Superpixel-based classification of gastric chromoendoscopy images
Conference paper
Boschetto, D and Grisan, E (2017). Superpixel-based classification of gastric chromoendoscopy images. SPIE Medical Imaging. Orlando, FL, USA 11 - 16 Feb 2017 SPIE. https://doi.org/10.1117/12.2254187
Authors | Boschetto, D and Grisan, E |
---|---|
Type | Conference paper |
Abstract | Chromoendoscopy (CH) is a gastroenterology imaging modality that involves the staining of tissues with methylene blue, which reacts with the internal walls of the gastrointestinal tract, improving the visual contrast in mucosal surfaces and thus enhancing a doctor’s ability to screen precancerous lesions or early cancer. This technique helps identify areas that can be targeted for biopsy or treatment and in this work we will focus on gastric cancer detection. Gastric chromoendoscopy for cancer detection has several taxonomies available, one of which classifies CH images into three classes (normal, metaplasia, dysplasia) based on color, shape and regularity of pit patterns. Computer-assisted diagnosis is desirable to help us improve the reliability of the tissue classification and abnormalities detection. However, traditional computer vision methodologies, mainly segmentation, do not translate well to the specific visual characteristics of a gastroenterology imaging scenario. We propose the exploitation of a first unsupervised segmentation via superpixel, which groups pixels into perceptually meaningful atomic regions, used to replace the rigid structure of the pixel grid. For each superpixel, a set of features is extracted and then fed to a random forest based classifier, which computes a model used to predict the class of each superpixel. The average general accuracy of our model is 92.05% in the pixel domain (86.62% in the superpixel domain), while detection accuracies on the normal and abnormal class are respectively 85.71% and 95%. Eventually, the whole image class can be predicted image through a majority vote on each superpixel’s predicted class. © 2017 SPIE. |
Keywords | chromoendoscopy; classification; gastric cancer; superpixel |
Year | 2017 |
Journal | Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101340W |
Publisher | SPIE |
Journal citation | 10134 |
Digital Object Identifier (DOI) | https://doi.org/10.1117/12.2254187 |
Web address (URL) | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85020251985&doi=10.1117%2f12.2254187&partnerID=40&md5=a710f003ba3d25d16124dc893b57252e |
Accepted author manuscript | License File Access Level Open |
Publication dates | |
03 Mar 2017 | |
Publication process dates | |
Accepted | 05 Oct 2016 |
Deposited | 27 Jan 2020 |
ISBN | 9781510607132 |
https://openresearch.lsbu.ac.uk/item/88xv3
Download files
Accepted author manuscript
SPIE_ChromoChallenge_finale_DB.docx | ||
License: CC BY-NC 4.0 | ||
File access level: Open |
108
total views99
total downloads0
views this month0
downloads this month