Microscopic computed tomography with AI-CNN-powered image analysis: the path to phenotype bleomycin-induced lung injury.

Bleomycin (BLM)-induced lung injury in mice is a valuable model for investigating the molecular mechanisms that drive inflammation and fibrosis and for evaluating potential therapeutic approaches to treat the disease. Given high variability in the BLM model, it is critical to accurately phenotype the animals in the course of an experiment. In the present study, we aimed to demonstrate the utility of microscopic computed tomography (µCT) imaging combined with an artificial intelligence (AI)-convolutional neural network (CNN)-powered lung segmentation for rapid phenotyping of BLM mice. µCT was performed in freely breathing C57BL/6J mice under isoflurane anesthesia on and after BLM administration. Terminal invasive lung function measurement and histological assessment of the left lung collagen content were conducted as well. µCT image analysis demonstrated gradual and time-dependent development of lung injury as evident by alterations in the lung density, air-to-tissue volume ratio, and lung aeration in mice treated with BLM. The right and left lung were unequally affected. µCT-derived parameters such as lung density, air-to-tissue volume ratio, and nonaerated lung volume correlated well with the invasive lung function measurement and left lung collagen content. Our study demonstrates the utility of AI-CNN-powered µCT image analysis for rapid and accurate phenotyping of BLM mice in the course of disease development and progression. Microscopic computed tomography (µCT) imaging combined with an artificial intelligence (AI)-convolutional neural network (CNN)-powered lung segmentation is a rapid and powerful tool for noninvasive phenotyping of bleomycin mice over the course of the disease. This, in turn, allows earlier and more reliable identification of therapeutic effects of new drug candidates, ultimately leading to the reduction of unnecessary procedures in animals in pharmacological research.