Deep learning for identifying radiogenomic associations in breast cancer

Abstract

Purpose: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.

Deep learning in radiology: An overview of the concepts and a survey of the state of the art with focus on MRI

“…An ensemble of fine‐tuned CNN classifiers was shown to outperform traditional CNNs in predicting the radiological image modality on a test set of 4166 images . A comparison of approaches using deep features and transfer learning with fine‐tuning has been shown useful for identifying radiogenomic relationships in breast cancer MRI . Although deep features performed better than transfer learning with the fine‐tuning approach, the method faced the issue of training on a small dataset.…”

Precision Medicine, AI, and the Future of Personalized Health Care

“…Radiogenomics, as a novel precision medicine research field, focuses on establishing associations between cancer imaging features and gene expression to predict a patient's risk of developing toxicity following radiotherapy. [51][52][53] For example, Chang et al proposed a framework of multiple residual convolutional neural networks to noninvasively predict isocitrate dehydrogenase genotype in grades II-IV glioma using multi-institutional magnetic resonance imaging datasets. Besides, AI has been used in discovering radiogenomic associations in breast cancer, 52 liver cancer, 54 and colorectal cancer.…”

Breast Cancer Radiogenomics: Current Status and Future Directions

“…Deep learning algorithms, rather than extracting specific computer visions features from images and then using those to predict genomic signatures, performs the prediction all at once, starting from the image itself and arriving at the prediction of genomics. For example in Zhu et al showed the ability of a convolutional neural network to directly predict surrogate molecular subtype based on DCE-MR images (47).…”