AI-powered CT imaging for early detection of subclinical pulmonary fibrosis in antisynthetase syndrome: a new era in autoimmune lung diagnostics

Antisynthetase syndrome (ASS), a rare autoimmune condition, often leads to subclinical pulmonary fibrosis (PF) that remains undetected until irreversible damage occurs. High-resolution computed tomography (HRCT) is pivotal in early PF detection, yet interpretation inconsistencies remain a challenge. Artificial intelligence (AI) and machine learning (ML) applications-such as multiple feature texture analysis, CALIPER, and deep learning segmentation tools-are revolutionizing lung imaging by minimizing observer variability, enhancing early diagnosis, and uncovering novel imaging biomarkers. While promising, the adoption of AI for rare disease diagnostics like ASS requires overcoming data limitations, bias, and validation hurdles. This letter calls for integrated genomic-imaging models, open-access repositories, and international data collaboration to effectively translate AI advancements into routine diagnostics for autoimmune lung disease.