GS-DOT: Gaussian splatting-based image reconstruction for diffuse optical tomography

TL;DR

GS-DOT introduces a Gaussian splatting-based framework for diffuse optical tomography, achieving accurate, robust, and memory-efficient image reconstruction of tissue absorption properties.

Contribution

It is the first adaptation of Gaussian splatting algorithms to photon diffusion in optical tomography, enabling improved accuracy and efficiency.

Findings

High accuracy in localization and quantification of absorption maps.

Robustness to noisy signals demonstrated.

Significant reduction in memory demand.

Abstract

This work presents GS-DOT, a novel image reconstruction framework based on Gaussian Splatting (GS) for diffuse optical tomography (DOT). Inspired by GS for rendering applications, absorption coefficients are represented as a sparse sum of anisotropic Gaussian primitives optimized to fit measured time-resolved point-spread functions through analytic gradients and Adam optimization. This is the first adaptation of GS algorithms in the photon diffusion regime, where the ray transport function is replaced by the diffusion functions to enable accurate modeling of light transport in highly scattering media. Validation on synthetic tissue models demonstrate high accuracy in localization and quantification of reconstructed absorption maps for both clean and noisy signals. GS-DOT has demonstrated high robustness to noise and showed a huge reduction in memory demand.