A machine learning model based on chest CT images accurately diagnoses and grades the severity of COPD.
Key Details
- 1Researchers developed a machine learning model using chest CT data from 173 COPD patients and 176 healthy controls.
- 2The model segments the lung parenchyma, airway, pulmonary artery, and vein, then extracts imaging features.
- 3Diagnostic accuracy for COPD was 95% (training set) and 96% (test set); AUC was 0.98 and 0.97, respectively.
- 4Severity grading accuracy was 78% (training) and 72% (test); AUC was 0.89 and 0.8.
- 5Traditional spirometry tests may be less effective or difficult for some patients, highlighting CT's added value.
Why It Matters
This machine learning approach could offer a more accessible and detailed assessment for COPD diagnosis and severity, especially for patients who struggle with spirometry. Improved diagnostic performance has the potential to personalize care and improve clinical outcomes for COPD patients in radiology practice.
Source
AuntMinnie
Related News
•AuntMinnie
Radiologists Struggle to Spot AI-Generated Radiology Images
Radiologists correctly identify AI-generated images 75% of the time, with CT and MRI images being particularly challenging to spot.
•AuntMinnie
Radiology Leads FDA AI Device Approvals Over Three Decades
Radiology accounts for 76% of all FDA-cleared AI/ML-enabled medical devices as of the end of 2025.
•Radiology Business
Automation Bias: How AI Can Compromise Radiologist Accuracy
AI decision support can induce automation bias, leading radiologists to accept incorrect interpretations and potentially reduce their diagnostic accuracy.