Quantitative Analysis of Arsenic- and Sucrose-Induced Liver Collagen Remodeling Using Machine Learning on Second-Harmonic Generation Microscopy Images.

Non-alcoholic fatty liver disease (NAFLD) is a silent condition that can lead to fatal cirrhosis, with dietary factors playing a central role. The effect of various dietary interventions on male Wistar rats were evaluated in four diets: control, arsenic, sucrose, and arsenic-sucrose. SHG microscopy images from the right ventral lobe of the liver tissue were analyzed with a neural network trained to detect the presence or absence of collagen fibers, followed by the assessment of their orientation and angular distribution. Machine learning classification of SHG microscopy images revealed a marked increase in fibrosis risk with dietary interventions: <10% in controls, 24% with arsenic, 40% with sucrose, and 62% with combined arsenic-sucrose intake. Angular width distribution of collagen fibers narrowed dramatically across groups: 26° (control), 24° (arsenic), 15.7° (sucrose), and 2.8° (arsenic-sucrose). This analysis revealed four key statistical features for classifying the images according to the presence or absence of collagen fibers: (1) the percentage of pixels whose intensity is above the 15% noise threshold, (2) the Mean-to-Standard Deviation ratio (Mean/std), (3) the mode, and (4) the total intensity (sum). These results demonstrate that a diet rich in sucrose, particularly in combination with arsenic, constitutes a significant risk factor for liver collagen fiber remodeling.