Related Experiment Video
Updated: Jun 3, 2025
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
14.1K
Artificial Intelligence Unveils the Unseen: Mapping Novel Lung Patterns in Bronchiectasis via Texture Analysis
Athira Nair1, Rakesh Mohan2, Mandya Venkateshmurthy Greeshma3
1Department of Respiratory Medicine, JSS Medical College, JSS Academy of Higher Education & Research (JSS AHER), Mysore 570004, Karnataka, India.
Diagnostics (Basel, Switzerland)
|January 8, 2025
Summary
Artificial intelligence (AI) analysis of lung texture in bronchiectasis reveals subtle parenchymal changes missed by conventional CT scans. This AI approach enhances understanding of disease progression and potential therapeutic strategies.
Area of Science:
- Pulmonary Medicine
- Radiology
- Medical Imaging Analysis
Background:
- Thin-section CT (TSCT) is the standard for detecting bronchiectasis but may miss subtle alveolar and interstitial changes.
- Artificial intelligence (AI) offers potential for novel insights into lung parenchymal involvement beyond traditional imaging.
- This study evaluates AI-based quantitative lung texture analysis alongside the Bronchiectasis Radiologically Indexed CT Score (BRICS).
Purpose of the Study:
- To assess lung involvement in bronchiectasis using BRICS and AI-based quantitative lung texture analysis.
- To identify subtle alveolar and interstitial changes not easily detectable with conventional HRCT.
- To explore the utility of AI in understanding bronchiectasis pathology and progression.
Main Methods:
- A cross-sectional study of 45 patients diagnosed with bronchiectasis.
- Severity classification using the Bronchiectasis Radiologically Indexed CT Score (BRICS): Mild, Moderate, Severe, and tractional.
- AI-based lung texture analysis using IMBIO software to detect abnormal lung textures, focusing on alveolar and interstitial involvement.
Main Results:
- BRICS classified disease severity: Mild (8.9%), Moderate (31.1%), Severe (24.4%), and tractional (35.6%).
- AI identified significant alveolar and interstitial abnormalities, providing insights beyond HRCT.
- Trends showed increased lung hyperlucency, ground-glass opacity, reticular changes, and honeycombing with disease severity. Elevated pulmonary vascular volume (PVV) correlated with higher BRICS scores.
Conclusions:
- AI-based lung texture analysis offers valuable insights into bronchiectasis parenchymal involvement.
- AI detects significant alveolar and interstitial abnormalities missed by conventional HRCT.
- AI has the potential to improve understanding of disease pathology, progression, and guide future therapeutic strategies.
