Multiple Sclerosis Lesion Inpainting Using Non-Local Partial Convolutions
This addresses the issue of biased morphometric analyses in MS brain imaging for medical researchers and clinicians, representing an incremental improvement over existing inpainting techniques.
The paper tackled the problem of inconsistent inpainting and artifacts in multiple sclerosis lesion repair by proposing non-local partial convolutions, which capture long-range dependencies to fill lesions with more similar features, resulting in more realistic inpainted regions and quantitative superiority over state-of-the-art methods.
Multiple sclerosis (MS) is an inflammatory demyelinating disease of the central nervous system (CNS) that results in focal injury to the grey and white matter. The presence of white matter lesions biases morphometric analyses such as registration, individual longitudinal measurements and tissue segmentation for brain volume measurements. Lesion-inpainting with intensities derived from surrounding healthy tissue represents one approach to alleviate such problems. However, existing methods inpaint lesions based on texture information derived from local surrounding tissue, often leading to inconsistent inpainting and the generation of artifacts such as intensity discrepancy and blurriness. Based on these observations, we propose non-local partial convolutions (NLPC) that integrates a Unet-like network with the non-local module. The non-local module is exploited to capture long range dependencies between the lesion area and remaining normal-appearing brain regions. Then, the lesion area is filled by referring to normal-appearing regions with more similar features. This method generates inpainted regions that appear more realistic and natural. Our quantitative experimental results also demonstrate superiority of this technique of existing state-of-the-art inpainting methods.