A dense multi-path decoder for tissue segmentation in histopathology images. (May 2019)

• Record Type: Journal Article
• Authors: Vu, Quoc Dang; Kwak, Jin Tae
• Is Part Of: Computer methods and programs in biomedicine. Volume 173(2019)
• Page Start: 119
• Page End: 129
• Publication Date: 2019-05
• Subjects: Tissue segmentation -- Digital pathology -- Convolutional neural networks -- Dense decoder; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.03.007
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We propose a dense multi-path decoder for tissue segmentation in histopathology images. Convolutional neural networks are built upon the up-to-date encoders and the proposed decoder. The proposed decoder achieves highly accurate segmentation performance and improves the generalizability of the networks. Three datasets from two organs (breast and prostate) are employed to systematically evaluate the proposed method. The proposed method achieves accurate and robust tissue segmentation and outperforms previous methodologies. Abstract: Background and Objective: Segmenting different tissue components in histopathological images is of great importance for analyzing tissues and tumor environments. In recent years, an encoder–decoder family of convolutional neural networks has increasingly adopted to develop automated segmentation tools. While an encoder has been the main focus of most investigations, the role of a decoder so far has not been well studied and understood. Herein, we proposed an improved design of a decoder for the segmentation of epithelium and stroma components in histopathology images. Methods: The proposed decoder is built upon a multi-path layout and dense shortcut connections between layers to maximize the learning and inference capability. Equipped with the proposed decoder, neural networks are built using three types of encoders (VGG, ResNet and preactived ResNet). To assess the proposed method, breast and prostate tissue datasets are utilized, including 108 and 52 hematoxylin and eosin (H&E) breast tissues images and 224 H&E prostate tissue images. Results: Combining the pre-activated ResNet encoder and the proposed decoder, we achieved a pixel wise accuracy (ACC) of 0.9122, a rand index (RAND) score of 0.8398, an area under receiver operating characteristic curve (AUC) of 0.9716, Dice coefficient for stroma (DICE_STR) of 0.9092 and Dice coefficient for epithelium (DICE_EPI) of 0.9150 on the breast tissue dataset. The same network obtained 0.9074 ACC, 0.8320 Rand index, 0.9719 AUC, 0.9021 DICE_EPI and 0.9121 DICE_STR on the prostate dataset. Conclusions: In general, the experimental results confirmed that the proposed network is superior to the networks combined with the conventional decoder. Therefore, the proposed decoder could aid in improving tissue analysis in histopathology images.