WARPNet: Scale-Wise Autoregressive Cross-Modal Synthesis for Accurate and Detail-Preserving MRI-to-PET Generation

Le résumé fourni par la source

Due to the inherent limitation of MRI in directly capturing early metabolic abnormalities associated with neurological disorders, and considering the high cost and radiation risks associated with PET scans, cross-modal MRI-to-PET image synthesis has emerged as a critical pathway for early and precise diagnosis. However, current methods generally suffer from structural distortion, blurred details, and computational inefficiencies, significantly restricting their clinical applicability. To address these limitations, this paper proposes an innovative multi-scale autoregressive-driven framework for MRI-to-PET cross-modal image generation. By explicitly modeling scalewise transformations between MRI and PET via a multi-scale autoregressive mechanism, and incorporating wavelet transform with a linear multi-step connection strategy, our framework effectively enhances structural accuracy and texture detail expression, especially in lesion regions. Experimental results on the ADNI Alzheimer's Disease dataset and a private epilepsy dataset demonstrate that the proposed method consistently outperforms state-of-the-art approaches, generating high-quality PET images efficiently and robustly. Furthermore, it substantially reduces diagnostic costs and radiation exposure, showcasing promising prospects for clinical adoption. Our source code is available at https://github.com/Guanyu-Zhou/WARPNet.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.