Segmentation for Classification of Gastroenterology Images

• Type: Article in International Conference Proceedings Book
• Date: 2010

Authors

Coimbra, M (Author) FCUP; Riaz, F (Author) Other; Areia, M (Author) Other; Baldaque Silva, FB (Author) Other; Dinis Ribeiro, M (Author) FMUP

Conference proceedings International

Title: 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

Pages: 4744-4747

2010 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC'10

Buenos Aires, 31 August 2010 through 4 September 2010

Indexing

ISI Web of Knowledge - 1 Citation

Scopus - 4 Citations

COMPENDEX

Scientific classification

FOS: Engineering and technology > Environmental biotechnology

CORDIS: Physical sciences > Computer science

Other information

Authenticus ID: P-003-D7Y

DOI: 10.1109/iembs.2010.5626622

Abstract (EN): Automatic classification of cancer lesions in tissues observed using gastroenterology imaging is a non-trivial pattern recognition task involving filtering, segmentation, feature extraction and classification. In this paper we measure the impact of a variety of segmentation algorithms (mean shift, normalized cuts, level-sets) on the automatic classification performance of gastric tissue into three classes: cancerous, precancerous and normal. Classification uses a combination of color (hue-saturation histograms) and texture (local binary patterns) features, applied to two distinct imaging modalities: chromoendoscopy and narrow-band imaging. Results show that mean-shift obtains an interesting performance for both scenarios producing low classification degradations (6%), full image classification is highly inaccurate reinforcing the importance of segmentation research for Gastroenterology, and confirm that Patch Index is an interesting measure of the classification potential of small to medium segmented regions.

Language: English

Type (Professor's evaluation): Scientific

Notes: ISBN-13: 9781424441235; DOI: 10.1109/IEMBS.2010.5626622. - Main Heading: Image segmentation; Controlled terms: Feature extraction, Gastroenterology; Uncontrolled terms: Automatic classification, Feature extraction and classification, Gastric tissue, Imaging modality, Level Set, Local binary patterns, Mean shift, Narrow bands, Non-trivial, Normalized cuts, Patch indices, Segmentation algorithms, Segmented regions.

No. of pages: 4