Deep learning in macroscopic diffuse optical imaging.

Significance: Biomedical optics system design, image formation, and image analysis have primarily been guided by classical physical modeling and signal processing methodologies. Recently, however, deep learning (DL) has become a major paradigm in computational modeling and has demonstrated utility in numerous scientific domains and various forms of data analysis.

Aim: We aim to comprehensively review the use of DL applied to macroscopic diffuse optical imaging (DOI).

Accelerating vasculature imaging in tumor using mesoscopic fluorescence molecular tomography via a hybrid reconstruction strategy.

Mesoscopic fluorescent molecular tomography (MFMT) enables to image fluorescent molecular probes beyond the typical depth limits of microscopic imaging and with enhanced resolution compared to macroscopic imaging. However, MFMT is a scattering-based inverse problem that is an ill-posed inverse problem and hence, requires relative complex iterative solvers coupled with regularization strategies. Inspired by the potential of deep learning in performing image formation tasks from raw measurements, this work proposes a hybrid approach to solve the MFMT inverse problem.

Non-Destructive Tumor Aggregate Morphology and Viability Quantification at Cellular Resolution, During Development and in Response to Drug.

Three-dimensional (3D) tissue-engineered in vitro models, particularly multicellular spheroids and organoids, have become important tools to explore disease progression and guide the development of novel therapeutic strategies. These avascular constructs are particularly powerful in oncological research due to their ability to mimic several key aspects of in vivo tumors, such as 3D structure and pathophysiologic gradients. Advancement of spheroid models requires characterization of critical features (i.

System configuration optimization for mesoscopic fluorescence molecular tomography.

Tissue engineering applications demand 3D, non-invasive, and longitudinal assessment of bioprinted constructs. Current emphasis is on developing tissue constructs mimicking conditions; however, these are increasingly challenging to image as they are typically a few millimeters thick and turbid, limiting the usefulness of classical fluorescence microscopic techniques. For such applications, we developed a Mesoscopic Fluorescence Molecular Tomography methodology that collects high information content data to enable high-resolution tomographic reconstruction of fluorescence biomarkers at millimeters depths.

Laser-based 3D bioprinting for spatial and size control of tumor spheroids and embryoid bodies.

3D multicellular aggregates, and more advanced organotypic systems, have become central tools in recent years to study a wide variety of complex biological processes. Most notably, these model systems have become mainstream within oncology (multicellular tumor spheroids) and regenerative medicine (embryoid bodies) research. However, the biological behavior of these in vitro tissue surrogates is extremely sensitive to their aggregate size and geometry.

Improving mesoscopic fluorescence molecular tomography via preconditioning and regularization.

Mesoscopic fluorescence molecular tomography (MFMT) is a novel imaging technique capable of obtaining 3-D distribution of molecular probes inside biological tissues at depths of a few millimeters with a resolution up to ~100 μm. However, the ill-conditioned nature of the MFMT inverse problem severely deteriorates its reconstruction performances. Furthermore, dense spatial sampling and fine discretization of the imaging volume required for high resolution reconstructions make the sensitivity matrix (Jacobian) highly correlated, which prevents even advanced algorithms from achieving optimal solutions.