AI-assisted semiquantitative measurement of murine bleomycin-induced lung fibrosis using in vivo micro-CT: an end-to-end approach.

Abstract

Small animal models are crucial for investigating idiopathic pulmonary fibrosis (IPF) and developing preclinical therapeutic strategies. However, there are several limitations to the quantitative measurements used in the longitudinal assessment of experimental lung fibrosis, e.g., histological or biochemical analyses introduce interindividual variability, whereas image-derived biomarker has yet to directly and accurately quantify the severity of lung fibrosis. This study investigates artificial intelligence (AI)-assisted, end-to-end, semiquantitative measurement of lung fibrosis using in vivo micro-computed tomography (CT). Based on the bleomycin (BLM)-induced lung fibrosis mouse model, the AI model predicts histopathological scores from in vivo micro-CT images, directly correlating these images with the severity of lung fibrosis in mice. Fibrosis severity was graded by the Ashcroft scale: none (0), mild (1-3), moderate (4-5), and severe (≥6). The overall accuracy, precision, recall, and F1 scores of the lung fibrosis severity-stratified 3-fold cross validation on 225 micro-CT images for the proposed AI model were 92.9%, 90.9%, 91.6%, and 91.0%, respectively. The overall area under the receiver operating characteristic curve (AUROC) was 0.990 [95% confidence interval (CI): 0.977, 1.000], with AUROC values of 1.000 for none (100 images, 95% CI: 0.997, 1.000), 0.969 for mild (43 images, 95% CI: 0.918, 1.000), 0.992 for moderate (36 images, 95% CI: 0.962, 1.000), and 0.992 for severe (46 images, 95% CI: 0.967, 1.000). Preliminary results indicate that AI-assisted, in vivo micro-CT-based semiquantitative measurements of murine are feasible and likely accurate. This novel method holds promise as a tool to improve the reproducibility of experimental studies in animal models of IPF.NEW & NOTEWORTHY To the best of our knowledge, this study is the first attempt to establish a direct link between radiological images and the severity of experimental lung fibrosis using artificial intelligence (AI). The proposed method, which accurately quantifies the degree of lung fibrosis in longitudinal observations of experimental animals, has the potential to serve as a new tool to improve the reproducibility of experimental studies in animals with idiopathic pulmonary fibrosis (IPF).