Weakly supervised identification of microscopic human breast cancer-related optical signatures from normal-appearing breast tissue.

With the latest advancements in optical bioimaging, rich structural and functional information has been generated from biological samples, which calls for capable computational tools to identify patterns and uncover relationships between optical characteristics and various biomedical conditions. Constrained by the existing knowledge of the novel signals obtained by those bioimaging techniques, precise and accurate ground truth annotations can be difficult to obtain. Here we present a weakly supervised deep learning framework for optical signature discovery based on inexact and incomplete supervision. The framework consists of a multiple instance learning-based classifier for the identification of regions of interest in coarsely labeled images and model interpretation techniques for optical signature discovery. We applied this framework to investigate human breast cancer-related optical signatures based on virtual histopathology enabled by simultaneous label-free autofluorescence multiharmonic microscopy (SLAM), with the goal of exploring unconventional cancer-related optical signatures from normal-appearing breast tissues. The framework has achieved an average area under the curve (AUC) of 0.975 on the cancer diagnosis task. In addition to well-known cancer biomarkers, non-obvious cancer-related patterns were revealed by the framework, including NAD(P)H-rich extracellular vesicles observed in normal-appearing breast cancer tissue, which facilitate new insights into the tumor microenvironment and field cancerization. This framework can be further extended to diverse imaging modalities and optical signature discovery tasks.

Differential Uptake of Antisense Oligonucleotides in Mouse Hepatocytes and Macrophages Revealed by Simultaneous Two-Photon Excited Fluorescence and Coherent Raman Imaging.

Antisense oligonucleotides (ASOs), a novel paradigm in modern therapeutics, modulate cellular gene expression by binding to complementary messenger RNA (mRNA) sequences. While advances in ASO medicinal chemistry have greatly improved the efficiency of cellular uptake, selective uptake by specific cell types has been difficult to achieve. For more efficient and selective uptake, ASOs are often conjugated with molecules with high binding affinity for transmembrane receptors. Triantennary N-acetyl-galactosamine conjugated phosphorothioate ASOs (GalNAc-PS-ASOs) were developed to enhance targeted ASO delivery into liver through the hepatocyte-specific asialoglycoprotein receptor (ASGR). We assessed the kinetics of uptake and subsequent intracellular distribution of AlexaFluor 488 (AF488)-labeled PS-ASOs and GalNAc-PS-ASOs in J774A.1 mouse macrophages and primary mouse or rat hepatocytes using simultaneous coherent anti-Stokes Raman scattering (CARS) and two-photon fluorescence (2PF) imaging. The CARS modality captured the dynamic lipid distributions and overall morphology of the cells; two-photon fluorescence (2PF) measured the time- and dose-dependent localization of ASOs delivered by a modified treatment of suspension cells. Our results show that in macrophages, the uptake rate of PS-ASOs did not significantly differ from that of GalNAc-PS-ASOs. However, in hepatocytes, GalNAc-PS-ASOs exhibited a peripheral uptake distribution compared to a polar uptake distribution observed in macrophages. The peripheral distribution correlated with a significantly larger amount of internalized GalNAc-PS-ASOs compared to the PS-ASOs. This work demonstrates the relevance of multimodal imaging for elucidating the uptake mechanism, accumulation, and fate of different ASOs in liver cells that can be used further in complex in vitro models and liver tissues to evaluate ASO distribution and activity.

Synthetic polarization-sensitive optical coherence tomography by deep learning.

Polarization-sensitive optical coherence tomography (PS-OCT) is a high-resolution label-free optical biomedical imaging modality that is sensitive to the microstructural architecture in tissue that gives rise to form birefringence, such as collagen or muscle fibers. To enable polarization sensitivity in an OCT system, however, requires additional hardware and complexity. We developed a deep-learning method to synthesize PS-OCT images by training a generative adversarial network (GAN) on OCT intensity and PS-OCT images. The synthesis accuracy was first evaluated by the structural similarity index (SSIM) between the synthetic and real PS-OCT images. Furthermore, the effectiveness of the computational PS-OCT images was validated by separately training two image classifiers using the real and synthetic PS-OCT images for cancer/normal classification. The similar classification results of the two trained classifiers demonstrate that the predicted PS-OCT images can be potentially used interchangeably in cancer diagnosis applications. In addition, we applied the trained GAN models on OCT images collected from a separate OCT imaging system, and the synthetic PS-OCT images correlate well with the real PS-OCT image collected from the same sample sites using the PS-OCT imaging system. This computational PS-OCT imaging method has the potential to reduce the cost, complexity, and need for hardware-based PS-OCT imaging systems.