Skip to main content

WE‐C‐AUD B‐05: Predicting Radiation‐Induced Cardiac Perfusion Defects Using a Fusion Model

Publication ,  Conference
Chen, S; Zhou, S; Hubbs, J; Wong, T; Borges‐neto, S; Yin, F; Marks, L; Das, S
Published in: Medical Physics
January 1, 2008

Purpose: To predict radiation‐induced cardiac perfusion defects using a fusion model that combines the results of four separate models: feed‐forward neural networks (NNET), self‐organizing maps (SOM), support vector machines (SVM), and multivariate adaptive regression splines (MARS). Method and Materials: The database comprised 111 patients with left‐sided breast treated with radiotherapy (56 diagnosed with cardiac perfusion defects post‐radiotherapy). The four independent models (NNET, SOM, SVM, and MARS) were constructed using a small number of independently selected features. The four models were then fused to a final model by averaging their patient predictions. Patient predictions were generated by testing the models using ten‐fold cross‐validation, wherein 1/10th of the data were tested, in turn, using models built with the remaining 9/10th of the data. To account for the variance in patient predictions caused by the effect of data splitting, 10‐fold cross validation was repeated 100 times with random data splitting. Results: For the fused model, the area under the Receiver Operating Characteristics (ROC) curve for cross‐validated testing was 0.890±0.012 (sensitivity = 80.6±1.7%, specificity = 80.2±1.7%). It was superior to the individual models (NNET: ROC = 0.764±0.015, sensitivity = 72.9±1.5%, specificity = 72.4±1.6%; SOM: ROC = 0.769±0.013, sensitivity = 73.0±1.4%, specificity = 72.2±1.5%; SVM: ROC = 0.900±0.048, sensitivity = 87.3±6.2%, specificity = 86.0±6.1%; MARS: ROC = 0.802±0.009, sensitivity = 76.1±1.1%, specificity = 75.6±1.1%) either in regard to higher predictive capability or lower variance. The fused model identified the following features as most important in predicting radiation‐induced perfusion defects: generalized equivalent uniform dose (EUD) with exponent a = 0.7, 1.0, and 3.6, and hypertension. Other features such as V46, V47, obesity, pack years, and chemotherapy played a less important role. Conclusion: The fused model provides promise for prospectively predicting radiation‐induced cardiac perfusion defects with high accuracy and confidence (low variance). © 2008, American Association of Physicists in Medicine. All rights reserved.

Duke Scholars

Published In

Medical Physics

DOI

ISSN

0094-2405

Publication Date

January 1, 2008

Volume

35

Issue

6

Start / End Page

2934

Related Subject Headings

  • Nuclear Medicine & Medical Imaging
  • 5105 Medical and biological physics
  • 4003 Biomedical engineering
  • 1112 Oncology and Carcinogenesis
  • 0903 Biomedical Engineering
  • 0299 Other Physical Sciences
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Chen, S., Zhou, S., Hubbs, J., Wong, T., Borges‐neto, S., Yin, F., … Das, S. (2008). WE‐C‐AUD B‐05: Predicting Radiation‐Induced Cardiac Perfusion Defects Using a Fusion Model. In Medical Physics (Vol. 35, p. 2934). https://doi.org/10.1118/1.2962692
Chen, S., S. Zhou, J. Hubbs, T. Wong, S. Borges‐neto, F. Yin, L. Marks, and S. Das. “WE‐C‐AUD B‐05: Predicting Radiation‐Induced Cardiac Perfusion Defects Using a Fusion Model.” In Medical Physics, 35:2934, 2008. https://doi.org/10.1118/1.2962692.
Chen S, Zhou S, Hubbs J, Wong T, Borges‐neto S, Yin F, et al. WE‐C‐AUD B‐05: Predicting Radiation‐Induced Cardiac Perfusion Defects Using a Fusion Model. In: Medical Physics. 2008. p. 2934.
Chen, S., et al. “WE‐C‐AUD B‐05: Predicting Radiation‐Induced Cardiac Perfusion Defects Using a Fusion Model.” Medical Physics, vol. 35, no. 6, 2008, p. 2934. Scopus, doi:10.1118/1.2962692.
Chen S, Zhou S, Hubbs J, Wong T, Borges‐neto S, Yin F, Marks L, Das S. WE‐C‐AUD B‐05: Predicting Radiation‐Induced Cardiac Perfusion Defects Using a Fusion Model. Medical Physics. 2008. p. 2934.

Published In

Medical Physics

DOI

ISSN

0094-2405

Publication Date

January 1, 2008

Volume

35

Issue

6

Start / End Page

2934

Related Subject Headings

  • Nuclear Medicine & Medical Imaging
  • 5105 Medical and biological physics
  • 4003 Biomedical engineering
  • 1112 Oncology and Carcinogenesis
  • 0903 Biomedical Engineering
  • 0299 Other Physical Sciences