3D k-space reflectance fluorescence tomography via deep learning.

We report on the potential to perform image reconstruction in 3D k-space reflectance fluorescence tomography (FT) using deep learning (DL). Herein, we adopt a modified AUTOMAP architecture and develop a training methodology that leverages an open-source Monte-Carlo-based simulator to generate a large dataset. Using an enhanced EMNIST (EEMNIST) dataset as an embedded contrast function allows us to train the network efficiently. The optical strategy utilizes k-space illumination in a reflectance configuration to probe tissue in the mesoscopic regime with high sensitivity and resolution. The proposed DL model training and validation is performed with both in silico data and a phantom experiment. Overall, our results indicate that the approach can correctly reconstruct both single and multiple fluorescent embedding(s) in a 3D volume. Furthermore, the presented technique is shown to outperform the traditional approaches [least-squares (LSQ) and total-variation minimization (TVAL)], especially at higher depths. We, therefore, expect the proposed computational technique to have future implications in preclinical studies.

Fast fit-free analysis of fluorescence lifetime imaging via deep learning.

Fluorescence lifetime imaging (FLI) provides unique quantitative information in biomedical and molecular biology studies but relies on complex data-fitting techniques to derive the quantities of interest. Herein, we propose a fit-free approach in FLI image formation that is based on deep learning (DL) to quantify fluorescence decays simultaneously over a whole image and at fast speeds. We report on a deep neural network (DNN) architecture, named fluorescence lifetime imaging network (FLI-Net) that is designed and trained for different classes of experiments, including visible FLI and near-infrared (NIR) FLI microscopy (FLIM) and NIR gated macroscopy FLI (MFLI). FLI-Net outputs quantitatively the spatially resolved lifetime-based parameters that are typically employed in the field. We validate the utility of the FLI-Net framework by performing quantitative microscopic and preclinical lifetime-based studies across the visible and NIR spectra, as well as across the 2 main data acquisition technologies. These results demonstrate that FLI-Net is well suited to accurately quantify complex fluorescence lifetimes in cells and, in real time, in intact animals without any parameter settings. Hence, FLI-Net paves the way to reproducible and quantitative lifetime studies at unprecedented speeds, for improved dissemination and impact of FLI in many important biomedical applications ranging from fundamental discoveries in molecular and cellular biology to clinical translation.

Deep Learning in Biomedical Optics.

This article reviews deep learning applications in biomedical optics with a particular emphasis on image formation. The review is organized by imaging domains within biomedical optics and includes microscopy, fluorescence lifetime imaging, in vivo microscopy, widefield endoscopy, optical coherence tomography, photoacoustic imaging, diffuse tomography, and functional optical brain imaging. For each of these domains, we summarize how deep learning has been applied and highlight methods by which deep learning can enable new capabilities for optics in medicine. Challenges and opportunities to improve translation and adoption of deep learning in biomedical optics are also summarized. Lasers Surg. Med. © 2021 Wiley Periodicals LLC.

Macroscopic fluorescence lifetime topography enhanced via spatial frequency domain imaging.

We report on a macroscopic fluorescence lifetime imaging (MFLI) topography computational framework based around machine learning with the main goal of retrieving the depth of fluorescent inclusions deeply seated in bio-tissues. This approach leverages the depth-resolved information inherent to time-resolved fluorescence data sets coupled with the retrieval of in situ optical properties as obtained via spatial frequency domain imaging (SFDI). Specifically, a Siamese network architecture is proposed with optical properties (OPs) and time-resolved fluorescence decays as input followed by simultaneous retrieval of lifetime maps and depth profiles. We validate our approach using comprehensive in silico data sets as well as with a phantom experiment. Overall, our results demonstrate that our approach can retrieve the depth of fluorescence inclusions, especially when coupled with optical properties estimation, with high accuracy. We expect the presented computational approach to find great utility in applications such as optical-guided surgery.

Quantification of Trastuzumab-HER2 Engagement In Vitro and In Vivo.

Human EGF Receptor 2 (HER2) is an important oncogene driving aggressive metastatic growth in up to 20% of breast cancer tumors. At the same time, it presents a target for passive immunotherapy such as trastuzumab (TZM). Although TZM has been widely used clinically since 1998, not all eligible patients benefit from this therapy due to primary and acquired drug resistance as well as potentially lack of drug exposure. Hence, it is critical to directly quantify TZM-HER2 binding dynamics, also known as cellular target engagement, in undisturbed tumor environments in live, intact tumor xenograft models. Herein, we report the direct measurement of TZM-HER2 binding in HER2-positive human breast cancer cells and tumor xenografts using fluorescence lifetime Forster Resonance Energy Transfer (FLI-FRET) via near-infrared (NIR) microscopy (FLIM-FRET) as well as macroscopy (MFLI-FRET) approaches. By sensing the reduction of fluorescence lifetime of donor-labeled TZM in the presence of acceptor-labeled TZM, we successfully quantified the fraction of HER2-bound and internalized TZM immunoconjugate both in cell culture and tumor xenografts in live animals. Ex vivo immunohistological analysis of tumors confirmed the binding and internalization of TZM-HER2 complex in breast cancer cells. Thus, FLI-FRET imaging presents a powerful analytical tool to monitor and quantify cellular target engagement and subsequent intracellular drug delivery in live HER2-positive tumor xenografts.

Novel small RNA (sRNA) landscape of the starvation-stress response transcriptome of Salmonella enterica serovar typhimurium.

Small RNAs (sRNAs) are short (∼50-200 nucleotides) noncoding RNAs that regulate cellular activities across bacteria. Salmonella enterica starved of a carbon-energy (C) source experience a host of genetic and physiological changes broadly referred to as the starvation-stress response (SSR). In an attempt to identify novel sRNAs contributing to SSR control, we grew log-phase, 5-h C-starved and 24-h C-starved cultures of the virulent Salmonella enterica subspecies enterica serovar Typhimurium strain SL1344 and comprehensively sequenced their small RNA transcriptomes. Strikingly, after employing a novel strategy for sRNA discovery based on identifying dynamic transcripts arising from "gene-empty" regions, we identify 58 wholly undescribed Salmonella sRNA genes potentially regulating SSR averaging an ∼1,000-fold change in expression between log-phase and C-starved cells. Importantly, the expressions of individual sRNA loci were confirmed by both comprehensive transcriptome analyses and northern blotting of select candidates. Of note, we find 43 candidate sRNAs share significant sequence identity to characterized sRNAs in other bacteria, and ∼70% of our sRNAs likely assume characteristic sRNA structural conformations. In addition, we find 53 of our 58 candidate sRNAs either overlap neighboring mRNA loci or share significant sequence complementarity to mRNAs transcribed elsewhere in the SL1344 genome strongly suggesting they regulate the expression of transcripts via antisense base-pairing. Finally, in addition to this work resulting in the identification of 58 entirely novel Salmonella enterica genes likely participating in the SSR, we also find evidence suggesting that sRNAs are significantly more prevalent than currently appreciated and that Salmonella sRNAs may actually number in the thousands.

In vitro and in vivo optimization of infrared laser treatment for injured peripheral nerves.

BACKGROUND AND OBJECTIVE: Repair of peripheral nerve injuries remains a major challenge in restorative medicine. Effective therapies that can be used in conjunction with surgical nerve repair to improve nerve regeneration and functional recovery are being actively investigated. It has been demonstrated by a number of peer reviewed publications that photobiomodulation (PBM) supports nerve regeneration, reinnervation of the denervated muscle, and functional recovery after peripheral nerve injury. However, a key issue in the use of PBM as a treatment for peripheral nerve injury is the lack of parameter optimization for any given wavelength. The objective of this study was to demonstrate that for a selected wavelength effective in vitro dosing parameters could be translated to effective in vivo parameters. MATERIALS AND METHODS: Comparison of infra-red (810 and 980 nm wavelengths) laser treatment parameters for injured peripheral nerves was done beginning with a series of in vitro experiments using primary human fibroblasts and primary rat cortical neurons. The primary rat cortical neurons were used for further optimization of energy density for 980 nm wavelength light using measurement of total neurite length as the bioassay. For these experiments, the parameters included a 1 W output power, power density of 10 mW/cm(2) , and energy densities of 0.01, 0.1, 0.5, 2, 10, 50, 200, 1,000, and 5,000 mJ/cm(2) . For translation of the in vitro data for use in vivo it was necessary to determine the transcutaneous penetration of 980 nm wavelength light to the level of the peroneal nerve. Two anesthetized, male White New Zealand rabbits were used for these experiments. The output power of the laser was set at 1.0 or 4.0 W. Power density measurements were taken at the surface of the skin, sub-dermally, and at the level of the nerve. Laser parameters used in the in vivo studies were calculated based on data from the in vitro studies and the light penetration measurements. For the in vivo experiments, a total of 22 White New Zealand rabbits (2.34-2.89 kg) were used. Translated dosing parameters were refined in a pilot study using a transection model of the peroneal nerve in rabbits. Output powers of 2 and 4 W were tested. For the final set of in vivo experiments, the same transection nerve injury model was used. An energy density of 10 mW/cm(2) at the level of the peroneal nerve was selected and the laser parameters were further refined. The dosing parameters used were: 1.5 W output power, 43 seconds exposure, 8 cm(2) area and a total energy of 65 J. RESULTS: In vitro, 980 nm wavelength light at 10 mW/cm(2) significantly improved neurite elongation at energy densities between 2 and 200 mJ/cm(2) . In vivo penetration of the infrared light measured in anesthetized rabbits showed that on average, 2.45% of the light applied to the skin reached the depth of the peroneal nerve. The in vivo pilot study data revealed that the 4 W parameters inhibited nerve regeneration while the 2 W parameters significantly improved axonal regrowth. For the final set of experiments, the irradiated group performed significantly better in the toe spread reflex test compared to the control group from week 7 post-injury, and the average length of motor endplates returned to uninjured levels. CONCLUSION: The results of this study demonstrate that treatment parameters can be determined initially using in vitro models and then translated to in vivo research and clinical practice. Furthermore, this study establishes that infrared light with optimized parameters promotes accelerated nerve regeneration and improved functional recovery in a surgically repaired peripheral nerve.

A Novel Technique for Fluorescence Lifetime Tomography.

Fluorescence lifetime has emerged as a unique imaging modality for quantitatively assessing in vivo the molecular environment of diseased tissues. Although fluorescence lifetime microscopy (in 2D) is a mature field, 3D imaging in deep tissues remains elusive and challenging owing to scattering. Herein, we report on a deep neural network (coined AUTO-FLI) that performs both 3D intensity and quantitative lifetime reconstructions in deep tissues. The proposed Deep Learning (DL)-based approach involves an in silico scheme to generate fluorescence lifetime data accurately. The developed DL model is validated both in silico and on experimental phantoms. Overall, AUTO-FLI provides accurate 3D quantitative estimates of both intensity and lifetime distributions in highly scattering media, demonstrating its unique potential for fluorescence lifetime-based molecular imaging at the mesoscopic and macroscopic scale.

Fluorescence Lifetime Imaging for Quantification of Targeted Drug Delivery in Varying Tumor Microenvironments.

Rationale: Trastuzumab (TZM) is a monoclonal antibody that targets the human epidermal growth factor receptor (HER2) and is clinically used for the treatment of HER2-positive breast tumors. However, the tumor microenvironment can limit the access of TZM to the HER2 targets across the whole tumor and thereby compromise TZM's therapeutic efficacy. An imaging methodology that can non-invasively quantify the binding of TZM-HER2, which is required for therapeutic action, and distribution within tumors with varying tumor microenvironments is much needed. Methods: We performed near-infrared (NIR) fluorescence lifetime (FLI) Forster Resonance Energy Transfer (FRET) to measure TZM-HER2 binding, using in vitro microscopy and in vivo widefield macroscopy, in HER2 overexpressing breast and ovarian cancer cells and tumor xenografts, respectively. Immunohistochemistry was used to validate in vivo imaging results. Results: NIR FLI FRET in vitro microscopy data show variations in intracellular distribution of bound TZM in HER2-positive breast AU565 and AU565 tumor-passaged XTM cell lines in comparison to SKOV-3 ovarian cancer cells. Macroscopy FLI (MFLI) FRET in vivo imaging data show that SKOV-3 tumors display reduced TZM binding compared to AU565 and XTM tumors, as validated by ex vivo immunohistochemistry. Moreover, AU565/XTM and SKOV-3 tumor xenografts display different amounts and distributions of TME components, such as collagen and vascularity. Therefore, these results suggest that SKOV-3 tumors are refractory to TZM delivery due to their disrupted vasculature and increased collagen content. Conclusion: Our study demonstrates that FLI is a powerful analytical tool to monitor the delivery of antibody drug tumor both in cell cultures and in vivo live systems. Especially, MFLI FRET is a unique imaging modality that can directly quantify target engagement with potential to elucidate the role of the TME in drug delivery efficacy in intact live tumor xenografts.

Label-free fluorescence lifetime imaging for the assessment of cell viability in living tumor fragments.

Significance: To enable non-destructive longitudinal assessment of drug agents in intact tumor tissue without the use of disruptive probes, we have designed a label-free method to quantify the health of individual tumor cells in excised tumor tissue using multiphoton fluorescence lifetime imaging microscopy (MP-FLIM). Aim: Using murine tumor fragments which preserve the native tumor microenvironment, we seek to demonstrate signals generated by the intrinsically fluorescent metabolic co-factors nicotinamide adenine dinucleotide phosphate [NAD(P)H] and flavin adenine dinucleotide (FAD) correlate with irreversible cascades leading to cell death. Approach: We use MP-FLIM of NAD(P)H and FAD on tissues and confirm viability using standard apoptosis and live/dead (Caspase 3/7 and propidium iodide, respectively) assays. Results: Through a statistical approach, reproducible shifts in FLIM data, determined through phasor analysis, are shown to correlate with loss of cell viability. With this, we demonstrate that cell death achieved through either apoptosis/necrosis or necroptosis can be discriminated. In addition, specific responses to common chemotherapeutic treatment inducing cell death were detected. Conclusions: These data demonstrate that MP-FLIM can detect and quantify cell viability without the use of potentially toxic dyes, thus enabling longitudinal multi-day studies assessing the effects of therapeutic agents on tumor fragments.

Assessing cell viability with dynamic optical coherence microscopy.

Assessing cell viability is important in many fields of research. Current optical methods to assess cell viability typically involve fluorescent dyes, which are often less reliable and have poor permeability in primary tissues. Dynamic optical coherence microscopy (dOCM) is an emerging tool that provides label-free contrast reflecting changes in cellular metabolism. In this work, we compare the live contrast obtained from dOCM to viability dyes, and for the first time to our knowledge, demonstrate that dOCM can distinguish live cells from dead cells in murine syngeneic tumors. We further demonstrate a strong correlation between dOCM live contrast and optical redox ratio by metabolic imaging in primary mouse liver tissue. The dOCM technique opens a new avenue to apply label-free imaging to assess the effects of immuno-oncology agents, targeted therapies, chemotherapy, and cell therapies using live tumor tissues.

Deep learning-based fusion of widefield diffuse optical tomography and micro-CT structural priors for accurate 3D reconstructions.

Widefield illumination and detection strategies leveraging structured light have enabled fast and robust probing of tissue properties over large surface areas and volumes. However, when applied to diffuse optical tomography (DOT) applications, they still require a time-consuming and expert-centric solving of an ill-posed inverse problem. Deep learning (DL) models have been recently proposed to facilitate this challenging step. Herein, we expand on a previously reported deep neural network (DNN) -based architecture (modified AUTOMAP - ModAM) for accurate and fast reconstructions of the absorption coefficient in 3D DOT based on a structured light illumination and detection scheme. Furthermore, we evaluate the improved performances when incorporating a micro-CT structural prior in the DNN-based workflow, named Z-AUTOMAP. This Z-AUTOMAP significantly improves the widefield imaging process's spatial resolution, especially in the transverse direction. The reported DL-based strategies are validated both in silico and in experimental phantom studies using spectral micro-CT priors. Overall, this is the first successful demonstration of micro-CT and DOT fusion using deep learning, greatly enhancing the prospect of rapid data-integration strategies, often demanded in challenging pre-clinical scenarios.

in vivo quantitative FRET small animal imaging: intensity versus lifetime-based FRET.

Förster Resonance Energy Transfer (FRET) microscopy is used in numerous biophysical and biomedical applications to monitor inter- and intramolecular interactions and conformational changes in the 2-10 nm range. FRET is currently being extended to in vivo optical imaging, its main application being in quantifying drug-target engagement or drug release in animal models of cancer using organic dye or nanoparticle-labeled probes. Herein, we compared FRET quantification using intensity-based FRET (sensitized emission FRET analysis with the 3-cube approach using an IVIS imager) and macroscopic fluorescence lifetime (MFLI) FRET using a custom system using a time-gated ICCD, for small animal optical in vivo imaging. The analytical expressions and experimental protocols required to quantify the product f D E of the FRET efficiency E and the fraction of donor molecules involved in FRET, f D , are described in detail for both methodologies. Dynamic in vivo FRET quantification of transferrin receptor-transferrin binding was acquired in live intact nude mice upon intravenous injection of near infrared-labeled transferrin FRET pair and benchmarked against in vitro FRET using hybridized oligonucleotides. Even though both in vivo imaging techniques provided similar dynamic trends for receptor-ligand engagement, we demonstrate that MFLI FRET has significant advantages. Whereas the sensitized emission FRET approach using the IVIS imager required 9 measurements (6 of which are used for calibration) acquired from three mice, MFLI FRET needed only one measurement collected from a single mouse, although a control mouse might be needed in a more general situation. Based on our study, MFLI therefore represents the method of choice for longitudinal preclinical FRET studies such as that of targeted drug delivery in intact, live mice.

In vivo quantitative FRET small animal imaging: Intensity versus lifetime-based FRET.

Förster resonance energy transfer (FRET) microscopy is used in numerous biophysical and biomedical applications to monitor inter- and intramolecular interactions and conformational changes in the 2-10 nm range. FRET is currently being extended to in vivo optical imaging, its main application being in quantifying drug-target engagement or drug release in animal models of cancer using organic dye or nanoparticle-labeled probes. Herein, we compared FRET quantification using intensity-based FRET (sensitized emission FRET analysis with the three-cube approach using an IVIS imager) and macroscopic fluorescence lifetime (MFLI) FRET using a custom system using a time-gated-intensified charge-coupled device, for small animal optical in vivo imaging. The analytical expressions and experimental protocols required to quantify the product fDE of the FRET efficiency E and the fraction of donor molecules involved in FRET, fD, are described in detail for both methodologies. Dynamic in vivo FRET quantification of transferrin receptor-transferrin binding was acquired in live intact nude mice upon intravenous injection of a near-infrared-labeled transferrin FRET pair and benchmarked against in vitro FRET using hybridized oligonucleotides. Even though both in vivo imaging techniques provided similar dynamic trends for receptor-ligand engagement, we demonstrate that MFLI-FRET has significant advantages. Whereas the sensitized emission FRET approach using the IVIS imager required nine measurements (six of which are used for calibration) acquired from three mice, MFLI-FRET needed only one measurement collected from a single mouse, although a control mouse might be needed in a more general situation. Based on our study, MFLI therefore represents the method of choice for longitudinal preclinical FRET studies such as that of targeted drug delivery in intact, live mice.

Roadmap on Deep Learning for Microscopy.

Through digital imaging, microscopy has evolved from primarily being a means for visual observation of life at the micro- and nano-scale, to a quantitative tool with ever-increasing resolution and throughput. Artificial intelligence, deep neural networks, and machine learning are all niche terms describing computational methods that have gained a pivotal role in microscopy-based research over the past decade. This Roadmap is written collectively by prominent researchers and encompasses selected aspects of how machine learning is applied to microscopy image data, with the aim of gaining scientific knowledge by improved image quality, automated detection, segmentation, classification and tracking of objects, and efficient merging of information from multiple imaging modalities. We aim to give the reader an overview of the key developments and an understanding of possibilities and limitations of machine learning for microscopy. It will be of interest to a wide cross-disciplinary audience in the physical sciences and life sciences.

Computational macroscopic lifetime imaging and concentration unmixing of autofluorescence.

Single-pixel computational imaging can leverage highly sensitive detectors that concurrently acquire data across spectral and temporal domains. For molecular imaging, such methodology enables to collect rich intensity and lifetime multiplexed fluorescence datasets. Herein we report on the application of a single-pixel structured light-based platform for macroscopic imaging of tissue autofluorescence. The super-continuum visible excitation and hyperspectral single-pixel detection allow for parallel characterization of autofluorescence intensity and lifetime. Furthermore, we exploit a deep learning based data processing pipeline, to perform autofluorescence unmixing while yielding the autofluorophores' concentrations. The full scheme (setup and processing) is validated in silico and in vitro with clinically relevant autofluorophores flavin adenine dinucleotide, riboflavin, and protoporphyrin. The presented results demonstrate the potential of the methodology for macroscopically quantifying the intensity and lifetime of autofluorophores, with higher specificity for cases of mixed emissions, which are ubiquitous in autofluorescence and multiplexed in vivo imaging.

Design and characterization of a time-domain optical tomography platform for mesoscopic lifetime imaging.

We report on the system design and instrumental characteristics of a novel time-domain mesoscopic fluorescence molecular tomography (TD-MFMT) system for multiplexed molecular imaging in turbid media. The system is equipped with a supercontinuum pulsed laser for broad spectral excitation, based on a high-density descanned raster scanning intensity-based acquisition for 2D and 3D imaging and augmented with a high-dynamical range linear time-resolved single-photon avalanche diode (SPAD) array for lifetime quantification. We report on the system's spatio-temporal and spectral characteristics and its sensitivity and specificity in controlled experimental settings. Also, a phantom study is undertaken to test the performance of the system to image deeply-seated fluorescence inclusions in tissue-like media. In addition, ex vivo tumor xenograft imaging is performed to validate the system's applicability to the biological sample. The characterization results manifest the capability to sense small fluorescence concentrations (on the order of nanomolar) while quantifying fluorescence lifetimes and lifetime-based parameters at high resolution. The phantom results demonstrate the system's potential to perform 3D multiplexed imaging thanks to spectral and lifetime contrast in the mesoscopic range (at millimeters depth). The ex vivo imaging exhibits the prospect of TD-MFMT to resolve intra-tumoral heterogeneity in a depth-dependent manner.

Macroscopic Fluorescence Lifetime Imaging for Monitoring of Drug-Target Engagement.

Precision medicine promises to improve therapeutic efficacy while reducing adverse effects, especially in oncology. However, despite great progresses in recent years, precision medicine for cancer treatment is not always part of routine care. Indeed, the ability to specifically tailor therapies to distinct patient profiles requires still significant improvements in targeted therapy development as well as decreases in drug treatment failures. In this regard, preclinical animal research is fundamental to advance our understanding of tumor biology, and diagnostic and therapeutic response. Most importantly, the ability to measure drug-target engagement accurately in live and intact animals is critical in guiding the development and optimization of targeted therapy. However, a major limitation of preclinical molecular imaging modalities is their lack of capability to directly and quantitatively discriminate between drug accumulation and drug-target engagement at the pathological site. Recently, we have developed Macroscopic Fluorescence Lifetime Imaging (MFLI) as a unique feature of optical imaging to quantitate in vivo drug-target engagement. MFLI quantitatively reports on nanoscale interactions via lifetime-sensing of Förster Resonance Energy Transfer (FRET) in live, intact animals. Hence, MFLI FRET acts as a direct reporter of receptor dimerization and target engagement via the measurement of the fraction of labeled-donor entity undergoing binding to its respective receptor. MFLI is expected to greatly impact preclinical imaging and also adjacent fields such as image-guided surgery and drug development.

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). APPROACH: First, we provide a layman introduction to DL. Then, the review summarizes current DL work in some of the most active areas of this field, including optical properties retrieval, fluorescence lifetime imaging, and diffuse optical tomography. RESULTS: The advantages of using DL for DOI versus conventional inverse solvers cited in the literature reviewed herein are numerous. These include, among others, a decrease in analysis time (often by many orders of magnitude), increased quantitative reconstruction quality, robustness to noise, and the unique capability to learn complex end-to-end relationships. CONCLUSIONS: The heavily validated capability of DL's use across a wide range of complex inverse solving methodologies has enormous potential to bring novel DOI modalities, otherwise deemed impractical for clinical translation, to the patient's bedside.

Monte Carlo-based data generation for efficient deep learning reconstruction of macroscopic diffuse optical tomography and topography applications.

SIGNIFICANCE: Deep learning (DL) models are being increasingly developed to map sensor data to the image domain directly. However, DL methodologies are data-driven and require large and diverse data sets to provide robust and accurate image formation performances. For research modalities such as 2D/3D diffuse optical imaging, the lack of large publicly available data sets and the wide variety of instrumentation designs, data types, and applications leads to unique challenges in obtaining well-controlled data sets for training and validation. Meanwhile, great efforts over the last four decades have focused on developing accurate and computationally efficient light propagation models that are flexible enough to simulate a wide variety of experimental conditions. AIM: Recent developments in Monte Carlo (MC)-based modeling offer the unique advantage of simulating accurately light propagation spatially, temporally, and over an extensive range of optical parameters, including minimally to highly scattering tissue within a computationally efficient platform. Herein, we demonstrate how such MC platforms, namely "Monte Carlo eXtreme" and "Mesh-based Monte Carlo," can be leveraged to generate large and representative data sets for training the DL model efficiently. APPROACH: We propose data generator pipeline strategies using these platforms and demonstrate their potential in fluorescence optical topography, fluorescence optical tomography, and single-pixel diffuse optical tomography. These applications represent a large variety in instrumentation design, sample properties, and contrast function. RESULTS: DL models trained using the MC-based in silico datasets, validated further with experimental data not used during training, show accurate and promising results. CONCLUSION: Overall, these MC-based data generation pipelines are expected to support the development of DL models for rapid, robust, and user-friendly image formation in a wide variety of applications.