Machine learning for lung CT texture analysis: Improvement of inter-observer agreement for radiological finding classification in patients with pulmonary diseases

Highlights: • ML-based software can improve agreement with standard reference in not only each reader (p < 0.0001), but also consensus reading (p < 0.0001). • Accuracy by consensus with the software was significantly higher than that without the software (p < 0.0001) and the software alone (p < 0.0001). • ML-based CT texture analysis software has potential to play as second reader for radiological finding classification in pulmonary diseases. To evaluate the capability ML-based CT texture analysis for improving interobserver agreement and accuracy of radiological finding assessment in patients with COPD, interstitial lung diseases or infectious diseases.