Zhe Zhu1, Ehab Albadawy2, Ashirbani Saha3, Jun Zhang4, Michael R Harowicz5, Maciej A Mazurowski6. 1. Department of Radiology, Duke University, USA. Electronic address: zhe.zhu@duke.edu. 2. Department of Radiology, Duke University, USA. Electronic address: ehalbadawy93@gmail.com. 3. Department of Radiology, Duke University, USA. Electronic address: as698@duke.edu. 4. Department of Radiology, Duke University, USA. Electronic address: xdzhangjun@gmail.com. 5. Department of Radiology, Duke University, USA. Electronic address: michael.harowicz@gmail.com. 6. Department of Radiology and Department of Electrical and Computer Engineering, Duke University, USA. Electronic address: maciej.mazurowski@duke.edu.
Abstract
RATIONALE AND OBJECTIVES: To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS: In this institutional review board-approved single-center study, we analyzed DCE-MR images of 270 patients at our institution. Lesions of interest were identified by radiologists. The task was to automatically determine whether the tumor is of the Luminal A subtype or of another subtype based on the MR image patches representing the tumor. Three different deep learning approaches were used to classify the tumor according to their molecular subtypes: learning from scratch where only tumor patches were used for training, transfer learning where networks pre-trained on natural images were fine-tuned using tumor patches, and off-the-shelf deep features where the features extracted by neural networks trained on natural images were used for classification with a support vector machine. Network architectures utilized in our experiments were GoogleNet, VGG, and CIFAR. We used 10-fold crossvalidation method for validation and area under the receiver operating characteristic (AUC) as the measure of performance. RESULTS: The best AUC performance for distinguishing molecular subtypes was 0.65 (95% CI:[0.57,0.71]) and was achieved by the off-the-shelf deep features approach. The highest AUC performance for training from scratch was 0.58 (95% CI:[0.51,0.64]) and the best AUC performance for transfer learning was 0.60 (95% CI:[0.52,0.65]) respectively. For the off-the-shelf approach, the features extracted from the fully connected layer performed the best. CONCLUSION: Deep learning may play a role in discovering radiogenomic associations in breast cancer.
RATIONALE AND OBJECTIVES: To determine whether deep learning models can distinguish between breast cancer molecular subtypes based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). MATERIALS AND METHODS: In this institutional review board-approved single-center study, we analyzed DCE-MR images of 270 patients at our institution. Lesions of interest were identified by radiologists. The task was to automatically determine whether the tumor is of the Luminal A subtype or of another subtype based on the MR image patches representing the tumor. Three different deep learning approaches were used to classify the tumor according to their molecular subtypes: learning from scratch where only tumor patches were used for training, transfer learning where networks pre-trained on natural images were fine-tuned using tumor patches, and off-the-shelf deep features where the features extracted by neural networks trained on natural images were used for classification with a support vector machine. Network architectures utilized in our experiments were GoogleNet, VGG, and CIFAR. We used 10-fold crossvalidation method for validation and area under the receiver operating characteristic (AUC) as the measure of performance. RESULTS: The best AUC performance for distinguishing molecular subtypes was 0.65 (95% CI:[0.57,0.71]) and was achieved by the off-the-shelf deep features approach. The highest AUC performance for training from scratch was 0.58 (95% CI:[0.51,0.64]) and the best AUC performance for transfer learning was 0.60 (95% CI:[0.52,0.65]) respectively. For the off-the-shelf approach, the features extracted from the fully connected layer performed the best. CONCLUSION: Deep learning may play a role in discovering radiogenomic associations in breast cancer.
Authors: Ashirbani Saha; Lars J Grimm; Michael Harowicz; Sujata V Ghate; Connie Kim; Ruth Walsh; Maciej A Mazurowski Journal: Med Phys Date: 2016-08 Impact factor: 4.071
Authors: Shannon C Agner; Mark A Rosen; Sarah Englander; John E Tomaszewski; Michael D Feldman; Paul Zhang; Carolyn Mies; Mitchell D Schnall; Anant Madabhushi Journal: Radiology Date: 2014-03-10 Impact factor: 11.105
Authors: Hui Li; Yitan Zhu; Elizabeth S Burnside; Erich Huang; Karen Drukker; Katherine A Hoadley; Cheng Fan; Suzanne D Conzen; Margarita Zuley; Jose M Net; Elizabeth Sutton; Gary J Whitman; Elizabeth Morris; Charles M Perou; Yuan Ji; Maryellen L Giger Journal: NPJ Breast Cancer Date: 2016-05-11