Interpolation Method for CT Image Reconstruction using Features Inferred by Self-Supervised Learning

Joowon Lim, Jinah Park

http://doi.org/10.5626/JOK.2021.48.9.1007

Since volumetric data includes internal information, it has an advantage of performing quantitative analysis. Especially medical image data render 3D structures of internal organs, and cubic voxel is necessary for accurate visualization. However, CT image volume is acquired in low z-resolution to reduce X-ray dose exposure. Between slices, image interpolation is a necessary step for visualization as well as for 3D data analysis. In this paper, we propose a self-supervised learning algorithm as an interpolation method that uses the information from the high-resolution images to infer missing information between slices. To achieve this, downscaled slice images are given as the input of the network, and the network recovers the original slice images from the downscaled images. The result of our method outperformed the commonly practiced interpolation methods - nearest-neighbor and trilinear interpolation – in the field, with respect to estimating details. Also, we verified that the proposed algorithm performs comparably with the supervised model with the same network.