Comparison of breast DCE-MRI contrast time points for predicting response to neoadjuvant chemotherapy using deep convolutional neural network features with transfer learning
| Autor: | Natasha Antropova, Benjamin Q. Huynh, Maryellen L. Giger |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Artificial neural network
business.industry Computer science Deep learning Pattern recognition 02 engineering and technology Machine learning computer.software_genre medicine.disease Linear discriminant analysis Convolutional neural network Cross-validation 030218 nuclear medicine & medical imaging 03 medical and health sciences 0302 clinical medicine Breast cancer 0202 electrical engineering electronic engineering information engineering medicine 020201 artificial intelligence & image processing Artificial intelligence business Transfer of learning computer |
| Zdroj: | Medical Imaging: Computer-Aided Diagnosis |
| ISSN: | 0277-786X |
| Popis: | DCE-MRI datasets have a temporal aspect to them, resulting in multiple regions of interest (ROIs) per subject, based on contrast time points. It is unclear how the different contrast time points vary in terms of usefulness for computer-aided diagnosis tasks in conjunction with deep learning methods. We thus sought to compare the different DCE-MRI contrast time points with regard to how well their extracted features predict response to neoadjuvant chemotherapy within a deep convolutional neural network. Our dataset consisted of 561 ROIs from 64 subjects. Each subject was categorized as a non-responder or responder, determined by recurrence-free survival. First, features were extracted from each ROI using a convolutional neural network (CNN) pre-trained on non-medical images. Linear discriminant analysis classifiers were then trained on varying subsets of these features, based on their contrast time points of origin. Leave-one-out cross validation (by subject) was used to assess performance in the task of estimating probability of response to therapy, with area under the ROC curve (AUC) as the metric. The classifier trained on features from strictly the pre-contrast time point performed the best, with an AUC of 0.85 (SD = 0.033). The remaining classifiers resulted in AUCs ranging from 0.71 (SD = 0.028) to 0.82 (SD = 0.027). Overall, we found the pre-contrast time point to be the most effective at predicting response to therapy and that including additional contrast time points moderately reduces variance. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|