Related Experiment Video
Updated: Jun 23, 2025
Imaging Features of Systemic Sclerosis-Associated Interstitial Lung Disease
Published on: June 16, 2020
Correlation of CT-based radiomics analysis with pathological cellular infiltration in fibrosing interstitial lung
Akira Haga1,2, Tae Iwasawa3, Toshihiro Misumi4
1Dept. of Radiology, Kanagawa Cardiovascular & Respiratory Center, Yokohama, Japan.
Insights
Computed tomography (CT) radiomics can predict cellular infiltration in patients with idiopathic pulmonary fibrosis (IPF). This AI-driven approach correlates CT features with surgical lung biopsy findings, aiding in disease assessment.
Area of Science:
- Pulmonary Medicine
- Radiology
- Artificial Intelligence
Background:
- Idiopathic pulmonary fibrosis (IPF) is a progressive lung disease characterized by cellular infiltration.
- Accurate assessment of cellular infiltration is crucial for IPF diagnosis and management.
- Current methods often rely on invasive procedures like surgical lung biopsy (SLB).
Purpose of the Study:
- To identify computed tomography (CT) radiomics features associated with cellular infiltration in fibrotic interstitial lung disease (ILD).
- To develop and validate CT radiomics models for predicting cellular infiltration in ILD patients.
Main Methods:
- Analysis of CT images from 100 ILD patients who underwent SLB.
- Extraction of radiomics features using AI-based software and PyRadiomics.
- Construction and external validation of models to predict cell counts and cellularity classifications.
Main Results:
- A CT radiomics model accurately predicted cell counts in 59 external validation specimens (RMSE: 0.797).
- A classification model achieved 70% accuracy and a 0.73 F1 score for predicting higher or lower cellularity.
- The models demonstrated good correlation with SLB findings.
Conclusions:
- CT radiomics offers a non-invasive method to assess cellular infiltration in ILD.
- The developed radiomics model provides valuable insights into ILD cellularity.
- This approach may aid in the non-invasive evaluation of fibrotic lung disease.
Purpose:
We aimed to identify computed tomography (CT) radiomics features that are associated with cellular infiltration and construct CT radiomics models predictive of cellular infiltration in patients with fibrotic ILD.
Materials And Methods:
CT images of patients with ILD who underwent surgical lung biopsy (SLB) were analyzed. Radiomics features were extracted using artificial intelligence-based software and PyRadiomics. We constructed a model predicting cell counts in histological specimens, and another model predicting two classifications of higher or lower cellularity. We tested these models using external validation.
Results:
Overall, 100 patients (mean age: 62 ± 8.9 [standard deviation] years; 61 men) were included. The CT radiomics model used to predict cell count in 140 histological specimens predicted the actual cell count in 59 external validation specimens (root-mean-square error: 0.797). The two-classification model's accuracy was 70% and the F1 score was 0.73 in the external validation dataset including 30 patients.
Conclusion:
The CT radiomics-based model developed in this study provided useful information regarding the cellular infiltration in the ILD with good correlation with SLB specimens.
More Related Videos
07:38A Multimodal Imaging Approach Based on Micro-CT and Fluorescence Molecular Tomography for Longitudinal Assessment of Bleomycin-Induced Lung Fibrosis in Mice
Published on: April 13, 2018
08:05Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020