Scale embedding shared neural networks for multiscale histological analysis of prostate cancer

Quy Dinh Duong; Dang Quoc Vu; Daigeun Lee; Stephen M. Hewitt; Kyungeun Kim; Jin Tae Kwak

doi:10.1117/12.2512807

Translator Disclaimer

18 March 2019 Scale embedding shared neural networks for multiscale histological analysis of prostate cancer

Quy Dinh Duong, Dang Quoc Vu, Daigeun Lee, Stephen M. Hewitt, Kyungeun Kim, Jin Tae Kwak

Author Affiliations +

Proceedings Volume 10956, Medical Imaging 2019: Digital Pathology; 1095606 (2019) https://doi.org/10.1117/12.2512807
Event: SPIE Medical Imaging, 2019, San Diego, California, United States

Abstract

In digital pathology, deep learning approaches have been increasingly applied and shown to be effective in analyzing digitized tissue specimen images. Such approaches have, in general, chosen an arbitrary scale or resolution at which the images are analyzed for several reasons, including computational cost and complexity. However, the tissue characteristics, indicative of cancer, tend to present at differing scales. Herein, we propose a framework that enables deep convolutional neural networks to perform multiscale histological analysis of tissue specimen images in an efficient and effective manner. A deep residual neural network is shared across multiple scales, extracting high-level features. The high-level features from multiple scales are aggregated and transformed in a way that the scale information is embedded in the network. The transformed features are utilized to classify tissue images into cancer and benign. The proposed method is compared to other methodologies to combine the feature from different scales. These competing methods combine the multi-scale features via 1) concatenation 2) addition and 3) convolution. Tissue microarrays (TMAs) were employed to evaluate the proposed method and the other competing methods. Three TMAs, including 225 benign and 377 cancer tissue samples, were used as training dataset. Two TMAs with 151 benign and 252 cancer tissue samples was utilized as testing dataset. The proposed method obtained an accuracy of 0.953 and the area under the receiver operating characteristics curve (AUC) of 0.971 (95% CI: 0.955-0.987), outperforming other competing methods. This suggests that the proposed multiscale approaches via a shared neural network and scale embedding scheme, could aid in improving digital pathology analysis and cancer pathology.

Conference Presentation

Citation Download Citation

Quy Dinh Duong, Dang Quoc Vu, Daigeun Lee, Stephen M. Hewitt, Kyungeun Kim, and Jin Tae Kwak "Scale embedding shared neural networks for multiscale histological analysis of prostate cancer", Proc. SPIE 10956, Medical Imaging 2019: Digital Pathology, 1095606 (18 March 2019); https://doi.org/10.1117/12.2512807

ACCESS THE FULL ARTICLE