Logo image
Multi-View Cnn For Total Lung Volume Inference On Cardiac Computed Tomography
Conference proceeding   Open access

Multi-View Cnn For Total Lung Volume Inference On Cardiac Computed Tomography

Artur Wysoczanski, Elsa D. Angelini, Yifei Sun, Benjamin M. Smith, Eric A. Hoffman, Karen Stukovsky, Matthew Budoff, Karol E. Watson, John Jeffrey Carr, Elizabeth C. Oelsner, …
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), pp.1-5
04/18/2023
DOI: 10.1109/ISBI53787.2023.10230821
url
https://pmc.ncbi.nlm.nih.gov/articles/PMC11479650/pdf/nihms-2027025.pdfView
Open Access

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.
Computed Tomography CNN Lung volume

Details

Metrics

19 Record Views
Logo image