Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/5329
Title: Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning
Authors: Önder, Devrim
Sarıoğlu, Sülen
Karaçalı, Bilge
Keywords: Dimensionality reduction
Histopathology
Quasi-supervised learning
Statistical learning
Texture classification
Issue Date: Apr-2013
Publisher: Elsevier Ltd.
Source: Önder, D., Sarıoğlu, S., and Karaçalı, B. (2013). Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning. Micron, 47. 33-42. doi:10.1016/j.micron.2013.01.003
Abstract: Quasi-supervised learning is a statistical learning algorithm that contrasts two datasets by computing estimate for the posterior probability of each sample in either dataset. This method has not been applied to histopathological images before. The purpose of this study is to evaluate the performance of the method to identify colorectal tissues with or without adenocarcinoma. Light microscopic digital images from histopathological sections were obtained from 30 colorectal radical surgery materials including adenocarcinoma and non-neoplastic regions. The texture features were extracted by using local histograms and co-occurrence matrices. The quasi-supervised learning algorithm operates on two datasets, one containing samples of normal tissues labelled only indirectly, and the other containing an unlabeled collection of samples of both normal and cancer tissues. As such, the algorithm eliminates the need for manually labelled samples of normal and cancer tissues for conventional supervised learning and significantly reduces the expert intervention. Several texture feature vector datasets corresponding to different extraction parameters were tested within the proposed framework. The Independent Component Analysis dimensionality reduction approach was also identified as the one improving the labelling performance evaluated in this series. In this series, the proposed method was applied to the dataset of 22,080 vectors with reduced dimensionality 119 from 132. Regions containing cancer tissue could be identified accurately having false and true positive rates up to 19% and 88% respectively without using manually labelled ground-truth datasets in a quasi-supervised strategy. The resulting labelling performances were compared to that of a conventional powerful supervised classifier using manually labelled ground-truth data. The supervised classifier results were calculated as 3.5% and 95% for the same case. The results in this series in comparison with the benchmark classifier, suggest that quasi-supervised image texture labelling may be a useful method in the analysis and classification of pathological slides but further study is required to improve the results.
URI: http://doi.org/10.1016/j.micron.2013.01.003
http://hdl.handle.net/11147/5329
ISSN: 0968-4328
1878-4291
0968-4328
Appears in Collections:Electrical - Electronic Engineering / Elektrik - Elektronik Mühendisliği
PubMed İndeksli Yayınlar Koleksiyonu / PubMed Indexed Publications Collection
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Files in This Item:
File Description SizeFormat 
5329.pdfMakale1.02 MBAdobe PDFThumbnail
View/Open
Show full item record

CORE Recommender

SCOPUSTM   
Citations

13
checked on Sep 24, 2022

WEB OF SCIENCETM
Citations

15
checked on Sep 24, 2022

Page view(s)

524
checked on Sep 26, 2022

Download(s)

140
checked on Sep 26, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.