Deep convolutional neural network-based scatterer density and resolution estimators in optical coherence tomography

Optical-coherence-tomography-based deep-learning scatterer-density estimator using physically accurate noise model

We demonstrate a deep-learning-based scatterer density estimator (SDE) that processes local speckle patterns of optical coherence tomography (OCT) images and estimates the scatterer density behind each speckle pattern. The SDE is trained using large quantities of numerically simulated OCT images and their associated scatterer densities. The numerical simulation uses a noise model that incorporates the spatial properties of three types of noise, i.e., shot noise, relative-intensity noise, and non-optical noise. The SDE's performance was evaluated numerically and experimentally using two types of scattering phantom and in vitro tumor spheroids. The results confirmed that the SDE estimates scatterer densities accurately. The estimation accuracy improved significantly when compared with our previous deep-learning-based SDE, which was trained using numerical speckle patterns generated from a noise model that did not account for the spatial properties of noise.

Erratum: Deep convolutional neural networks-based scatterer density and resolution estimators in optical coherence tomography: erratum

[This corrects the article on p. 168 in vol. 13, PMID: 35154862.].

Label-free visualization and quantification of the drug-type-dependent response of tumor spheroids by dynamic optical coherence tomography

We demonstrate label-free dynamic optical coherence tomography (D-OCT)-based visualization and quantitative assessment of patterns of tumor spheroid response to three anti-cancer drugs. The study involved treating human breast adenocarcinoma (MCF-7 cell-line) with paclitaxel (PTX), tamoxifen citrate (TAM), and doxorubicin (DOX) at concentrations of 0 (control), 0.1, 1, and 10 µM for 1, 3, and 6 days. In addition, fluorescence microscopy imaging was performed for reference. The D-OCT imaging was performed using a custom-built OCT device. Two algorithms, namely logarithmic intensity variance (LIV) and late OCT correlation decay speed (OCDS[Formula: see text]) were used to visualize the tissue dynamics. The spheroids treated with 0.1 and 1 µM TAM appeared similar to the control spheroid, whereas those treated with 10 µM TAM had significant structural corruption and decreasing LIV and OCDS[Formula: see text] over treatment time. The spheroids treated with PTX had decreasing volumes and decrease of LIV and OCDS[Formula: see text] signals over time at most PTX concentrations. The spheroids treated with DOX had decreasing and increasing volumes over time at DOX concentrations of 1 and 10 µM, respectively. Meanwhile, the LIV and OCDS[Formula: see text] signals decreased over treatment time at all DOX concentrations. The D-OCT, particularly OCDS[Formula: see text], patterns were consistent with the fluorescence microscopic patterns. The diversity in the structural and D-OCT results among the drug types and among the concentrations are explained by the mechanisms of the drugs. The presented results suggest that D-OCT is useful for evaluating the difference in the tumor spheroid response to different drugs and it can be a useful tool for anti-cancer drug testing.

Machine Learning-Assisted Short-Wave InfraRed (SWIR) Techniques for Biomedical Applications: Towards Personalized Medicine

Personalized medicine transforms healthcare by adapting interventions to individuals' unique genetic, molecular, and clinical profiles. To maximize diagnostic and/or therapeutic efficacy, personalized medicine requires advanced imaging devices and sensors for accurate assessment and monitoring of individual patient conditions or responses to therapeutics. In the field of biomedical optics, short-wave infrared (SWIR) techniques offer an array of capabilities that hold promise to significantly enhance diagnostics, imaging, and therapeutic interventions. SWIR techniques provide in vivo information, which was previously inaccessible, by making use of its capacity to penetrate biological tissues with reduced attenuation and enable researchers and clinicians to delve deeper into anatomical structures, physiological processes, and molecular interactions. Combining SWIR techniques with machine learning (ML), which is a powerful tool for analyzing information, holds the potential to provide unprecedented accuracy for disease detection, precision in treatment guidance, and correlations of complex biological features, opening the way for the data-driven personalized medicine field. Despite numerous biomedical demonstrations that utilize cutting-edge SWIR techniques, the clinical potential of this approach has remained significantly underexplored. This paper demonstrates how the synergy between SWIR imaging and ML is reshaping biomedical research and clinical applications. As the paper showcases the growing significance of SWIR imaging techniques that are empowered by ML, it calls for continued collaboration between researchers, engineers, and clinicians to boost the translation of this technology into clinics, ultimately bridging the gap between cutting-edge technology and its potential for personalized medicine.

Synthesizing the degree of polarization uniformity from non-polarization-sensitive optical coherence tomography signals using a neural network

Degree of polarization uniformity (DOPU) imaging obtained by polarization-sensitive optical coherence tomography (PS-OCT) has the potential to provide biomarkers for retinal diseases. It highlights abnormalities in the retinal pigment epithelium that are not always clear in the OCT intensity images. However, a PS-OCT system is more complicated than conventional OCT. We present a neural-network-based approach to estimate the DOPU from standard OCT images. DOPU images were used to train a neural network to synthesize the DOPU from single-polarization-component OCT intensity images. DOPU images were then synthesized by the neural network, and the clinical findings from ground truth DOPU and synthesized DOPU were compared. There is a good agreement in the findings for RPE abnormalities: recall was 0.869 and precision was 0.920 for 20 cases with retinal diseases. In five cases of healthy volunteers, no abnormalities were found in either the synthesized or ground truth DOPU images. The proposed neural-network-based DOPU synthesis method demonstrates the potential of extending the features of retinal non-PS OCT.