DGDOT-Net: A Deep Generative Model With Attention Fusion for Enhanced High-Density Diffuse Optical Tomography

Functional Near-Infrared Spectroscopy (fNIRS) non-invasively evaluates the optical properties of target tissues to monitor functional changes. High-density Diffuse Optical Tomography (HD-DOT) based on this technology enables highresolution 3D reconstruction. However, the strong scattering of photons by brain tissue limits the ability of detected signals to accurately reflect changes in brain function, reducing both the accuracy and 3D resolution of fNIRS-based reconstructions. This paper introduces a deep generative model, DGDOT-Net, which incorporates an attention fusion mechanism to enhance the imaging resolution and robustness. The model first decouples key features in the inverse mapping process between observed signals and reconstructed results, leveraging the conditional variational autoencoder (CVAE) architecture to model the probability distribution in latent space and regulate the reconstruction outcome. Additionally, an depth-aware attention mechanism embedded within the encoder and decoder extracts effective features from the progressive encoding process, improving learning efficiency. This study first demonstrates the superior reconstruction performance of the model through a series of numerical simulation experiments and evaluates its robustness under low signal-to-noise ratios and varying medium conditions. Specifically, the average values of SSIM, PSNR, MAE, CNR, R, and Jaccard Index achieved by DGDOT-Net on simulated data are 0.83, 21.03 dB, 2.75×10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−3</sup>, 7.10, 0.45, and 0.73, respectively. Subsequently, physical phantom data collected using a locally developed prototype system are tested, yielding average metric values of 0.87, 18.65 dB, 15.32×10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">−3</sup>, 9.61, 0.79, and 0.92, respectively. Furthermore, DGDOT-Net demonstrates the ability to reconstruct optical properties at a depth of 1.5 cm with a spatial resolution of 1 cm. The experimental results confirm that the proposed model enhances 3D reconstruction of brain functions using fNIRS, advancing the clinical applicability of elated technologies.