A fully automated deep learning pipeline for micro-CT-imaging-based densitometry of lung fibrosis murine models.

Idiopathic pulmonary fibrosis, the archetype of pulmonary fibrosis (PF), is a chronic lung disease of a poor prognosis, characterized by progressively worsening of lung function. Although histology is still the gold standard for PF assessment in preclinical practice, histological data typically involve less than 1% of total lung volume and are not amenable to longitudinal studies. A miniaturized version of computed tomography (µCT) has been introduced to radiologically examine lung in preclinical murine models of PF. The linear relationship between X-ray attenuation and tissue density allows lung densitometry on total lung volume. However, the huge density changes caused by PF usually require manual segmentation by trained operators, limiting µCT deployment in preclinical routine. Deep learning approaches have achieved state-of-the-art performance in medical image segmentation. In this work, we propose a fully automated deep learning approach to segment right and left lung on µCT imaging and subsequently derive lung densitometry. Our pipeline first employs a convolutional network (CNN) for pre-processing at low-resolution and then a 2.5D CNN for higher-resolution segmentation, combining computational advantage of 2D and ability to address 3D spatial coherence without compromising accuracy. Finally, lungs are divided into compartments based on air content assessed by density. We validated this pipeline on 72 mice with different grades of PF, achieving a Dice score of 0.967 on test set. Our tests demonstrate that this automated tool allows for rapid and comprehensive analysis of µCT scans of PF murine models, thus laying the ground for its wider exploitation in preclinical settings.

The importance of routine quality control for reproducible pulmonary measurements by in vivo micro-CT.

Micro-computed tomography (CT) imaging provides densitometric and functional assessment of lung diseases in animal models, playing a key role either in understanding disease progression or in drug discovery studies. The generation of reliable and reproducible experimental data is strictly dependent on a system's stability. Quality controls (QC) are essential to monitor micro-CT performance but, although QC procedures are standardized and routinely employed in clinical practice, detailed guidelines for preclinical imaging are lacking. In this work, we propose a routine QC protocol for in vivo micro-CT, based on three commercial phantoms. To investigate the impact of a detected scanner drift on image post-processing, a retrospective analysis using twenty-two healthy mice was performed and lung density histograms used to compare the area under curve (AUC), the skewness and the kurtosis before and after the drift. As expected, statistically significant differences were found for all the selected parameters [AUC 532 ± 31 vs. 420 ± 38 (p < 0.001); skewness 2.3 ± 0.1 vs. 2.5 ± 0.1 (p < 0.001) and kurtosis 4.2 ± 0.3 vs. 5.1 ± 0.5 (p < 0.001)], confirming the importance of the designed QC procedure to obtain a reliable longitudinal quantification of disease progression and drug efficacy evaluation.

Pivotal role of micro-CT technology in setting up an optimized lung fibrosis mouse model for drug screening.

Idiopathic pulmonary fibrosis (IPF) is a progressive disease with no curative pharmacological treatment. The most used animal model of IPF for anti-fibrotic drug screening is bleomycin (BLM)-induced lung fibrosis. However, several issues have been reported: the balance among disease resolution, an appropriate time window for therapeutic intervention and animal welfare remain critical aspects yet to be fully elucidated. In this study, C57Bl/6 male mice were treated with BLM via oropharyngeal aspiration (OA) following either double or triple administration. The fibrosis progression was longitudinally assessed by micro-CT every 7 days for 4 weeks after BLM administration. Quantitative micro-CT measurements highlighted that triple BLM administration was the ideal dose regimen to provoke sustained lung fibrosis up to 28 days. These results were corroborated with lung histology and Bronchoalveolar Lavage Fluid cells. We have developed a mouse model with prolonged lung fibrosis enabling three weeks of a curative therapeutic window for the screening of putative anti-fibrotic drugs. Moreover, we have demonstrated the pivotal role of longitudinal micro-CT imaging in reducing the number of animals required per experiment in which each animal can be its own control. This approach permits a valuable decrease in costs and time to develop disease animal models.

In-vivo lung fibrosis staging in a bleomycin-mouse model: a new micro-CT guided densitometric approach.

Although increasing used in the preclinical testing of new anti-fibrotic drugs, a thorough validation of micro-computed tomography (CT) in pulmonary fibrosis models has not been performed. Moreover, no attempts have been made so far to define density thresholds to discriminate between aeration levels in lung parenchyma. In the present study, a histogram-based analysis was performed in a mouse model of bleomycin (BLM)-induced pulmonary fibrosis by micro-CT, evaluating longitudinal density changes from 7 to 21 days after BLM challenge, a period representing the progression of fibrosis. Two discriminative densitometric indices (i.e. 40th and 70th percentiles) were extracted from Hounsfield Unit density distributions and selected for lung fibrosis staging. The strong correlation with histological findings (rSpearman = 0.76, p < 0.01) confirmed that variations in 70th percentile could reflect a pathological lung condition and estimate the effect of antifibrotic treatments. This index was therefore used to define lung aeration levels in mice distinguishing in hyper-inflated, normo-, hypo- and non-aerated pulmonary compartments. A retrospective analysis performed on a large cohort of mice confirmed the correlation between the proposed preclinical density thresholds and the histological outcomes (rSpearman = 0.6, p < 0.01), strengthening their suitability for tracking disease progression and evaluating antifibrotic drug candidates.