[Paper Review] Deep Learning-Based Airway Segmentation in Systemic Lupus Erythematosus Patients with Interstitial Lung Disease (SLE-ILD): A Comparative High-Resolution CT Analysis

Sirong Piao, Ying Ming+12 more|arXiv (Cornell University)|Mar 18, 2026

Systemic Lupus Erythematosus Research0 citations

TL;DR

The study develops a deep learning (U-Net) based automatic airway segmentation framework on non-contrast HRCT to compare airway volumes between SLE patients with ILD and without ILD, revealing region-specific airway dilation in SLE-ILD. Significant upper-lobe and certain segmental airway enlargements were found in SLE-ILD vs non-ILD.

ABSTRACT

To characterize lobar and segmental airway volume differences between systemic lupus erythematosus (SLE) patients with interstitial lung disease (ILD) and those without ILD (non-ILD) using a deep learning-based approach on non-contrast chest high-resolution CT (HRCT). Methods: A retrospective analysis was conducted on 106 SLE patients (27 SLE-ILD, 79 SLE-non-ILD) who underwent HRCT. A customized deep learning framework based on the U-Net architecture was developed to automatically segment airway structures at the lobar and segmental levels via HRCT. Volumetric measurements of lung lobes and segments derived from the segmentations were statistically compared between the two groups using two-sample t-tests (significance threshold: p < 0.05). Results: At lobar level, significant airway volume enlargement in SLE-ILD patients was observed in the right upper lobe (p=0.009) and left upper lobe (p=0.039) compared to SLE-non-ILD. At the segmental level, significant differences were found in segments including R1 (p=0.016), R3 (p<0.001), and L3 (p=0.038), with the most marked changes in the upper lung zones, while lower zones showed non-significant trends. Conclusion: Our study demonstrates that an automated deep learning-based approach can effectively quantify airway volumes on HRCT scans and reveal significant, region-specific airway dilation in patients with SLE-ILD compared to those without ILD. The pattern of involvement, predominantly affecting the upper lobes and specific segments, highlights a distinct topographic phenotype of SLE-ILD and implicates airway structural alterations as a potential biomarker for disease presence. This AI-powered quantitative imaging biomarker holds promise for enhancing the early detection and monitoring of ILD in the SLE population, ultimately contributing to more personalized patient management.

Motivation & Objective

• Characterize lobar and segmental airway volume differences between SLE-ILD and SLE-non-ILD using automated HRCT-based segmentation.
• Develop a U-Net based framework to automatically segment airway structures at lobar and segmental levels.
• Quantify volumetric lung airway measurements and compare between patient groups using statistical tests.

Proposed method

• Retrospective analysis of 106 SLE patients (27 SLE-ILD, 79 SLE-non-ILD) with non-contrast HRCT.
• A customized deep learning framework based on U-Net automatically segments airway structures at lobar and segmental levels.
• Derivation of volumetric measurements from segmentations and comparison between groups via two-sample t-tests (p<0.05).
• Statistical focus on regional differences, particularly upper lobes and specific segments.

Experimental results

Research questions

• RQ1 Do SLE-ILD patients show different lobar airway volumes compared to SLE-non-ILD patients on HRCT?
• RQ2 Are there segmental-level airway differences that distinguish SLE-ILD from non-ILD, and where are they most pronounced?
• RQ3 Can a DL-based airway segmentation approach reliably quantify regional airway dilation as a potential biomarker for ILD presence in SLE?

Key findings

• Significant lobar airway enlargement in SLE-ILD for the right upper lobe (p=0.009) and left upper lobe (p=0.039) versus SLE-non-ILD.
• Significant segmental differences in R1 (p=0.016), R3 (p<0.001), and L3 (p=0.038), with the most pronounced changes in the upper lung zones.
• Lower lung zones showed non-significant trends in airway differences between groups.
• Automated DL-based airway segmentation effectively quantifies airway volumes on HRCT and detects region-specific changes.
• The results suggest a distinct topographic phenotype of SLE-ILD and potential airway-based biomarker for disease presence.