Conference proceeding
Multi-View Cnn For Total Lung Volume Inference On Cardiac Computed Tomography
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.1-5
04/18/2023
DOI: 10.1109/ISBI53787.2023.10230821
Abstract
Total lung volume (TLV) at full inspiration is a parameter of significant interest in pulmonary physiology but requires computed tomography (CT) scanning of the full axial extent of the lung. There is a growing interest to infer TLV from cardiac CT scans, which are much more widely available in epidemiologic studies. In this study, we present an original approach to train a multi-view convolutional neural network (CNN) model to infer TLV from cardiac CT scans, which visualize about 2/3rd of the lung volume. Supervised learning is used, exploiting paired full-lung and cardiac CT scans in the Multi-Ethnic Study of Atherosclerosis (MESA). Our results show that our network outperforms existing regression models for TLV estimation, and achieves accuracy and reproducibility comparable to the scan-rescan reproducibility of TLV on full-lung CT.
Details
- Title: Subtitle
- Multi-View Cnn For Total Lung Volume Inference On Cardiac Computed Tomography
- Creators
- Artur Wysoczanski - Columbia UniversityElsa D. Angelini - Columbia UniversityYifei Sun - Columbia UniversityBenjamin M. Smith - Columbia UniversityEric A. Hoffman - University of IowaKaren Stukovsky - University of WashingtonMatthew Budoff - Harbor–UCLA Medical CenterKarol E. Watson - David Geffen School of Medicine,Division of Cardiovascular Medicine,Los Angeles,CA,USAJohn Jeffrey Carr - Vanderbilt University School of MedicineElizabeth C. Oelsner - Columbia UniversityR Graham Barr - Columbia UniversityAndrew F. Laine - Columbia University
- Resource Type
- Conference proceeding
- Publication Details
- 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.1-5
- DOI
- 10.1109/ISBI53787.2023.10230821
- eISSN
- 1945-8452
- Publisher
- IEEE
- Grant note
- American Lung Association (10.13039/100002590)
- Language
- English
- Date published
- 04/18/2023
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Internal Medicine
- Record Identifier
- 9984461350202771
Metrics
19 Record Views