Automated diagnosis of usual interstitial pneumonia on chest CT via the mean curvature of isophotes.
Authors
Affiliations (13)
Affiliations (13)
- School of Computer Science, McGill University, Montreal, QC, Canada.
- Centre for Intelligent Machines, McGill University, Montreal, QC, Canada.
- Rosalind & Morris Goodman Cancer Institute, McGill University, Montreal, QC, Canada.
- Department of Epidemiology, Biostatistics and Occupational Health, McGill University, Montreal, QC, Canada.
- 5 Prime Sciences, Montreal, QC, Canada.
- Department of Radiology, Radiation Oncology and Nuclear Medicine, Université de Montréal, Montreal, QC, Canada.
- Department of Radiology, Centre Hospitalier de l'Université de Montréal (CHUM), Montreal, QC, Canada.
- Centre d'intégration et d'analyse des données médicales (CITADEL), Centre Hospitalier de l'Université de Montréal (CHUM), Montreal, QC, Canada.
- Department of Medicine, McGill University, Montreal, QC, Canada.
- Research Institute, McGill University Health Center, Montreal, QC, Canada.
- Montreal Chest Institute, McGill University Health Center, Montreal, QC, Canada.
- Lakeshore General Hospital, Pointe-Claire, QC, Canada.
- Department of Diagnostic Radiology, McGill University, Montreal, QC, Canada.
Abstract
To test whether the mean curvature of isophotes (MCI), a geometric image transformation, can be used to improve automatic detection on chest CT of Usual Interstitial Pneumonia (UIP), a determining radiological pattern in the diagnosis of Interstitial Lung Diseases (ILD). This retrospective study included chest CT scans from 234 patients (123 female,111 male; mean age: 61.6 years; age range: 18-90 years) obtained at two independent institutions between 2007 and 2024.Three different classification models were trained on the original CT images and separately on MCI-transformed CT images: (1) a previously published deep learning model for classifying fibrotic lung disease on chest CT, (2) a classification pipeline based on the EfficientNet-V2 convolutional neural network architecture, and (3) a non-deep-learning model based on the functional principal component analysis (FPCA) of density functions of voxel intensity.All models were trained on data from the first institution and evaluated on data from the second institution with the recall-macro, precision-macro and F1-macro scores. Performance difference between classifier pairs was tested with the Stuart-Maxwell marginal homogeneity test. For a fixed model architecture and training algorithm, MCI-transformed images yield comparable or better classification performance than the original CT images. The best performance improvement achieved with MCI compared to CT was: recall-macro 0.83 vs 0.57, precision-macro 0.81 vs 0.50, F1-macro 0.80 vs 0.49, p = 4.2e-5. MCI may be a valuable addition to existing AI systems for screening for UIP on chest CT.