Projection Inpainting Using Partial Convolution for Metal Artifact Reduction

TL;DR

This paper introduces a partial convolution-based inpainting method within a U-Net architecture to improve metal artifact reduction in CT images, outperforming traditional convolutional approaches.

Contribution

The study demonstrates that using partial convolution in U-Net significantly enhances inpainting quality for metal artifact reduction compared to conventional convolution.

Findings

Partial convolution improves inpainting of metal artifacts.

U-Net with partial convolution outperforms conventional CNNs.

Enhanced image quality in CT reconstructions with metal implants.

Abstract

In computer tomography, due to the presence of metal implants in the patient body, reconstructed images will suffer from metal artifacts. In order to reduce metal artifacts, metals are typically removed in projection images. Therefore, the metal corrupted projection areas need to be inpainted. For deep learning inpainting methods, convolutional neural networks (CNNs) are widely used, for example, the U-Net. However, such CNNs use convolutional filter responses on both valid and corrupted pixel values, resulting in unsatisfactory image quality. In this work, partial convolution is applied for projection inpainting, which only relies on valid pixels values. The U-Net with partial convolution and conventional convolution are compared for metal artifact reduction. Our experiments demonstrate that the U-Net with partial convolution is able to inpaint the metal corrupted areas better than that with conventional convolution.