Epithelium and stroma segmentation using multiscale superpixel clustering.

Landini, Gabriel and Fouad, Shereen and Galton, Antony and Randell, David (2018) Epithelium and stroma segmentation using multiscale superpixel clustering. In: 14th European Congress on Digital Pathology, 29th May - 1st June, 2018, Finland.

Full text not available from this repository. (Request a copy)

Abstract

Introduction: Accurate image segmentation is essential in quantitative histopathology although challenging due to tissue complexity, heterogeneity and the uncertainty of scene contents. Because structures detected at certain resolutions do not always coincide with the resolution at which other features are detected, we investigated a multiscale approach of image segmentation. Method: We developed an unsupervised framework using multiscale superpixels and k-means clustering. Images were partitioned into increasingly sized superpixels and clustered into 3 classes based on tissue stain uptake after colour deconvolution (aiming to identify background, epithelium and stroma) in H&E oropharyngeal cancer TMA sections. To overcome arbitrary label assignments during clustering, labelled regions were sequentially matched across consecutive scale image pairs using the additive inverse of the Dice index to generate a ‘cost matrix’ for all label combinations. A bipartite graph matching algorithm identified the combination that minimised the matrix overall cost. Results: From the matched ensemble, labelling probability images were generated to compute a ‘most likely’ segmentation. Fifty-six micro-array images compared with annotated standards achieved an average Dice index of 0.76 (median 0.79). The ‘most likely’ segmentations versus the standard, achieved a higher Dice index than those of the smallest and largest scale results (71% and 95% of instances respectively) and the average Dice over all scales (in 93% of instances). Conclusions: Our unsupervised segmentation, on average, performs better than single resolution superpixel clusterings. The method can also be applied to samples stained by other methods, once the dye RGB vectors (for colour deconvolution) have been appropriately determined.

Item Type: Conference or Workshop Item (Poster)
Subjects: B800 Medical Technology
G400 Computer Science
Divisions: Faculty of Computing, Engineering and the Built Environment
Faculty of Computing, Engineering and the Built Environment > School of Computing and Digital Technology
REF UoA Output Collections > REF2021 UoA11: Computer Science and Informatics
Depositing User: Shereen Fouad
Date Deposited: 02 Apr 2019 09:05
Last Modified: 02 Apr 2019 09:05
URI: http://www.open-access.bcu.ac.uk/id/eprint/7312

Actions (login required)

View Item View Item

Research

In this section...