TY - JOUR
T1 - WE‐C‐AUD B‐05
T2 - Predicting Radiation‐Induced Cardiac Perfusion Defects Using a Fusion Model
AU - Chen, S.
AU - Zhou, S.
AU - Hubbs, J.
AU - Wong, T.
AU - Borges‐neto, S.
AU - Yin, F.
AU - Marks, L.
AU - Das, S.
N1 - Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2008/6
Y1 - 2008/6
N2 - 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).
AB - 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).
UR - http://www.scopus.com/inward/record.url?scp=85024806256&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85024806256&partnerID=8YFLogxK
U2 - 10.1118/1.2962692
DO - 10.1118/1.2962692
M3 - Article
AN - SCOPUS:85024806256
SN - 0094-2405
VL - 35
SP - 2934
JO - Medical physics
JF - Medical physics
IS - 6
ER -