Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation

Abstract The advancement of artificial intelligence (AI) has facilitated its application in medical fields. However, there has been little research for AI-assisted endoscopy, despite the clinical significance of the efficiency and safety of cannulation in the endoscopic retrograde cholangiopancreato...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Taesung Kim, Jinhee Kim, Hyuk Soon Choi, Eun Sun Kim, Bora Keum, Yoon Tae Jeen, Hong Sik Lee, Hoon Jai Chun, Sung Yong Han, Dong Uk Kim, Soonwook Kwon, Jaegul Choo, Jae Min Lee
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/7faffbe01bd3449bbde1be6039f54e82
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:7faffbe01bd3449bbde1be6039f54e82
record_format	dspace
spelling	oai:doaj.org-article:7faffbe01bd3449bbde1be6039f54e822021-12-02T15:51:13ZArtificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation10.1038/s41598-021-87737-32045-2322https://doaj.org/article/7faffbe01bd3449bbde1be6039f54e822021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-87737-3https://doaj.org/toc/2045-2322Abstract The advancement of artificial intelligence (AI) has facilitated its application in medical fields. However, there has been little research for AI-assisted endoscopy, despite the clinical significance of the efficiency and safety of cannulation in the endoscopic retrograde cholangiopancreatography (ERCP). In this study, we aim to assist endoscopists performing ERCP through automatic detection of the ampulla and the identification of cannulation difficulty. We developed a novel AI-assisted system based on convolutional neural networks that predict the location of the ampulla and the difficulty of cannulation to the ampulla. ERCP data of 531 and 451 patients were utilized in the evaluation of our model for each task. Our model detected the ampulla with mean intersection-over-union 64.1%, precision 76.2%, recall 78.4%, and centroid distance 0.021. In classifying the cannulation difficulty, it achieved the recall of 71.9% for the class of easy cases and that of 61.1% for that of difficult cases. Remarkably, our model accurately detected AOV with varying morphological shape, size, and texture on par with the level of a human expert and showed promising results for recognizing cannulation difficulty. It demonstrated its potential to improve the quality of ERCP by assisting endoscopists.Taesung KimJinhee KimHyuk Soon ChoiEun Sun KimBora KeumYoon Tae JeenHong Sik LeeHoon Jai ChunSung Yong HanDong Uk KimSoonwook KwonJaegul ChooJae Min LeeNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Taesung Kim Jinhee Kim Hyuk Soon Choi Eun Sun Kim Bora Keum Yoon Tae Jeen Hong Sik Lee Hoon Jai Chun Sung Yong Han Dong Uk Kim Soonwook Kwon Jaegul Choo Jae Min Lee Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation
description	Abstract The advancement of artificial intelligence (AI) has facilitated its application in medical fields. However, there has been little research for AI-assisted endoscopy, despite the clinical significance of the efficiency and safety of cannulation in the endoscopic retrograde cholangiopancreatography (ERCP). In this study, we aim to assist endoscopists performing ERCP through automatic detection of the ampulla and the identification of cannulation difficulty. We developed a novel AI-assisted system based on convolutional neural networks that predict the location of the ampulla and the difficulty of cannulation to the ampulla. ERCP data of 531 and 451 patients were utilized in the evaluation of our model for each task. Our model detected the ampulla with mean intersection-over-union 64.1%, precision 76.2%, recall 78.4%, and centroid distance 0.021. In classifying the cannulation difficulty, it achieved the recall of 71.9% for the class of easy cases and that of 61.1% for that of difficult cases. Remarkably, our model accurately detected AOV with varying morphological shape, size, and texture on par with the level of a human expert and showed promising results for recognizing cannulation difficulty. It demonstrated its potential to improve the quality of ERCP by assisting endoscopists.
format	article
author	Taesung Kim Jinhee Kim Hyuk Soon Choi Eun Sun Kim Bora Keum Yoon Tae Jeen Hong Sik Lee Hoon Jai Chun Sung Yong Han Dong Uk Kim Soonwook Kwon Jaegul Choo Jae Min Lee
author_facet	Taesung Kim Jinhee Kim Hyuk Soon Choi Eun Sun Kim Bora Keum Yoon Tae Jeen Hong Sik Lee Hoon Jai Chun Sung Yong Han Dong Uk Kim Soonwook Kwon Jaegul Choo Jae Min Lee
author_sort	Taesung Kim
title	Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation
title_short	Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation
title_full	Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation
title_fullStr	Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation
title_full_unstemmed	Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation
title_sort	artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/7faffbe01bd3449bbde1be6039f54e82
work_keys_str_mv	AT taesungkim artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT jinheekim artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT hyuksoonchoi artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT eunsunkim artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT borakeum artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT yoontaejeen artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT hongsiklee artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT hoonjaichun artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT sungyonghan artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT dongukkim artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT soonwookkwon artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT jaegulchoo artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation AT jaeminlee artificialintelligenceassistedanalysisofendoscopicretrogradecholangiopancreatographyimageforidentifyingampullaanddifficultyofselectivecannulation
_version_	1718385643608866816

Artificial intelligence-assisted analysis of endoscopic retrograde cholangiopancreatography image for identifying ampulla and difficulty of selective cannulation

Ejemplares similares