Convolutional Neural Networks have been successfully used in several tasks in the last decade, but this kind of supervised method requires a large number of annotated examples to obtain good results. However, in biomedical domains, such as digital pathology, the amount of annotated samples is very reduced and imbalanced. On the other hand, models trained using supervised methods need to be retrained when a new class (with its samples) is introduced. This process is computationally expensive and can be difficult when you don’t have a lot of examples for the same class. In order to address these issues, there are novel approaches that use a few number of annotated examples to achieve an acceptable or good generalization capability of the model. One of these methods is One-shot Learning, which is intended to classify a set of data from different classes from one or a few number of annotated examples, and which allows to incorporate new data from new classes without re-training the model. This work explores a method to classify samples of tissues in breast cancer histopathology images by means of similarity between pairs of image samples using a Siamese Convolutional Neural Networks, which achieved a 90.83% of accuracy test.
The Convolutional neural networks (CNN) have been shown to be able to learn the relevant visual features for different computer vision tasks from large amounts of annotated data. Hence, the performance of CNNs can vary depending on the training data set and associated model architecture. This article presents a comparative analysis of the robustness and sensitivity of different CNN architectures to classify invasive breast cancer tissue. Our experiment involved a comparison of six CNN architectures with different depths (number of layers), specifically trained to detect invasive breast cancer from digitized pathology images. Additionally, the pre-trained model VGG 16 (trained to classify natural images) was added as the seventh architecture. Each of the models was trained with two different data sets: a cohort of 239 breast cancer slide images from the Hospital of the University of Pennsylvania (HUP), and another with 172 digitized breast cancer images from the Cancer Genome Atlas (TCGA). In addition, in each case the training was validated with 40 breast cancer slide images from the New Jersey Cancer Institute (CINJ). The last layer of the VGG 16 model was modified to allow classification of the binary problem (presence or absence of invasive ductal carcinoma). The experimental results show a performance of greater than 93% in terms of AUC (Area Under the ROC Curve) for the CNNs trained specifically with cases of invasive breast cancer from the TCGA. However, we also note that VGG-CNN-16 achieves an AUC of 92.43% and 86.87% respectively, despite the fact that it was trained for a different domain.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.