AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices

Abstract We have designed a deep-learning model, an “Artificial Intelligent Endoscopist (a.k.a. AI-doscopist)”, to localise colonic neoplasia during colonoscopy. This study aims to evaluate the agreement between endoscopists and AI-doscopist for colorectal neoplasm localisation. AI-doscopist was pre...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Carmen C. Y. Poon, Yuqi Jiang, Ruikai Zhang, Winnie W. Y. Lo, Maggie S. H. Cheung, Ruoxi Yu, Yali Zheng, John C. T. Wong, Qing Liu, Sunny H. Wong, Tony W. C. Mak, James Y. W. Lau
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2020
Materias:	Computer applications to medicine. Medical informatics R858-859.7
Acceso en línea:	https://doaj.org/article/770504c377534cd0bd60f862a5912cdc
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:770504c377534cd0bd60f862a5912cdc
record_format	dspace
spelling	oai:doaj.org-article:770504c377534cd0bd60f862a5912cdc2021-12-02T16:51:31ZAI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices10.1038/s41746-020-0281-z2398-6352https://doaj.org/article/770504c377534cd0bd60f862a5912cdc2020-05-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-0281-zhttps://doaj.org/toc/2398-6352Abstract We have designed a deep-learning model, an “Artificial Intelligent Endoscopist (a.k.a. AI-doscopist)”, to localise colonic neoplasia during colonoscopy. This study aims to evaluate the agreement between endoscopists and AI-doscopist for colorectal neoplasm localisation. AI-doscopist was pre-trained by 1.2 million non-medical images and fine-tuned by 291,090 colonoscopy and non-medical images. The colonoscopy images were obtained from six databases, where the colonoscopy images were classified into 13 categories and the polyps’ locations were marked image-by-image by the smallest bounding boxes. Seven categories of non-medical images, which were believed to share some common features with colorectal polyps, were downloaded from an online search engine. Written informed consent were obtained from 144 patients who underwent colonoscopy and their full colonoscopy videos were prospectively recorded for evaluation. A total of 128 suspicious lesions were resected or biopsied for histological confirmation. When evaluated image-by-image on the 144 full colonoscopies, the specificity of AI-doscopist was 93.3%. AI-doscopist were able to localise 124 out of 128 polyps (polyp-based sensitivity = 96.9%). Furthermore, after reviewing the suspected regions highlighted by AI-doscopist in a 102-patient cohort, an endoscopist has high confidence in recognizing four missed polyps in three patients who were not diagnosed with any lesion during their original colonoscopies. In summary, AI-doscopist can localise 96.9% of the polyps resected by the endoscopists. If AI-doscopist were to be used in real-time, it can potentially assist endoscopists in detecting one more patient with polyp in every 20–33 colonoscopies.Carmen C. Y. PoonYuqi JiangRuikai ZhangWinnie W. Y. LoMaggie S. H. CheungRuoxi YuYali ZhengJohn C. T. WongQing LiuSunny H. WongTony W. C. MakJames Y. W. LauNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-8 (2020)
institution	DOAJ
collection	DOAJ
language	EN
topic	Computer applications to medicine. Medical informatics R858-859.7
spellingShingle	Computer applications to medicine. Medical informatics R858-859.7 Carmen C. Y. Poon Yuqi Jiang Ruikai Zhang Winnie W. Y. Lo Maggie S. H. Cheung Ruoxi Yu Yali Zheng John C. T. Wong Qing Liu Sunny H. Wong Tony W. C. Mak James Y. W. Lau AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices
description	Abstract We have designed a deep-learning model, an “Artificial Intelligent Endoscopist (a.k.a. AI-doscopist)”, to localise colonic neoplasia during colonoscopy. This study aims to evaluate the agreement between endoscopists and AI-doscopist for colorectal neoplasm localisation. AI-doscopist was pre-trained by 1.2 million non-medical images and fine-tuned by 291,090 colonoscopy and non-medical images. The colonoscopy images were obtained from six databases, where the colonoscopy images were classified into 13 categories and the polyps’ locations were marked image-by-image by the smallest bounding boxes. Seven categories of non-medical images, which were believed to share some common features with colorectal polyps, were downloaded from an online search engine. Written informed consent were obtained from 144 patients who underwent colonoscopy and their full colonoscopy videos were prospectively recorded for evaluation. A total of 128 suspicious lesions were resected or biopsied for histological confirmation. When evaluated image-by-image on the 144 full colonoscopies, the specificity of AI-doscopist was 93.3%. AI-doscopist were able to localise 124 out of 128 polyps (polyp-based sensitivity = 96.9%). Furthermore, after reviewing the suspected regions highlighted by AI-doscopist in a 102-patient cohort, an endoscopist has high confidence in recognizing four missed polyps in three patients who were not diagnosed with any lesion during their original colonoscopies. In summary, AI-doscopist can localise 96.9% of the polyps resected by the endoscopists. If AI-doscopist were to be used in real-time, it can potentially assist endoscopists in detecting one more patient with polyp in every 20–33 colonoscopies.
format	article
author	Carmen C. Y. Poon Yuqi Jiang Ruikai Zhang Winnie W. Y. Lo Maggie S. H. Cheung Ruoxi Yu Yali Zheng John C. T. Wong Qing Liu Sunny H. Wong Tony W. C. Mak James Y. W. Lau
author_facet	Carmen C. Y. Poon Yuqi Jiang Ruikai Zhang Winnie W. Y. Lo Maggie S. H. Cheung Ruoxi Yu Yali Zheng John C. T. Wong Qing Liu Sunny H. Wong Tony W. C. Mak James Y. W. Lau
author_sort	Carmen C. Y. Poon
title	AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices
title_short	AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices
title_full	AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices
title_fullStr	AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices
title_full_unstemmed	AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices
title_sort	ai-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices
publisher	Nature Portfolio
publishDate	2020
url	https://doaj.org/article/770504c377534cd0bd60f862a5912cdc
work_keys_str_mv	AT carmencypoon aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT yuqijiang aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT ruikaizhang aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT winniewylo aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT maggieshcheung aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT ruoxiyu aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT yalizheng aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT johnctwong aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT qingliu aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT sunnyhwong aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT tonywcmak aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices AT jamesywlau aidoscopistarealtimedeeplearningbasedalgorithmforlocalisingpolypsincolonoscopyvideoswithedgecomputingdevices
_version_	1718382926164393984

AI-doscopist: a real-time deep-learning-based algorithm for localising polyps in colonoscopy videos with edge computing devices

Ejemplares similares