Applications of Deep Learning for Ill-Posed Inverse Problems Within Optical Tomography

TL;DR

This paper reviews the challenges of reconstructing images in optical tomography, especially in medical imaging with undersampled data, and explores how deep learning can address these ill-posed inverse problems.

Contribution

It provides a comprehensive analysis of classical and deep learning methods for inverse problems in optical tomography, highlighting future research directions.

Findings

Deep learning improves image reconstruction in undersampled X-Ray CT.

Classical methods are limited in handling noisy, undersampled data.

Future research avenues include hybrid models and improved training strategies.

Abstract

Increasingly in medical imaging has emerged an issue surrounding the reconstruction of noisy images from raw measurement data. Where the forward problem is the generation of raw measurement data from a ground truth image, the inverse problem is the reconstruction of those images from the measurement data. In most cases with medical imaging, classical inverse Radon transforms, such as an inverse Fourier transform for MRI, work well for recovering clean images from the measured data. Unfortunately in the case of X-Ray CT, where undersampled data is very common, more than this is needed to resolve faithful and usable images. In this paper, we explore the history of classical methods for solving the inverse problem for X-Ray CT, followed by an analysis of the state of the art methods that utilize supervised deep learning. Finally, we will provide some possible avenues for research in the future.