Application of Artificial Intelligence to In Vitro Tumor Modeling and Characterization of the Tumor Microenvironment.

In vitro tumor models have played vital roles in enhancing the understanding of the cellular and molecular composition of tumors, as well as their biochemical and biophysical characteristics. Advances in technology have enabled the evolution of tumor models from two-dimensional cell cultures to three-dimensional printed tumor models with increased levels of complexity and diverse output parameters. With the increase in complexity, the new generation of models is able to replicate the architecture and heterogeneity of the tumor microenvironment more realistically than their predecessors.

Isolation of Primary Rat Hepatocytes with Multiparameter Perfusion Control.

Primary hepatocytes are widely used in basic research on liver diseases and for toxicity testing in vitro. The two-step collagenase perfusion procedure for primary hepatocyte isolation is technically challenging, especially in portal vein cannulation. The procedure is also prone to occasional contamination and variations in perfusion conditions due to difficulties in the assembly, optimization, or maintenance of the perfusion setup.

Computer-aided assessment of the chemokine receptors CXCR3, CXCR4 and CXCR7 expression in gallbladder carcinoma.

Gallbladder carcinoma (GBC) is a vicious and invasive disease. The major challenge in the clinical treatment of GBC is the lack of a suitable prognosis method. Chemokine receptors such as CXCR3, CXCR4 and CXCR7 play vital roles in the process of tumour progression and metastasis.

Tethered primary hepatocyte spheroids on polystyrene multi-well plates for high-throughput drug safety testing.

Hepatocyte spheroids are useful models for mimicking liver phenotypes in vitro because of their three-dimensionality. However, the lack of a biomaterial platform which allows the facile manipulation of spheroid cultures on a large scale severely limits their application in automated high-throughput drug safety testing. In addition, there is not yet a robust way of controlling spheroid size, homogeneity and integrity during extended culture.

Deep learning enables automated scoring of liver fibrosis stages.

Current liver fibrosis scoring by computer-assisted image analytics is not fully automated as it requires manual preprocessing (segmentation and feature extraction) typically based on domain knowledge in liver pathology. Deep learning-based algorithms can potentially classify these images without the need for preprocessing through learning from a large dataset of images. We investigated the performance of classification models built using a deep learning-based algorithm pre-trained using multiple sources of images to score liver fibrosis and compared them against conventional non-deep learning-based algorithms - artificial neural networks (ANN), multinomial logistic regression (MLR), support vector machines (SVM) and random forests (RF).

Actomyosin contractility drives bile regurgitation as an early response during obstructive cholestasis.

Background & Aims: A wide range of liver diseases manifest as biliary obstruction, or cholestasis. However, the sequence of molecular events triggered as part of the early hepatocellular homeostatic response in obstructive cholestasis is poorly elucidated. Pericanalicular actin is known to accumulate during obstructive cholestasis.