Back to all papers

Artificial Intelligence-Aided Lung Ultrasound Detection of Interstitial Lung Disease in Systemic Sclerosis and Inflammatory Myopathy.

April 6, 2026pubmed logopapers

Authors

Fairchild RM,Deluna MD,Fazli M,Mar DA,Chung M,Davuluri S,Kawano Y,Guo H,Baker MC,Fiorentino D,Tamang S,Chung L

Affiliations (5)

  • Stanford University School of Medicine, Stanford, CA, USA.
  • Santa Clara Valley Medical Center, Santa Clara, CA, USA.
  • Kaiser Permanente, MD, USA.
  • Brigham and Women's Hospital, Harvard Medical School, Boston, MA.
  • Veterans Affairs Palo Alto Health Care System, Palo Alto, CA, USA.

Abstract

Lung ultrasound (LUS) is a sensitive, low-cost, and radiation-free modality for ILD detection. We previously developed and validated LUS interpretation criteria in systemic sclerosis (SSc) and idiopathic inflammatory myopathy (IIM) showing excellent diagnostic performance and correlations with ILD severity. In this study, we applied deep learning to evaluate whether convolutional neural networks (CNNs) can accurately detect ILD and its severity on LUS. Patients with SSc or IIM ± ILD, and paired LUS and chest computed tomography (CT) were included. LUS images were labeled using CT results and human LUS-ILD-24 interpretation. Three pretrained CNN architectures (InceptionV3, ResNet-50, VGG-16) were fine-tuned via transfer learning, and a de novo lightweight architecture (LUS-Net) was developed. Model performance for ILD detection was assessed at image and patient-levels using AUC, sensitivity, specificity, and agreement with expert interpretation. CNN outputs were correlated with pulmonary function tests (PFTs) and CT-based CALIPER indices. Grad-CAM visualized regions driving predictions. A total of 140 patients representing 3,920 LUS images were included and split into development (74) and independent test sets (66). VGG-16 achieved the best patient-level performance (AUC = 0.972; sensitivity = 97.4%; specificity = 92.6%) showing strong correlations with PFTs and CT severity. Grad-CAM highlighted pleural features as the primary regions influencing model predictions. CNN performance matched or exceeded LUS-ILD-24 interpretation. Deep learning applied to LUS enables accurate ILD detection in connective tissue disease and can enhance expert interpretation. Explainable AI suggests pleural features, even when B-lines are infrequent, are sufficient for reliable ILD recognition.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.