Paper
6 March 2018 A performance comparison of low- and high-level features learned by deep convolutional neural networks in epithelium and stroma classification
Author Affiliations +
Abstract
Deep convolutional neural networks (CNNs) based transfer learning is an effective tool to reduce the dependence on hand-crafted features for handling medical classification problems, which may mitigate the problem of the insufficient training caused by the limited sample size. In this study, we investigated the discrimination power of the features at different CNN levels for the task of classifying epithelial and stromal regions on digitized pathologic slides which are prepared from breast cancer tissue. We extracted the low level and high level features from four different deep CNN architectures namely, AlexNet, Places365-AlexNet, VGG, and GoogLeNet. These features are used as input to train and optimize different classifiers including support vector machine (SVM), random forest (RF), and k-nearest neighborhood (KNN). A number of 15000 regions of interest (ROIs) acquired from the public database are employed to conduct this study. The result was observed that the low-level features of AlexNet, Places365-AlexNet and VGG outperformed the high-level ones, but the situation is in the opposite direction when the GoogLeNet is applied. Moreover, the best accuracy was achieved as 89.7% by the relatively deep layer of max pool 4 of GoogLeNet. In summary, our extensive empirical evaluation may suggest that it is viable to extend the use of transfer learning to the development of high-performance detection and diagnosis systems for medical imaging tasks.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yue Du, Roy Zhang, Abolfazl Zargari, Theresa C. Thai, Camille C. Gunderson, Katherine M. Moxley, Hong Liu, Bin Zheng, and Yuchen Qiu "A performance comparison of low- and high-level features learned by deep convolutional neural networks in epithelium and stroma classification", Proc. SPIE 10581, Medical Imaging 2018: Digital Pathology, 1058116 (6 March 2018); https://doi.org/10.1117/12.2292840
Lens.org Logo
CITATIONS
Cited by 8 scholarly publications and 1 patent.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Feature extraction

Convolutional neural networks

Cancer

Image classification

Tissues

Breast cancer

Pathology

Back to Top