and loss of anatomical detail under low sampling rates or high noise—this paper proposes TC-KANRecon, a conditional-guided diffusion model. Methodologically, it introduces (1) a novel Multi-Degree-of-Freedom U-KAN (MF-UKAN) module that integrates multi-head attention with scalar modulation factors to jointly optimize denoising performance and anatomical structure preservation; (2) a dynamic cropping strategy that adaptively adjusts diffusion sampling step intervals to improve inference efficiency; and (3) a full k-space conditional encoding mechanism to enhance fidelity in high-frequency detail reconstruction. Extensive experiments demonstrate that TC-KANRecon achieves significant PSNR and SSIM improvements over state-of-the-art methods across diverse undersampling ratios and noise levels, with markedly enhanced visual fidelity and structural integrity. The source code is publicly available.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Magnetic Resonance Imaging (MRI) has become essential in clinical diagnosis due to its high resolution and multiple contrast mechanisms. However, the relatively long acquisition time limits its broader application. To address this issue, this study presents an innovative conditional guided diffusion model, named as TC-KANRecon, which incorporates the Multi-Free U-KAN (MF-UKAN) module and a dynamic clipping strategy. TC-KANRecon model aims to accelerate the MRI reconstruction process through deep learning methods while maintaining the quality of the reconstructed images. The MF-UKAN module can effectively balance the tradeoff between image denoising and structure preservation. Specifically, it presents the multi-head attention mechanisms and scalar modulation factors, which significantly enhances the model's robustness and structure preservation capabilities in complex noise environments. Moreover, the dynamic clipping strategy in TC-KANRecon adjusts the cropping interval according to the sampling steps, thereby mitigating image detail loss typicalching the visual features of the images. Furthermore, the MC-Model incorporates full-sampling k-space information, realizing efficient fusion of conditional information, enhancing the model's ability to process complex data, and improving the realism and detail richness of reconstructed images. Experimental results demonstrate that the proposed method outperforms other MRI reconstruction methods in both qualitative and quantitative evaluations. Notably, TC-KANRecon method exhibits excellent reconstruction results when processing high-noise, low-sampling-rate MRI data. Our source code is available at https://github.com/lcbkmm/TC-KANRecon.

Problem

• MRI Image Reconstruction
• Scanning Time
• Image Clarity and Detail Preservation

Innovation

• TC-KANRecon
• MRI image reconstruction
• noise distinction