Colonoscopy pit-pattern classification based on shape features

Research output: Contribution to conferencePaperAcademic

Abstract

BACKGROUND – With magnifying endoscopy, specialist physicians are able to make a presumptive tissue diagnosis by studying the pit pattern of a lesion in the colon (Kudo et al.), since this pattern corresponds with the histology. This could enable the endoscopist to directly remove adenomatous polyps and leave the hyperplastic polyps in situ, hereby reducing the risk and costs of colonoscopies. GOAL – Investigate the technical feasibility of a system, that supports the endoscopist in classifying the pit pattern type of colonic lesions. METHODS – We propose an algorithm, that uses shape information of the pits to identify the type of pit pattern of the lesion. We define four descriptive measures: Elongation, Circularity, Irregularity and Convexity. These measures are computed for every pit in an image obtained with magnifying colonoscopy. For each pit, the pit type is determined using a trained Support Vector Machine (SVM). The pit pattern is classified as the most occurring pit type in the image, using the occurring percentage as a reliability parameter. RESULTS – We have yet tested the proposed algorithm using 36 clinically validated pit pattern images acquired by a magnifying colonoscope. The system achieved an classification accuracy of 88.9% and similar sensitivity and specificity. CONCLUSION – Our first experiments show that the proposed measures are able to capture the shape of the mucosal pits relatively well and that the pit pattern type can be derived from classified pits. Research is ongoing to further develop and validate the proposed system.
Original languageEnglish
Publication statusPublished - 2013
Eventconference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04 -
Duration: 4 Apr 20134 Apr 2013

Conference

Conferenceconference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04
Period4/04/134/04/13
OtherWetenschapsavond Catharina Ziekenhuis

Fingerprint

Pattern recognition
Histology
Endoscopy
Support vector machines
Elongation
Tissue
Costs
Experiments

Cite this

Sommen, van der, F., Camp, M., Zinger, S., With, de, P. H. N., & Schoon, E. J. (2013). Colonoscopy pit-pattern classification based on shape features. Paper presented at conference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04, .
Sommen, van der, F. ; Camp, M. ; Zinger, S. ; With, de, P.H.N. ; Schoon, E.J. / Colonoscopy pit-pattern classification based on shape features. Paper presented at conference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04, .
@conference{d757cd4d868d4ceea486f5ddc08b399c,
title = "Colonoscopy pit-pattern classification based on shape features",
abstract = "BACKGROUND – With magnifying endoscopy, specialist physicians are able to make a presumptive tissue diagnosis by studying the pit pattern of a lesion in the colon (Kudo et al.), since this pattern corresponds with the histology. This could enable the endoscopist to directly remove adenomatous polyps and leave the hyperplastic polyps in situ, hereby reducing the risk and costs of colonoscopies. GOAL – Investigate the technical feasibility of a system, that supports the endoscopist in classifying the pit pattern type of colonic lesions. METHODS – We propose an algorithm, that uses shape information of the pits to identify the type of pit pattern of the lesion. We define four descriptive measures: Elongation, Circularity, Irregularity and Convexity. These measures are computed for every pit in an image obtained with magnifying colonoscopy. For each pit, the pit type is determined using a trained Support Vector Machine (SVM). The pit pattern is classified as the most occurring pit type in the image, using the occurring percentage as a reliability parameter. RESULTS – We have yet tested the proposed algorithm using 36 clinically validated pit pattern images acquired by a magnifying colonoscope. The system achieved an classification accuracy of 88.9{\%} and similar sensitivity and specificity. CONCLUSION – Our first experiments show that the proposed measures are able to capture the shape of the mucosal pits relatively well and that the pit pattern type can be derived from classified pits. Research is ongoing to further develop and validate the proposed system.",
author = "{Sommen, van der}, F. and M. Camp and S. Zinger and {With, de}, P.H.N. and E.J. Schoon",
year = "2013",
language = "English",
note = "conference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04 ; Conference date: 04-04-2013 Through 04-04-2013",

}

Sommen, van der, F, Camp, M, Zinger, S, With, de, PHN & Schoon, EJ 2013, 'Colonoscopy pit-pattern classification based on shape features' Paper presented at conference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04, 4/04/13 - 4/04/13, .

Colonoscopy pit-pattern classification based on shape features. / Sommen, van der, F.; Camp, M.; Zinger, S.; With, de, P.H.N.; Schoon, E.J.

2013. Paper presented at conference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04, .

Research output: Contribution to conferencePaperAcademic

TY - CONF

T1 - Colonoscopy pit-pattern classification based on shape features

AU - Sommen, van der, F.

AU - Camp, M.

AU - Zinger, S.

AU - With, de, P.H.N.

AU - Schoon, E.J.

PY - 2013

Y1 - 2013

N2 - BACKGROUND – With magnifying endoscopy, specialist physicians are able to make a presumptive tissue diagnosis by studying the pit pattern of a lesion in the colon (Kudo et al.), since this pattern corresponds with the histology. This could enable the endoscopist to directly remove adenomatous polyps and leave the hyperplastic polyps in situ, hereby reducing the risk and costs of colonoscopies. GOAL – Investigate the technical feasibility of a system, that supports the endoscopist in classifying the pit pattern type of colonic lesions. METHODS – We propose an algorithm, that uses shape information of the pits to identify the type of pit pattern of the lesion. We define four descriptive measures: Elongation, Circularity, Irregularity and Convexity. These measures are computed for every pit in an image obtained with magnifying colonoscopy. For each pit, the pit type is determined using a trained Support Vector Machine (SVM). The pit pattern is classified as the most occurring pit type in the image, using the occurring percentage as a reliability parameter. RESULTS – We have yet tested the proposed algorithm using 36 clinically validated pit pattern images acquired by a magnifying colonoscope. The system achieved an classification accuracy of 88.9% and similar sensitivity and specificity. CONCLUSION – Our first experiments show that the proposed measures are able to capture the shape of the mucosal pits relatively well and that the pit pattern type can be derived from classified pits. Research is ongoing to further develop and validate the proposed system.

AB - BACKGROUND – With magnifying endoscopy, specialist physicians are able to make a presumptive tissue diagnosis by studying the pit pattern of a lesion in the colon (Kudo et al.), since this pattern corresponds with the histology. This could enable the endoscopist to directly remove adenomatous polyps and leave the hyperplastic polyps in situ, hereby reducing the risk and costs of colonoscopies. GOAL – Investigate the technical feasibility of a system, that supports the endoscopist in classifying the pit pattern type of colonic lesions. METHODS – We propose an algorithm, that uses shape information of the pits to identify the type of pit pattern of the lesion. We define four descriptive measures: Elongation, Circularity, Irregularity and Convexity. These measures are computed for every pit in an image obtained with magnifying colonoscopy. For each pit, the pit type is determined using a trained Support Vector Machine (SVM). The pit pattern is classified as the most occurring pit type in the image, using the occurring percentage as a reliability parameter. RESULTS – We have yet tested the proposed algorithm using 36 clinically validated pit pattern images acquired by a magnifying colonoscope. The system achieved an classification accuracy of 88.9% and similar sensitivity and specificity. CONCLUSION – Our first experiments show that the proposed measures are able to capture the shape of the mucosal pits relatively well and that the pit pattern type can be derived from classified pits. Research is ongoing to further develop and validate the proposed system.

M3 - Paper

ER -

Sommen, van der F, Camp M, Zinger S, With, de PHN, Schoon EJ. Colonoscopy pit-pattern classification based on shape features. 2013. Paper presented at conference; Wetenschapsavond Catharina Ziekenhuis; 2013-04-04; 2013-04-04, .