Deep learning based automation of mean linear intercept quantification in COPD research

TL;DR

This paper introduces a deep learning method to automate the quantification of lung tissue changes in COPD research, improving efficiency and reliability.

Contribution

A novel deep learning-based automation for mean linear intercept quantification in COPD histology using AIxCell.

Findings

The AIxCell algorithm achieves IoU scores exceeding 90% in segmenting histological lung sections.

Automated MLI values are consistently higher than manual values but show reliable and significant results.

The method reliably distinguishes between smoker and non-smoker lung tissue.

Abstract

Chronic obstructive pulmonary disease (COPD), a major cause of global mortality, necessitates novel therapies targeting lung function and remodeling. Their effect on emphysema formation is initially investigated using mouse models by analyzing histological lung sections. The extent of airspace enlargement that is characteristic for emphysema is quantified by manual assessment of the mean linear intercept (MLI) across multiple histological microscopy images. Besides being tedious and cost intensive, this manual task lacks scientific comparability due to complexity and subjectivity. In order to continue with the well-established practice and to preserve the comparability of study results, we propose a deep learning-based approach for automating the determination of MLI in histological lung sections utilizing the AutoML software AIxCell which is specialized for the domain of semantic segmentation-based cell culture and tissue analysis. We develop and evaluate our image processing pipeline on stained histological microscope images that stem from a study including two groups of C57BL/6 mice where one group was exposed to cigarette smoke while the control group was not. The results indicate that the AIxCell segmentation algorithm achieves excellent performance, with IoU scores consistently exceeding 90%. Furthermore, the automated approach consistently yields higher MLI values compared to the manually generated values. However, the consistent nature of this discrepancy suggests that the automated approach can be reliably employed without any limitations. Moreover, it demonstrates statistical significance in distinguishing between smoker's and non-smoker's lungs.

Figures