DiffKAN-Inpainting: KAN-based Diffusion model for brain tumor inpainting
Tianli Tao, Ziyang Wang, Han Zhang, Theodoros N. Arvanitis, Le Zhang
TL;DR
This work tackles the challenge of brain tumor inpainting to restore healthy brain tissue in MRI data for preprocessing. It introduces DiffKAN-Inpainting, a diffusion model built on a U-KAN backbone, augmented with RePaint denoising and explicit tumor-conditioned guidance to produce anatomically plausible reconstructions. The model leverages subject-specific latent conditioning and dual guidance (image latent and tumor geometry) and is evaluated on the BraTS dataset, including ablation studies to balance performance and computing cost. Results show superior fidelity (e.g., higher PSNR and SSIM, lower MAE) and smoother tissue margins compared with state-of-the-art baselines, with clear guidance on architectural choices for compute efficiency and accuracy.
Abstract
Brain tumors delay the standard preprocessing workflow for further examination. Brain inpainting offers a viable, although difficult, solution for tumor tissue processing, which is necessary to improve the precision of the diagnosis and treatment. Most conventional U-Net-based generative models, however, often face challenges in capturing the complex, nonlinear latent representations inherent in brain imaging. In order to accomplish high-quality healthy brain tissue reconstruction, this work proposes DiffKAN-Inpainting, an innovative method that blends diffusion models with the Kolmogorov-Arnold Networks architecture. During the denoising process, we introduce the RePaint method and tumor information to generate images with a higher fidelity and smoother margin. Both qualitative and quantitative results demonstrate that as compared to the state-of-the-art methods, our proposed DiffKAN-Inpainting inpaints more detailed and realistic reconstructions on the BraTS dataset. The knowledge gained from ablation study provide insights for future research to balance performance with computing cost.