We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Deep Learning Classification of Usual Interstitial Pneumonia Predicts Outcomes.
- Authors
Humphries, Stephen M.; Thieke, Devlin; Baraghoshi, David; Strand, Matthew J.; Swigris, Jeffrey J.; Chae, Kum Ju; Hwang, Hye Jeon; Oh, Andrea S.; Flaherty, Kevin R.; Adegunsoye, Ayodeji; Jablonski, Renea; Lee, Cathryn T.; Husain, Aliya N.; Chung, Jonathan H.; Strek, Mary E.; Lynch, David A.
- Abstract
Rationale: Computed tomography (CT) enables noninvasive diagnosis of usual interstitial pneumonia (UIP), but enhanced image analyses are needed to overcome the limitations of visual assessment. Objectives: Apply multiple instance learning (MIL) to develop an explainable deep learning algorithm for prediction of UIP from CT and validate its performance in independent cohorts. Methods: We trained an MIL algorithm using a pooled dataset (n = 2,143) and tested it in three independent populations: data from a prior publication (n = 127), a single-institution clinical cohort (n = 239), and a national registry of patients with pulmonary fibrosis (n = 979). We tested UIP classification performance using receiver operating characteristic analysis, with histologic UIP as ground truth. Cox proportional hazards and linear mixed-effects models were used to examine associations between MIL predictions and survival or longitudinal FVC. Measurements and Main Results: In two cohorts with biopsy data, MIL improved accuracy for histologic UIP (area under the curve, 0.77 [n = 127] and 0.79 [n = 239]) compared with visual assessment (area under the curve, 0.65 and 0.71). In cohorts with survival data, MIL-UIP classifications were significant for mortality (n = 239, mortality to April 2021: unadjusted hazard ratio, 3.1; 95% confidence interval [CI], 1.96–4.91; P < 0.001; and n = 979, mortality to July 2022: unadjusted hazard ratio, 3.64; 95% CI, 2.66–4.97; P < 0.001). Individuals classified as UIP positive by the algorithm had a significantly greater annual decline in FVC than those classified as UIP negative (−88 ml/yr vs. −45 ml/yr; n = 979; P < 0.01), adjusting for extent of lung fibrosis. Conclusions: Computerized assessment using MIL identifies clinically significant features of UIP on CT. Such a method could improve confidence in radiologic assessment of patients with interstitial lung disease, potentially enabling earlier and more precise diagnosis.
- Subjects
IDIOPATHIC pulmonary fibrosis; DEEP learning; MACHINE learning; INTERSTITIAL lung diseases; PULMONARY fibrosis; RECEIVER operating characteristic curves; NONINVASIVE diagnostic tests; DICOM (Computer network protocol)
- Publication
American Journal of Respiratory & Critical Care Medicine, 2024, Vol 209, Issue 9, p1121
- ISSN
1073-449X
- Publication type
Article
- DOI
10.1164/rccm.202307-1191OC