Cell‐type based semantic segmentation of histopathological images using deep convolutional neural networks. Issue 3 (7th February 2019)

• Record Type: Journal Article
• Authors: Öztürk, Şaban; Akdemir, Bayram
• Is Part Of: International journal of imaging systems and technology. Volume 29:Issue 3(2019)
• Page Start: 234
• Page End: 246
• Publication Date: 2019-02-07
• Subjects: semantic segmentation -- Convolutional neural networks -- CNN -- histopathological image -- whole‐slide -- fully connected networks; Imaging systems -- Periodicals; Image processing -- Periodicals; 621.367
• DOI: 10.1002/ima.22309
• Languages: English
• ISSNs: 0899-9457

Abstract

Abstract: Histopathological whole‐slide image (WSI) analysis is still one of the most important ways to identify regions of cancer risk. For cancer in which early diagnosis is vital, pathologists are at the center of the decision‐making process. Thanks to the widespread use of digital pathology and the development of artificial intelligence methods, automatic histopathological image analysis methods help pathologists in their decision‐making process. In this process, rather than producing labels for whole‐slide image patches, semantic segmentation is very useful, which facilitates the pathologists' interpretation. In this study, automatic semantic segmentation based on cell type is proposed for the first time in the literature using novel deep convolutional networks structure (DCNN). We presents semantic information on four classes, including white areas in the whole‐slide image, tissue without cells, tissue with normal cells and tissue with cancerous cells. This visual information presented to the pathologist is an easy‐to‐understand picture of the status of the cells and their implications for the spread of cancerous cells. A new DCNN architecture is created, inspired by the residual network and deconvolution network architecture. Our network is trained end‐to‐end manner with histopathological image patches for cell structures to be more discriminative. The proposed method not only produces more successful results than other state‐of‐art semantic segmentation algorithms with 9.2% training error and 88.89% F‐score for test, but also has the most important advantage in that it has the ability to generate automatic information about the cancer and also provides information that pathologists can quickly interpret.