A Modular Deep Learning-based Approach for Diffuse Optical Tomography Reconstruction
Abstract
Medical imaging is nowadays a pillar in diagnostics and therapeutic follow-up. Current research tries to integrate established - but ionizing - tomographic techniques with technologies offering reduced radiation exposure. Diffuse Optical Tomography (DOT) uses non-ionizing light in the Near-Infrared (NIR) window to reconstruct optical coefficients in living beings, providing functional indications about the composition of the investigated organ/tissue. Due to predominant light scattering at NIR wavelengths, DOT reconstruction is, however, a severely ill-conditioned inverse problem. Conventional reconstruction approaches show severe weaknesses when dealing also with mildly complex cases and/or are computationally very intensive. In this work we explore deep learning techniques for DOT inversion. Namely, we propose a fully data-driven approach based on a modularity concept: first data and originating signal are separately processed via autoencoders, then the corresponding low-dimensional latent spaces are connected via a bridging network which acts at the same time as a learned regularizer.
Cite
@article{arxiv.2402.09277,
title = {A Modular Deep Learning-based Approach for Diffuse Optical Tomography Reconstruction},
author = {Alessandro Benfenati and Paola Causin and Martina Quinteri},
journal= {arXiv preprint arXiv:2402.09277},
year = {2024}
}