Leyendecker Lars, Weltin Anna Louisa, Nienhaus Florian, Matthey Michaela, Nießing Bastian, Wenzel Daniela, Schmitt Robert H
Department of Production Quality, Production Metrology and Bio-Adaptive Production, Fraunhofer Institute for Production Technology IPT, Aachen, Germany.
Department of Systems Physiology, Medical Faculty, Ruhr University of Bochum, Bochum, Germany.
Front Big Data. 2025 Jun 10;8:1461016. doi: 10.3389/fdata.2025.1461016. eCollection 2025.
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 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 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.
慢性阻塞性肺疾病（COPD）是全球死亡的主要原因之一，需要针对肺功能和重塑的新疗法。最初通过分析组织学肺切片，利用小鼠模型研究它们对肺气肿形成的影响。通过手动评估多个组织学显微镜图像上的平均线性截距（MLI），对肺气肿特有的气腔扩大程度进行量化。除了繁琐且成本高昂外，由于其复杂性和主观性，这项手动任务缺乏科学可比性。为了延续既定做法并保持研究结果的可比性，我们提出一种基于深度学习的方法，利用专门用于基于语义分割的细胞培养和组织分析领域的自动机器学习（AutoML）软件，自动测定组织学肺切片中的MLI。我们在源自一项研究的染色组织学显微镜图像上开发并评估我们的图像处理管道，该研究包括两组C57BL/6小鼠，其中一组暴露于香烟烟雾，而对照组未暴露。结果表明，分割算法表现出色，交并比（IoU）分数始终超过90%。此外，与手动生成的值相比，自动方法始终产生更高的MLI值。然而，这种差异的一致性表明，自动方法可以不受任何限制地可靠使用。此外，它在区分吸烟者和非吸烟者的肺部方面具有统计学意义。
