Conference proceeding
Estimating Local Tissue Expansion in Thoracic Computed Tomography Images Using Convolutional Neural Networks
2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Vol.2020-, pp.1856-1860
04/2020
DOI: 10.1109/ISBI45749.2020.9098413
Abstract
Registration of lungs in thoracic computed tomography (CT) images produces a dense correspondence which can be analyzed to estimate local tissue expansion. However, the validity of this local expansion estimate is dependent on the accuracy of the image registration. In this work, a convolutional neural network (CNN) model is used to directly estimate the local tissue expansion between lungs imaged at two lung volumes, without requiring image registration. The network was trained with 5705 subjects from COPDGene with varying degrees of disease severity. The CNN-based model was evaluated with 3046 subjects from COPDGene. At the global scale, the mean lung expansion estimated from the CNN-based and registration-based models were highly correlated ( r_{s}=0.945 ). At the local scale, the proposed method achieved a voxelwise Spearman correlation of 0.871\pm 0.080 . At the regional scale, Dice coefficient for low- and high-functioning regions was 0.805\pm 0.066 and 0.806\pm 0.065 , respectively. The results indicate the CNN-based model was able to reproduce image registration derived tissue expansion images without explicitly estimating the correspondence.
Details
- Title: Subtitle
- Estimating Local Tissue Expansion in Thoracic Computed Tomography Images Using Convolutional Neural Networks
- Creators
- Sarah E Gerard - Brigham and Women's HospitalJoseph M Reinhardt - University of IowaGary E Christensen - University of IowaRaul San Jose Estepar - Brigham and Women's Hospital
- Resource Type
- Conference proceeding
- Publication Details
- 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Vol.2020-, pp.1856-1860
- Publisher
- IEEE
- DOI
- 10.1109/ISBI45749.2020.9098413
- ISSN
- 1945-7928
- eISSN
- 1945-8452
- Language
- English
- Date published
- 04/2020
- Academic Unit
- Radiation Research Laboratory; The Iowa Institute for Biomedical Imaging; Electrical and Computer Engineering; Roy J. Carver Department of Biomedical Engineering; Advanced Pulmonary Physiomic Imaging Laboratory; Radiology; Iowa Technology Institute; Radiation Oncology; Holden Comprehensive Cancer Center
- Record Identifier
- 9984196973802771
Metrics
37 Record Views