Automated AI-assisted Ashcroft scoring of lung fibrosis in spirometry-confirmed and bleomycin-induced mouse model of IPF

Background & aim:

Clinically derived Ashcroft scoring of lung fibrosis is commonly applied to preclinical models of idiopathic pulmonary fibrosis (IPF). As for any manual, semiquantitative histopathological scoring system, Ashcroft scoring is prone to inter- and intra-observer variability which influences accuracy and reproducibility of study results. The present study aimed to develop and validate an automated deep learning-assisted digital imaging analysis pipeline, termed GHOST (Gubra Histopathological Objective Scoring Technology) for objective assessment of Ashcroft score in the spirometry-confirmed and bleomycin-induced mouse model of IPF (BLEO-IPF).