• Alex Bratt, James M Williams, Grace Liu, Ananya Panda, Parth P Patel, Lara Walkoff, Anne-Marie G Sykes, Yasmeen K Tandon, Christopher J Francois, Daniel J Blezek, Nicholas B Larson, Bradley J Erickson, Eunhee S Yi, Teng Moua, and Chi Wan Koo.
• Mayo Clinic, Rochester, MN. Electronic address: bratt.alexander@mayo.edu.
• Chest. 2022 Oct 1; 162 (4): 815823815-823.

BackgroundIdiopathic pulmonary fibrosis (IPF) is a progressive, often fatal form of interstitial lung disease (ILD) characterized by the absence of a known cause and usual interstitial pneumonitis (UIP) pattern on chest CT imaging and/or histopathology. Distinguishing UIP/IPF from other ILD subtypes is essential given different treatments and prognosis. Lung biopsy is necessary when noninvasive data are insufficient to render a confident diagnosis.Research QuestionCan we improve noninvasive diagnosis of UIP be improved by predicting ILD histopathology from CT scans by using deep learning?Study Design And MethodsThis study retrospectively identified a cohort of 1,239 patients in a multicenter database with pathologically proven ILD who had chest CT imaging. Each case was assigned a label based on histopathologic diagnosis (UIP or non-UIP). A custom deep learning model was trained to predict class labels from CT images (training set, n = 894) and was evaluated on a 198-patient test set. Separately, two subspecialty-trained radiologists manually labeled each CT scan in the test set according to the 2018 American Thoracic Society IPF guidelines. The performance of the model in predicting histopathologic class was compared against radiologists' performance by using area under the receiver-operating characteristic curve as the primary metric. Deep learning model reproducibility was compared against intra-rater and inter-rater radiologist reproducibility.ResultsFor the entire cohort, mean patient age was 62 ± 12 years, and 605 patients were female (49%). Deep learning performance was superior to visual analysis in predicting histopathologic diagnosis (area under the receiver-operating characteristic curve, 0.87 vs 0.80, respectively; P < .05). Deep learning model reproducibility was significantly greater than radiologist inter-rater and intra-rater reproducibility (95% CI for difference in Krippendorff's alpha did not include zero).InterpretationDeep learning may be superior to visual assessment in predicting UIP/IPF histopathology from CT imaging and may serve as an alternative to invasive lung biopsy.Copyright © 2022 American College of Chest Physicians. Published by Elsevier Inc. All rights reserved.

23 keywords...

hide…