Diffuse optical tomography using deep learning is an emerging technology that has found impressive medical diagnostic applications. However, creating an optical imaging system that uses visible and near-infrared (NIR) light is not straightforward due to photon absorption and multi-scattering by tissues. The high distortion levels caused due to these effects make the image reconstruction incredibly challenging. To overcome these challenges, various techniques have been proposed in the past, with varying success. One of the most successful techniques is the application of deep learning algorithms in diffuse optical tomography. This article discusses the current state-of-the-art diffuse optical tomography systems and comprehensively reviews the deep learning algorithms used in image reconstruction. This article attempts to provide researchers with the necessary background and tools to implement deep learning methods to solve diffuse optical tomography.

Imaging through highly scattering media is a challenging problem with numerous applications in biomedical and remote‐sensing fields. Existing methods that use analytical or deep learning tools are limited by simplified forward models or a requirement for prior physical knowledge, resulting in blurry images or a need for large training databases. To address these limitations, we propose a hybrid scheme called Hybrid‐DOT that combines analytically derived image estimates with a deep learning network. Our analysis demonstrates that Hybrid‐DOT outperforms a state‐of‐the‐art ToF‐DOT algorithm by improving the PSNR ratio by 4.6 dB and reducing the resolution by a factor of 2.5. Furthermore, when compared to a deep learning stand‐alone model, Hybrid‐DOT achieves a 0.8 dB increase in PSNR, 1.5 times the resolution, and a significant reduction in the required dataset size (factor of 1.6–3). The proposed model remains effective at higher depths, providing similar improvements for up to 160 mean‐free paths.

Diffuse optical imaging (DOI) offers valuable insights into scattering mediums, but the quest for high-resolution imaging often requires dense sampling strategies, leading to higher imaging errors and lengthy acquisition times. This work introduces Space-Time Encoded Modulation (STEM), a novel light modulation scheme enabling low-noise, high-resolution imaging with single-pixel detectors. In STEM, a laser illuminates the sample, and the transmitted light is detected using a single pixel detector. The detected image is partitioned into a two-dimensional array of sub-images, each encoded with a unique quasi-orthogonal code. These coded sub-images represent light transmission at specific locations along the sample boundary. A single-pixel detector then measures their combined transmission. By virtue of their quasi-orthogonality, the relative strength of each sub-image can be measured, enabling image formation. In this paper, we present a comprehensive mathematical description and experimental validation of the STEM method. Compared to traditional raster scanning, STEM significantly enhances imaging quality, reducing imaging errors by up to 60% and yielding a 3.5-fold increase in reconstruction contrast.