Deep Learning-based Disease Severity Biomarkers on CT; Posthoc Analysis in a Phase 2a Placebo-controlled Study of ENV-101 in Subjects With Idiopathic Pulmonary Fibrosis (ATS 2025) - Feb 24, 2025 - Pres time: May 20, 2025; 09:15 AM - 11:15 AM; Location: Room 2002; Poster Board # 610; P2 | "Emerging deep learning-based CT biomarkers may offer a non-invasive way to predict disease progression and assess treatment effects in antifibrotic clinical trials. The ENV-IPF-101 (NCT04968574) trial was a randomised, double-blind, placebo-controlled study of ENV-101, a novel Hedgehog (Hh) signalling pathway inhibitor, in patients with IPF... Utilizing deep learning models, patients treated with ENV-101 over 12 weeks showed significantly improved lung volume, significantly reduced pulmonary vascular volume and reduced fibrosis. These results indicate that in IPF, deep learning based quantification of lung volume and pulmonary vascular changes may provide additional insights that corroborate physiological improvement in lung function."
Biomarker • Clinical • P2a data • Retrospective data • Cognitive Disorders • Fibrosis • Idiopathic Pulmonary Fibrosis • Immunology • Pulmonary Disease • Respiratory Diseases
|
|
Muhunthan Thillai, MD, PhD; Anita Difrancesco, BSc; Simon L F. Walsh, MD, PhD; Elliott Bussell, PhD; Miguel de los Rios, PhD; John Hood, PhD, BS; Miguel Montiero, PhD
|