ipA-MedGAN: Inpainting of Arbitrary Regions in Medical Imaging
This work addresses a common issue in medical imaging for automated analysis, enabling better post-processing like segmentation, but it appears incremental as it builds on existing generative frameworks.
The authors tackled the problem of inpainting arbitrary-shaped missing or distorted regions in medical images, such as those caused by metallic implants in MRI, and proposed ipA-MedGAN, which achieved superior performance in brain MR inpainting compared to other methods.
Local deformations in medical modalities are common phenomena due to a multitude of factors such as metallic implants or limited field of views in magnetic resonance imaging (MRI). Completion of the missing or distorted regions is of special interest for automatic image analysis frameworks to enhance post-processing tasks such as segmentation or classification. In this work, we propose a new generative framework for medical image inpainting, titled ipA-MedGAN. It bypasses the limitations of previous frameworks by enabling inpainting of arbitrary shaped regions without a prior localization of the regions of interest. Thorough qualitative and quantitative comparisons with other inpainting and translational approaches have illustrated the superior performance of the proposed framework for the task of brain MR inpainting.