Studying pulmonary fibrosis due to microbial infection via automated microscopic image analysis
Yajie Chen1, Henghui He2, Licheng Luo1
1School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China.
Introduction:
Pulmonary fibrosis is a consequential complication of microbial infections, which has notably been observed in SARS-CoV-2 infections in recent times. Macrophage polarization, specifically the M2-type, is a significant mechanism that induces pulmonary fibrosis, and its role in the development of Post- COVID-19 Pulmonary Fibrosis is worth investigating. While pathological examination is the gold standard for studying pulmonary fibrosis, manual review is subject to limitations. In light of this, we have constructed a novel method that utilizes artificial intelligence techniques to analyze fibro-pathological images. This method involves image registration, cropping, fibrosis degree classification, cell counting and calibration, and it has been utilized to analyze microscopic images of COVID-19 lung tissue.
Methods:
Our approach combines the Transformer network with ResNet for fibrosis degree classification, leading to a significant improvement over the use of ResNet or Transformer individually. Furthermore, we employ semi-supervised learning which utilize both labeled and unlabeled data to enhance the ability of the classification network in analyzing complex samples. To facilitate cell counting, we applied the Trimap method to localize target cells. To further improve the accuracy of the counting results, we utilized an effective area calibration method that better reflects the positive density of target cells.
Results:
The image analysis method developed in this paper allows for standardization, precision, and staging of pulmonary fibrosis. Analysis of microscopic images of COVID-19 lung tissue revealed a significant number of macrophage aggregates, among which the number of M2-type macrophages was proportional to the degree of fibrosis.
Discussion:
The image analysis method provids a more standardized approach and more accurate data for correlation studies on the degree of pulmonary fibrosis. This advancement can assist in the treatment and prevention of pulmonary fibrosis. And M2-type macrophage polarization is a critical mechanism that affects pulmonary fibrosis, and its specific molecular mechanism warrants further exploration.
Insights
Artificial intelligence analyzes lung tissue images to quantify pulmonary fibrosis. This novel method reveals M2-type macrophages correlate with fibrosis severity in post-COVID-19 patients, aiding future treatments.
Area of Science:
- Pathology
- Medical Imaging
- Artificial Intelligence
Background:
- Pulmonary fibrosis is a serious complication of infections like SARS-CoV-2.
- M2-type macrophage polarization is a key driver of pulmonary fibrosis.
- Manual analysis of lung tissue images for fibrosis has limitations.
Purpose of the Study:
- To develop and validate an AI-driven method for analyzing fibro-pathological images.
- To investigate the role of M2-type macrophages in post-COVID-19 pulmonary fibrosis.
Main Methods:
- Developed an AI method combining Transformer and ResNet for fibrosis classification.
- Utilized semi-supervised learning to enhance classification accuracy.
- Employed Trimap and area calibration for precise cell counting.
Main Results:
- The AI method enables standardized, precise staging of pulmonary fibrosis.
- Analysis of COVID-19 lung tissue showed M2-type macrophage aggregates.
- The number of M2-type macrophages was proportional to the degree of fibrosis.
Conclusions:
- The AI image analysis method offers improved standardization and accuracy for fibrosis studies.
- M2-type macrophage polarization is critical in pulmonary fibrosis development.
- Further research into the molecular mechanisms of M2-type macrophages is warranted.
