Addressing priority challenges in the Detection and Assessment of Colorectal Polyps from Capsule endoscopy and Colonoscopy in Colorectal Cancer Screening using Machine Learning

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Resumé

Background: Colorectal capsule endoscopy (CCE) is a potentially valuable patient-friendly technique for colorectal cancer screening in large populations. Before it can be widely applied, significant research priorities need to be addressed. We present two innovative data science algorithms which can considerably improve acquisition and analysis of relevant data on colorectal polyps obtained from capsule endoscopy.
Material and methods: A fully paired study was performed (2015–2016), where 255 participants from the Danish national screening program had CCE, colonoscopy, and histopathology of all detected polyps. We developed: (1) a new algorithm to match CCE and colonoscopy polyps, based on objective measures of similarity between polyps, and (2) a deep convolutional neural network (CNN) for autonomous detection and localization of colorectal polyps in colon capsule endoscopy.
Results and conclusion: Unlike previous matching methods, our matching algorithm is able to objectively quantify the similarity between CCE and colonoscopy polyps based on their size, morphology and location, and provides a one-to-one unequivocal match between CCE and colonoscopy polyps. Compared to previous methods, the autonomous detection algorithm showed unprecedented high accuracy (96.4%), sensitivity (97.1%) and specificity (93.3%), calculated in respect to the number of polyps detected by trained nurses and gastroenterologists after visualizing frame-by-frame the CCE videos.
OriginalsprogEngelsk
TidsskriftActa Oncologica
Vol/bind58
Udgave nummerSuppl. 1
Sider (fra-til)S29-S36
ISSN0284-186X
DOI
StatusUdgivet - 1. apr. 2019

Fingeraftryk

Capsule Endoscopy
Early Detection of Cancer
Colorectal Neoplasms
Colon
Nurses

Citer dette

@article{557effb3fbf341b58c7433ca1045a1f8,
title = "Addressing priority challenges in the Detection and Assessment of Colorectal Polyps from Capsule endoscopy and Colonoscopy in Colorectal Cancer Screening using Machine Learning",
abstract = "Background: Colorectal capsule endoscopy (CCE) is a potentially valuable patient-friendly technique for colorectal cancer screening in large populations. Before it can be widely applied, significant research priorities need to be addressed. We present two innovative data science algorithms which can considerably improve acquisition and analysis of relevant data on colorectal polyps obtained from capsule endoscopy.Material and methods: A fully paired study was performed (2015–2016), where 255 participants from the Danish national screening program had CCE, colonoscopy, and histopathology of all detected polyps. We developed: (1) a new algorithm to match CCE and colonoscopy polyps, based on objective measures of similarity between polyps, and (2) a deep convolutional neural network (CNN) for autonomous detection and localization of colorectal polyps in colon capsule endoscopy.Results and conclusion: Unlike previous matching methods, our matching algorithm is able to objectively quantify the similarity between CCE and colonoscopy polyps based on their size, morphology and location, and provides a one-to-one unequivocal match between CCE and colonoscopy polyps. Compared to previous methods, the autonomous detection algorithm showed unprecedented high accuracy (96.4{\%}), sensitivity (97.1{\%}) and specificity (93.3{\%}), calculated in respect to the number of polyps detected by trained nurses and gastroenterologists after visualizing frame-by-frame the CCE videos.",
keywords = "Algorithms, Capsule Endoscopy/methods, Colonoscopy/methods, Colorectal Neoplasms/diagnosis, Early Detection of Cancer/methods, Humans, Machine Learning, Polyps/diagnosis, Prognosis",
author = "Victoria Blanes-Vidal and Gunnar Baatrup and {S. Nadimi}, Esmaeil",
year = "2019",
month = "4",
day = "1",
doi = "10.1080/0284186X.2019.1584404",
language = "English",
volume = "58",
pages = "S29--S36",
journal = "Acta Oncologica",
issn = "0284-186X",
publisher = "Taylor & Francis",
number = "Suppl. 1",

}

TY - JOUR

T1 - Addressing priority challenges in the Detection and Assessment of Colorectal Polyps from Capsule endoscopy and Colonoscopy in Colorectal Cancer Screening using Machine Learning

AU - Blanes-Vidal, Victoria

AU - Baatrup, Gunnar

AU - S. Nadimi, Esmaeil

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Background: Colorectal capsule endoscopy (CCE) is a potentially valuable patient-friendly technique for colorectal cancer screening in large populations. Before it can be widely applied, significant research priorities need to be addressed. We present two innovative data science algorithms which can considerably improve acquisition and analysis of relevant data on colorectal polyps obtained from capsule endoscopy.Material and methods: A fully paired study was performed (2015–2016), where 255 participants from the Danish national screening program had CCE, colonoscopy, and histopathology of all detected polyps. We developed: (1) a new algorithm to match CCE and colonoscopy polyps, based on objective measures of similarity between polyps, and (2) a deep convolutional neural network (CNN) for autonomous detection and localization of colorectal polyps in colon capsule endoscopy.Results and conclusion: Unlike previous matching methods, our matching algorithm is able to objectively quantify the similarity between CCE and colonoscopy polyps based on their size, morphology and location, and provides a one-to-one unequivocal match between CCE and colonoscopy polyps. Compared to previous methods, the autonomous detection algorithm showed unprecedented high accuracy (96.4%), sensitivity (97.1%) and specificity (93.3%), calculated in respect to the number of polyps detected by trained nurses and gastroenterologists after visualizing frame-by-frame the CCE videos.

AB - Background: Colorectal capsule endoscopy (CCE) is a potentially valuable patient-friendly technique for colorectal cancer screening in large populations. Before it can be widely applied, significant research priorities need to be addressed. We present two innovative data science algorithms which can considerably improve acquisition and analysis of relevant data on colorectal polyps obtained from capsule endoscopy.Material and methods: A fully paired study was performed (2015–2016), where 255 participants from the Danish national screening program had CCE, colonoscopy, and histopathology of all detected polyps. We developed: (1) a new algorithm to match CCE and colonoscopy polyps, based on objective measures of similarity between polyps, and (2) a deep convolutional neural network (CNN) for autonomous detection and localization of colorectal polyps in colon capsule endoscopy.Results and conclusion: Unlike previous matching methods, our matching algorithm is able to objectively quantify the similarity between CCE and colonoscopy polyps based on their size, morphology and location, and provides a one-to-one unequivocal match between CCE and colonoscopy polyps. Compared to previous methods, the autonomous detection algorithm showed unprecedented high accuracy (96.4%), sensitivity (97.1%) and specificity (93.3%), calculated in respect to the number of polyps detected by trained nurses and gastroenterologists after visualizing frame-by-frame the CCE videos.

KW - Algorithms

KW - Capsule Endoscopy/methods

KW - Colonoscopy/methods

KW - Colorectal Neoplasms/diagnosis

KW - Early Detection of Cancer/methods

KW - Humans

KW - Machine Learning

KW - Polyps/diagnosis

KW - Prognosis

U2 - 10.1080/0284186X.2019.1584404

DO - 10.1080/0284186X.2019.1584404

M3 - Journal article

VL - 58

SP - S29-S36

JO - Acta Oncologica

JF - Acta Oncologica

SN - 0284-186X

IS - Suppl. 1

ER -