VanderLaan, Paul A.

Abstract Introduction: Endobronchial optical coherence tomography (EB-OCT) imaging has unique potential to diagnose and quantify early, microscopic disease changes and assess therapeutic responsivity in interstitial lung disease (ILD). However, training and time requirements for interpretation and quantitative evaluation of large volumetric EB-OCT datasets need to be optimized to facilitate clinical adoption. We develop and validate a computationally-efficient, rapid EB-OCT quantitative image analysis framework using artificial intelligence (AI) with deep learning architecture for 2D feature segmentation, 3D feature burden and spatial distribution mapping, and computer-aided diagnosis in early ILD subjects. Methods: Volumetric EB-OCT datasets, consisting of 2D cross-sectional images, were acquired from multiple locations in the bilateral lungs of ILD and healthy control subjects. EB-OCT features were manually segmented from cross-sectional images by an expert EB-OCT reader, including fibrosis, microscopic honeycombing, traction bronchiolectasis, normal parenchyma, and emphysema. EB-OCT images with corresponding feature segmentations were used to train and validate a multiclass convolutional neural network. The 2D AI-based segmentation model was subsequently evaluated against manual ‘ground truth’ segmentations for each feature in a de novo ‘test’ dataset of independent subjects using dice similarity score, precision, recall/sensitivity, specificity, and balanced accuracy. To generate 3D AI-based quantitative feature burden and spatial distribution maps, AI-based feature segmentation was performed on each EB-OCT 2D cross-sectional image within a volumetric imaging site. Three external pathologist readers independently interpreted 3D AI-based features maps for each EB-OCT imaging site acquired for a subject (without access to EB-OCT images) and provided a single diagnosis of usual interstitial pneumonia (UIP) or non-UIP ILD. Performance of computer-aided ILD diagnosis was compared against independently evaluated histopathology, clinical diagnosis, and prior EB-OCT image interpretation. Results: EB-OCT was acquired in 51 subjects: 30 in vivo early ILD, 5 in vivo non-ILD controls, and 16 ex vivo end-stage ILD. Overall pixel similarity between 2D manual and AI-based segmentation demonstrated high accuracy for each ILD feature (mean balanced accuracy 0.9). 3D quantitative AI-based feature maps demonstrated strong agreement (Spearman ρ0.87, p<0.001) between manual and AI-based segmentation. AI-based computer-aided diagnosis demonstrated 100% sensitivity/specificity for histologic UIP and clinical IPF for all pathologist readers, with improved diagnostic accuracy and significantly reduced training (45-minute training, 75% reduction) and interpretation time (<1 minute per subject for computer-aided diagnosis, 88% reduction) compared to EB-OCT image interpretation. Conclusion: The AI-based EB-OCT image analysis framework could expedite computer-aided diagnosis of early ILD and robust, quantitative assessment of microscopic disease burden, progression, and therapeutic responsivity.

Abstract Rationale Early, accurate diagnosis of interstitial lung disease (ILD) informs prognosis and therapy, especially in idiopathic pulmonary fibrosis (IPF). Current diagnostic methods are imperfect. High-resolution computed tomography has limited resolution, and surgical lung biopsy (SLB) carries risks of morbidity and mortality. Endobronchial optical coherence tomography (EB-OCT) is a low-risk, bronchoscope-compatible modality that images large lung volumes in vivo with microscopic resolution, including subpleural lung, and has the potential to improve the diagnostic accuracy of bronchoscopy for ILD diagnosis. Objectives We performed a prospective diagnostic accuracy study of EB-OCT in patients with ILD with a low-confidence diagnosis undergoing SLB. The primary endpoints were EB-OCT sensitivity/specificity for diagnosis of the histopathologic pattern of usual interstitial pneumonia (UIP) and clinical IPF. The secondary endpoint was agreement between EB-OCT and SLB for diagnosis of the ILD fibrosis pattern. Methods EB-OCT was performed immediately before SLB. The resulting EB-OCT images and histopathology were interpreted by blinded, independent pathologists. Clinical diagnosis was obtained from the treating pulmonologists after SLB, blinded to EB-OCT. Measurements and Main Results We enrolled 31 patients, and 4 were excluded because of inconclusive histopathology or lack of EB-OCT data. Twenty-seven patients were included in the analysis (16 men, average age: 65.0 yr): 12 were diagnosed with UIP and 15 with non-UIP ILD. Average FVC and Dl CO were 75.3% (SD, 18.5) and 53.5% (SD, 16.4), respectively. Sensitivity and specificity of EB-OCT was 100% (95% confidence interval, 75.8–100.0%) and 100% (79.6–100%), respectively, for both histopathologic UIP and clinical diagnosis of IPF. There was high agreement between EB-OCT and histopathology for diagnosis of ILD fibrosis pattern (weighted κ: 0.87 [0.72–1.0]). Conclusions EB-OCT is a safe, accurate method for microscopic ILD diagnosis, as a complement to high-resolution computed tomography and an alternative to SLB.