Machine learning methods can quantify extent of lung fibrosis on CT scans

What is it about?

Extent of lung fibrosis can be assessed quantitatively on CT scans using a machine learning method called data-driven texture analysis (DTA). DTA fibrosis scores are reliable, valid and responsive, and an increase of ∼3.4% represents a clinically important change.

Featured Image

Why is it important?

This work suggests that quantitative CT analysis using DTA, an objective, image-based measure of morphology, may be a valuable additional tool for assessing outcomes in IPF.