Abstract
In this paper, we propose a transfer learning-based dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) method for classifying fibroadenoma and invasive ductal carcinoma (IDC) in breast tumors. A total of 207 breast tumors from patients were collected and identified by pathologic diagnosis within 15 days after enhanced DCE-MRI examination; 119 patients (average age 50.52±10.33 years) had fibroadenomas, and 88 patients (average age 42.20±10.10 years) had IDCs. Two lesion-level models were built based on the InceptionV3 and VGG19 models, which were pretrained with the ImageNet dataset. The effects of different depths of transfer learning were examined. The network's performance was evaluated through five-fold cross validation. In the lesion-level models, the model based on Inception V3 obtained better results (area under the receiver operating characteristic curve (AUC) = 0.89) when the weights were frozen before layer-276. The other model based on VGG19 obtained better results (AUC = 0.87) when the weights were frozen before layer-13. Compared with the image-level models, both lesion-level models displayed better discrimination (accuracy increased by 13% and 14%) based on the VGG19 and Inception V3 models, respectively. Our research confirms that transfer learning can be utilized to classify fibroadenomas and IDCs in DCE-MRI images. Different depths of transfer learning result in different performances, and our proposed lesion-level model notably improves the classification accuracy.
Highlights
Since female breast cancer can be screened early and treated, the death rates decreased by 40% from 1989 to 2016 [1]
PERFORMANCES WITH DIFFERENT DEPTHS OF TRANSFER LEARNING The models were trained with the iteration stopping criteria, which were determined by monitoring the convergence of the ACC and the loss of the validation and training datasets
The convergence ranges of validation loss were 0.5-0.7 and 0.5-0.7, and the averaged validation accuracies were 89-94% and 81-91%, in Inception V3 and VGG19 respectively
Summary
Since female breast cancer can be screened early and treated, the death rates decreased by 40% from 1989 to 2016 [1]. Breast cancer is one of the most common diseases in women worldwide and is the second leading cause of cancer-related death [2]. According to the American Cancer Society (ACS), a breast cancer patient who receives treatment for early-stage disease (i.e., stage 0 and stage 1) has a 99% chance of. Various imaging examinations, such as mammograms, ultrasounds, and magnetic resonance imaging (MRI), have increased the incidental detection of breast tumors [5], [6]. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which can compactly capture both anatomical and metabolic features, has been demonstrated as a great screening examination for those with a high risk of breast cancer [7]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
