Journal article
Predicting Usual Interstitial Pneumonia Histopathology From Chest CT Imaging With Deep Learning
Chest, Vol.162(4), pp.815-823
10/2022
DOI: 10.1016/j.chest.2022.03.044
PMID: 35405110
Abstract
Idiopathic 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.
Can we improve noninvasive diagnosis of UIP be improved by predicting ILD histopathology from CT scans by using deep learning?
This 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.
For 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).
Deep 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.
Details
- Title: Subtitle
- Predicting Usual Interstitial Pneumonia Histopathology From Chest CT Imaging With Deep Learning
- Creators
- Alex Bratt - Mayo Clinic in ArizonaJames M Williams - Mayo Clinic in ArizonaGrace Liu - Mayo Clinic in ArizonaAnanya Panda - Mayo Clinic in ArizonaParth P Patel - Mayo Clinic in ArizonaLara Walkoff - Mayo Clinic in ArizonaAnne-Marie G Sykes - Mayo Clinic in ArizonaYasmeen K Tandon - Mayo Clinic in ArizonaChristopher J Francois - Mayo Clinic in ArizonaDaniel J Blezek - Mayo Clinic in ArizonaNicholas B Larson - Mayo Clinic in ArizonaBradley J Erickson - Mayo Clinic in ArizonaEunhee S Yi - Mayo Clinic in ArizonaTeng Moua - Mayo Clinic in ArizonaChi Wan Koo - Mayo Clinic in Arizona
- Resource Type
- Journal article
- Publication Details
- Chest, Vol.162(4), pp.815-823
- Publisher
- ELSEVIER; AMSTERDAM
- DOI
- 10.1016/j.chest.2022.03.044
- PMID
- 35405110
- ISSN
- 0012-3692
- eISSN
- 1931-3543
- Grant note
This study was funded by Mayo Clinic Internal Research Support.
- Language
- English
- Date published
- 10/2022
- Academic Unit
- Radiology
- Record Identifier
- 9984697637002771
Metrics
5 Record Views