Automated labelling of cancer textures in colorectal histopathology slides using quasi-supervised learning

Abstract

a b s t r a c tQuasi-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.

Confident texture-based laryngeal tissue classification for early stage diagnosis support

“…As recommended in Ref. 23, such features are adopted to integrate the texture-based information encoded in LBP riu2 R;P . In addition to these descriptors, we tested two feature combinations (F GLCM þ stat 1 , H LBP riu2 þ stat 1 ), as suggested in Ref.…”

“…In addition to these descriptors, we tested two feature combinations (F GLCM þ stat 1 , H LBP riu2 þ stat 1 ), as suggested in Ref. 23 for applications in colorectal image analysis.…”

Digital imaging of colon tissue: method for evaluation of inflammation severity by spatial frequency features of the histological images

“…Analysis of microscopy images and histological scoring is not only time consuming, but the results are often susceptible to inconsistency due to human factor [ 11 , 12 ]. Development of digital microscopic imaging technology and image processing techniques [ 13 ] inspired research towards translational computational systems that can detect, analyze, classify, and quantify tissue sections. Usage of digital imaging systems could make histological image assessment less time consuming, but also could improve diagnostic quality due to objective estimation of image features.…”

Automatic Bone Marrow Cellularity Estimation in H&E Stained Whole Slide Images

“…[Color figure can be viewed at wileyonlinelibrary.com] matrices features, which has shown promising results (15)(16)(17)(18). For this purpose, previous studies have proposed using intensity and texture features for tissue classification within WSI H&E stains, for example, based on gray level cooccurrence matrix (GLCM), Gaussian Markov random field, and run-length The columns show original subimages, ground truth segmentations, results after the tissue classification, and results after the bone marrow segmentation, respectively.…”

“…(i) an example containing fibrin (tissue to the left), fibrosis (middle tissue), and bone (tissue to the right). [Color figure can be viewed at wileyonlinelibrary.com] matrices features, which has shown promising results (15)(16)(17)(18). Therefore, such features may be useful to classify between different tissue types in bone marrow biopsies.…”