Enhanced Artificial Intelligence Methods for Liver Steatosis Assessment Using Machine Learning and Color Image Processing: Liver Color Project.

BACKGROUND: The use of livers with significant steatosis is associated with worse transplantation outcomes. Brain death donor liver acceptance is mostly based on subjective surgeon assessment of liver appearance, since steatotic livers acquire a yellowish tone. The aim of this study was to develop a rapid, robust, accurate, and cost-effective method to assess liver steatosis. METHODS: From June 1, 2018, to November 30, 2023, photographs and tru-cut needle biopsies were taken from adult brain death donor livers at a single university hospital for the study. All the liver photographs were taken by smartphones then color calibrated, segmented, and divided into patches. Color and texture features were then extracted and used as input, and the machine learning method was applied. This is a collaborative project between Vall d'Hebron University Hospital and Barcelona MedTech, Pompeu Fabra University, and is referred to as LiverColor. RESULTS: A total of 192 livers (362 photographs and 7240 patches) were included. When setting a macrosteatosis threshold of 30%, the best results were obtained using the random forest classifier, achieving an AUROC = 0.74, with 85% accuracy. CONCLUSION: Machine learning coupled with liver texture and color analysis of photographs taken with smartphones provides excellent accuracy for determining liver steatosis.

TRPV4 Channels Promote Pathological, but Not Physiological, Cardiac Remodeling through the Activation of Calcineurin/NFAT and TRPC6.

TRPV4 channels, which respond to mechanical activation by permeating Ca2+ into the cell, may play a pivotal role in cardiac remodeling during cardiac overload. Our study aimed to investigate TRPV4 involvement in pathological and physiological remodeling through Ca2+-dependent signaling. TRPV4 expression was assessed in heart failure (HF) models, induced by isoproterenol infusion or transverse aortic constriction, and in exercise-induced adaptive remodeling models. The impact of genetic TRPV4 inhibition on HF was studied by echocardiography, histology, gene and protein analysis, arrhythmia inducibility, Ca2+ dynamics, calcineurin (CN) activity, and NFAT nuclear translocation. TRPV4 expression exclusively increased in HF models, strongly correlating with fibrosis. Isoproterenol-administered transgenic TRPV4-/- mice did not exhibit HF features. Cardiac fibroblasts (CFb) from TRPV4+/+ animals, compared to TRPV4-/-, displayed significant TRPV4 overexpression, elevated Ca2+ influx, and enhanced CN/NFATc3 pathway activation. TRPC6 expression paralleled that of TRPV4 in all models, with no increase in TRPV4-/- mice. In cultured CFb, the activation of TRPV4 by GSK1016790A increased TRPC6 expression, which led to enhanced CN/NFATc3 activation through synergistic action of both channels. In conclusion, TRPV4 channels contribute to pathological remodeling by promoting fibrosis and inducing TRPC6 upregulation through the activation of Ca2+-dependent CN/NFATc3 signaling. These results pose TRPV4 as a primary mediator of the pathological response.