Recent advancements in medical imaging have opened new avenues in the treatment and monitoring of idiopathic pulmonary fibrosis (IPF), a progressive lung disease that has long posed challenges for both patients and healthcare providers. Researchers have unveiled novel CT-based tools that have shown promising results in detecting improvements in lung volume and fibrosis in patients undergoing treatment with the Hedgehog pathway inhibitor ENV-101. This groundbreaking research was presented at the American Thoracic Society (ATS) 2025 International Conference, highlighting the potential of integrating artificial intelligence (AI) into patient care.
Understanding IPF: Challenges and Current Approaches
IPF is characterized by the progressive scarring of lung tissue, leading to declining lung function with an alarmingly low median survival of just three years. Traditional imaging methods often fall short in sensitivity, making subtle changes in disease progression difficult to monitor effectively. Therefore, there has been a pressing need for more robust and responsive diagnostic tools that can accurately gauge treatment responses.
AI-Based Imaging of Disease Progression
The research leveraged data from the ENV-IPF-101 clinical trial (see NCT04968574), a double-blind, placebo-controlled phase 2a study assessing ENV-101 in adults with IPF. This innovative therapeutic agent has been designed to inhibit aberrant Hedgehog pathway signaling, which is a critical factor in driving lung fibrosis and myofibroblast activation. The participants in the trial were randomly assigned to receive ENV-101 or a placebo over a 12-week period.
For their investigation, researchers from Qureight and Endeavor BioMedicines analyzed high-resolution CT (HRCT) scans from 34 patients—16 treated with ENV-101 and 18 given a placebo—utilizing four validated deep learning models to extract nuanced quantitative measures:
- Lung8, for assessing lung volume
- Vascul8, for pulmonary vessel volume measurement
- Fibr8, to determine the extent of fibrosis
- Air8, used for measuring airway volume
These AI models were optimized to identify subtle structural changes in fibrotic lung tissue, providing physicians with reliable, noninvasive snapshots of lung health that reflect real changes in patients’ breathing capacities.
Impact of ENV-101 on Lung Health
The results revealed that patients treated with ENV-101 experienced statistically significant increases in lung volume after 12 weeks, achieving an increase of 142.28 mL compared to a decrease of 113.07 mL in the placebo group. This positive change also correlated with improvements in percent predicted forced vital capacity (FVC), with statistical significance (P = .03).
Moreover, patients receiving ENV-101 demonstrated a notable reduction in pulmonary vascular volume compared to those on placebo (–0.25% vs. 0.07%; P = .0007), and a numerical trend toward less fibrosis (–1.32% vs. 1.32%; P = .063). This indicates that ENV-101 could be pivotal in alleviating lung congestion and reducing scarring over time, hinting at the drug’s potential to slow or potentially reverse lung damage associated with IPF.
The effect sizes observed in this study were substantial across several key metrics, including 0.78 for percent predicted FVC and 0.87 for lung volume. Such statistics suggest that ENV-101 may represent a significant advancement in halting or even reversing fibrotic progression in a subset of patients.
Looking Ahead: The Promise of ENV-101
While the analysis was based on a limited sample size and a relatively short treatment duration, it highlights the promising role of deep learning as a complementary tool to traditional methods in IPF trials. As John Hood, PhD, cofounder and CEO of Endeavor BioMedicines, noted in a discussion at the ATS conference, ENV-101 may provide advantages over existing treatments, such as pirfenidone and nintedanib, which can cause tolerability issues and do not consistently improve patients’ well-being.
Dr. Hood expressed the critical unmet medical need in treating IPF: “We just don’t have a therapy that makes patients better,” reflecting the aspirations at Endeavor to deliver a treatment that improves lung function and overall quality of life for those impacted by this debilitating condition.
As the study findings undergo validation in larger trials, the hope is that ENV-101 could reshape the therapeutic landscape for IPF, enhancing care for patients currently facing limited options in managing this complex disease.
References
- Walsh SL, Difrancesco A, Hood J. 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. Presented at: ATS 2025 International Conference; May 20, 2025; San Francisco, CA. https://www.atsjournals.org/doi/abs/10.1164/ajrccm.2025.211.Abstracts.A5339
- Zolak JS, de Andrade JA. Idiopathic pulmonary fibrosis. Immunol Allergy Clin North Am. 2012;32(4):473-485. doi:10.1016/j.iac.2012.08.006
- A study evaluating the safety and efficacy of ENV-101 in subjects with idiopathic pulmonary fibrosis (IPF). ClinicalTrials.gov. Updated December 2, 2024. Accessed June 25, 2025. https://clinicaltrials.gov/study/NCT04968574
- Klein HE, Santoro C. Dr John Hood highlights advantages of IPF hedgehog inhibitor ENV-101. AJMC. June 13, 2024. Accessed June 25, 2025. https://www.ajmc.com/view/dr-john-hood-highlights-advantages-of-ipf-hedgehog-inhibitor-env-101