Preprint
Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies
arXiv.org
Cornell University
03/01/2024
DOI: 10.48550/arxiv.2403.00257
Abstract
Pulmonary emphysema, the progressive, irreversible loss of lung tissue, is conventionally categorized into three subtypes identifiable on pathology and on lung computed tomography (CT) images. Recent work has led to the unsupervised learning of ten spatially-informed lung texture patterns (sLTPs) on lung CT, representing distinct patterns of emphysematous lung parenchyma based on both textural appearance and spatial location within the lung, and which aggregate into 6 robust and reproducible CT Emphysema Subtypes (CTES). Existing methods for sLTP segmentation, however, are slow and highly sensitive to changes in CT acquisition protocol. In this work, we present a robust 3-D squeeze-and-excitation CNN for supervised classification of sLTPs and CTES on lung CT. Our results demonstrate that this model achieves accurate and reproducible sLTP segmentation on lung CTscans, across two independent cohorts and independently of scanner manufacturer and model.
Details
- Title: Subtitle
- Robust deep labeling of radiological emphysema subtypes using squeeze and excitation convolutional neural networks: The MESA Lung and SPIROMICS Studies
- Creators
- Artur WysoczanskiNabil EttehadiSoroush ArabshahiYifei SunKaren Hinckley StukovskyKarol E WatsonMeiLan K HanErin D MichosAlejandro P ComellasEric A HoffmanAndrew F LaineR. Graham BarrElsa D Angelini
- Resource Type
- Preprint
- Publication Details
- arXiv.org
- DOI
- 10.48550/arxiv.2403.00257
- eISSN
- 2331-8422
- Publisher
- Cornell University; Ithaca, New York
- Language
- English
- Date posted
- 03/01/2024
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Pulmonary, Critical Care, and Occupational Medicine; ICTS; Internal Medicine
- Record Identifier
- 9984568048402771
Metrics
52 Record Views