Journal article
Predicting pulmonary ventilation damage after radiation therapy for Non-Small cell lung cancer using a ResNet generative adversarial network
Medical physics (Lancaster), Vol.50(5), pp.3199-3209
05/2023
DOI: 10.1002/mp.16311
PMID: 36779695
Abstract
Functional lung avoidance radiation therapy (RT) is a technique being investigated to preferentially avoid specific regions of the lung that are predicted to be more susceptible to radiation-induced damage. Reducing the dose delivered to high functioning regions may reduce the occurrence radiation-induced lung injuries and toxicities. However, in order to develop effective lung function-sparing plans, accurate predictions of post-RT ventilation change are needed to determine which regions of the lung should be spared.
To predict pulmonary ventilation change following radiation therapy (RT) for non-small cell lung cancer using machine learning.
A conditional generative adversarial network (cGAN) was developed with data from 82 human subjects enrolled in a randomized clinical trial approved by the institution's IRB to predict post-RT pulmonary ventilation change. The inputs to the network were the pre-RT pulmonary ventilation map and radiation dose distribution. The loss function was a combination of the binary cross-entropy loss and an asymmetrical structural similarity index measure (aSSIM) function designed to increase penalization of under-prediction of ventilation damage. Network performance was evaluated against a previously developed polynomial regression model using a paired sample t-test for comparison. Evaluation was performed using 8-fold cross-validation.
From the 8-fold cross-validation we found that relative to the polynomial model, the cGAN model significantly improved predicting regions of ventilation damage following radiotherapy based on true positive rate (TPR), 0.14±0.15 to 0.72±0.21, and Dice similarity coefficient (DSC), 0.19±0.16 to 0.46±0.14, but significantly declined in true negative rate, 0.97±0.05 to 0.62±0.21, and accuracy, 0.79±0.08 to 0.65±0.14. Additionally, the average true positive volume increased from 104±119 cc in the POLY model to 565±332 cc in the cGAN model, and the average false negative volume decreased from 654±361 cc in the POLY model to 193±163 cc in the cGAN model.
The proposed cGAN model demonstrated significant improvement in TPR and DSC. The higher sensitivity of the cGAN model can improve the clinical utility of functional lung avoidance RT by identifying larger volumes of functional lung that can be spared and thus decrease the probability of the patient developing radiation-induced lung injuries. This article is protected by copyright. All rights reserved.
Details
- Title: Subtitle
- Predicting pulmonary ventilation damage after radiation therapy for Non-Small cell lung cancer using a ResNet generative adversarial network
- Creators
- Eric M Wallat - University of Wisconsin–MadisonAntonia E Wuschner - University of Wisconsin–MadisonMattison J Flakus - University of Wisconsin–MadisonSarah E Gerard - University of IowaGary E Christensen - University of IowaJoseph M Reinhardt - University of IowaJohn E Bayouth - Oregon Health & Science University
- Resource Type
- Journal article
- Publication Details
- Medical physics (Lancaster), Vol.50(5), pp.3199-3209
- DOI
- 10.1002/mp.16311
- PMID
- 36779695
- NLM abbreviation
- Med Phys
- eISSN
- 2473-4209
- Grant note
- DOI: 10.13039/100000054, name: National Cancer Institute, award: R01CA166703
- Language
- English
- Electronic publication date
- 02/13/2023
- Date published
- 05/2023
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Radiology; Electrical and Computer Engineering; Radiation Oncology; Radiation Research Laboratory; The Iowa Institute for Biomedical Imaging; Advanced Pulmonary Physiomic Imaging Laboratory; Holden Comprehensive Cancer Center
- Record Identifier
- 9984366233602771
Metrics
39 Record Views