Publication detail

Grading of Colorectal Cancer using Histology images

SENGAR, N. MISHRA, N. DUTTA, M. BURGET, R. PŘINOSIL, J.

Original Title

Grading of Colorectal Cancer using Histology images

English Title

Grading of Colorectal Cancer using Histology images

Type

conference paper

Language

en

Original Abstract

This paper presents an automated system for grading of colorectal cancer using image processing method. About, half a million people die every year due to colon cancer. Histopathological tissue analysis is a common method of its detection, which needs an expert pathologist. Screening for this cancer is effective for prevention as well as early detection. This proposed method segments the glands automatically by using intensity based thresholding and using organizational properties for classification. In existing literature, the majority of studies focus on gland segmentation in healthy or benign samples, but rarely on intermediate or high grade cancer. Unlike most of existing methods this system is fully automated and grades the images as benign healthy, benign adenomatous, moderately differentiated malignant and poorly differentiated malignant. The proposed method achieves overall accuracy of 81% when tested on 165 histology images

English abstract

This paper presents an automated system for grading of colorectal cancer using image processing method. About, half a million people die every year due to colon cancer. Histopathological tissue analysis is a common method of its detection, which needs an expert pathologist. Screening for this cancer is effective for prevention as well as early detection. This proposed method segments the glands automatically by using intensity based thresholding and using organizational properties for classification. In existing literature, the majority of studies focus on gland segmentation in healthy or benign samples, but rarely on intermediate or high grade cancer. Unlike most of existing methods this system is fully automated and grades the images as benign healthy, benign adenomatous, moderately differentiated malignant and poorly differentiated malignant. The proposed method achieves overall accuracy of 81% when tested on 165 histology images

Keywords

colorectal cancer; histology image; image processing

Released

27.06.2016

Location

Vieanna, Austria

ISBN

978-1-5090-1287-9

Book

2016 39th International Conference on Telecommunications and Signal Processing (TSP)

Pages from

529

Pages to

532

Pages count

4

URL

BibTex


@inproceedings{BUT128334,
  author="Namita {Sengar} and Neeraj {Mishra} and Malay Kishore {Dutta} and Jiří {Přinosil} and Radim {Burget}",
  title="Grading of Colorectal Cancer using Histology images",
  annote="This paper presents an automated system for grading of colorectal cancer using image processing method. About, half a million people die every year due to colon cancer. Histopathological tissue analysis is a common method of its detection, which needs an expert pathologist. Screening for this cancer is effective for prevention as well as early detection. This proposed method segments the glands automatically by using intensity based thresholding and using organizational properties for classification. In existing literature, the majority of studies focus on gland segmentation in healthy or benign samples, but rarely on intermediate or high grade cancer. Unlike most of existing methods this system is fully automated and grades the images as benign healthy, benign adenomatous, moderately differentiated malignant and poorly differentiated malignant. The proposed method achieves overall accuracy of 81% when tested on 165 histology images",
  booktitle="2016 39th International Conference on Telecommunications and Signal Processing (TSP)",
  chapter="128334",
  doi="10.1109/TSP.2016.7760936",
  howpublished="online",
  year="2016",
  month="june",
  pages="529--532",
  type="conference paper"
}