Shape-Aware Masking for Inpainting in Medical Imaging

TL;DR

This paper introduces a shape-aware masking technique for medical image inpainting that leverages organ topology to improve model generalization and reconstruction quality.

Contribution

It proposes an unsupervised guided masking approach using superpixel segmentation to generate shape-dependent masks tailored to anatomical structures.

Findings

Shape-aware masks outperform standard square masks in inpainting tasks.

The method improves generalization across different anatomical classes.

Experimental results show enhanced reconstruction quality in abdominal MR images.

Abstract

Inpainting has recently been proposed as a successful deep learning technique for unsupervised medical image model discovery. The masks used for inpainting are generally independent of the dataset and are not tailored to perform on different given classes of anatomy. In this work, we introduce a method for generating shape-aware masks for inpainting, which aims at learning the statistical shape prior. We hypothesize that although the variation of masks improves the generalizability of inpainting models, the shape of the masks should follow the topology of the organs of interest. Hence, we propose an unsupervised guided masking approach based on an off-the-shelf inpainting model and a superpixel over-segmentation algorithm to generate a wide range of shape-dependent masks. Experimental results on abdominal MR image reconstruction show the superiority of our proposed masking method over standard methods using square-shaped or dataset of irregular shape masks.