Radiomics Analysis of CT Scans Enhances Evaluation of Sarcoidosis

Clinicians often rely on visual review of chest computed tomography (CT) to assess pulmonary involvement, but interpretations can vary. This variability makes it hard to stratify risk and monitor progression consistently. A new study shows that advanced, computer-based CT analysis can distinguish forms of sarcoidosis to support more objective evaluation.

Researchers at National Jewish Health (Denver, CO, USA) and collaborators evaluated radiomics, a quantitative imaging approach applied to chest CT, to profile lung involvement in sarcoidosis. The method uses algorithms to extract large numbers of image features that reflect parenchymal texture and distribution of abnormalities. By moving beyond subjective visual reads, the approach aims to standardize image interpretation across centers and time points.

The team analyzed prior high-resolution CT scans from 320 individuals with sarcoidosis enrolled in the Genomic Research in Alpha-1 Antitrypsin Deficiency and Sarcoidosis (GRADS) Study, one of the largest sarcoidosis cohorts in the United States. Using machine-learning clustering, investigators identified four distinct imaging profiles that captured heterogeneity ranging from relatively limited changes to patterns consistent with more extensive inflammation or fibrosis. These radiomic groups were linked to differences in lung function and disease severity. The associations persisted even after accounting for traditional imaging assessments commonly used in clinical practice.

According to the report, the analysis can be performed quickly and automatically with open‑source software, which could enable large‑scale application in busy clinics. The study, published in Scientific Reports, highlights how radiomics may complement radiologist expertise by quantifying subtle, reproducible patterns that are difficult to discern visually. The authors note that additional studies are needed to determine how radiomics might be integrated into routine care for diagnosis, subtype identification, and longitudinal monitoring.

“Radiomics has the potential to complement the expertise of radiologists by providing objective measurements of lung abnormalities, identifying disease subtypes, monitoring progression and potentially guiding more personalized treatment strategies,” said Tasha Fingerlin, Ph.D., vice chair of the Department of Immunology and Genomic Medicine at National Jewish Health and co-senior author of the study.

“There is promise for significant impact on patient care, especially in regions where there is no expert in sarcoidosis radiology, which is much of the country and certainly most areas in the Far West. Radiomics could also expedite care in clinics with rapid turnaround for patients at specialized centers and revolutionize the way we interpret CT scans for research and clinical trials,” said Lisa Maier, MD, head of the World Association of Sarcoidosis and Granulomatous Disease (WASOG) Sarcoidosis Center of Excellence at National Jewish Health and co-senior author of the study.

Related Links
National Jewish Health