New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images

Abstract While colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be res...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Young Jae Kim, Jang Pyo Bae, Jun-Won Chung, Dong Kyun Park, Kwang Gi Kim, Yoon Jae Kim
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/5f8f89d4669f4c1aaa3962a6ee25b6d3
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5f8f89d4669f4c1aaa3962a6ee25b6d3
record_format	dspace
spelling	oai:doaj.org-article:5f8f89d4669f4c1aaa3962a6ee25b6d32021-12-02T14:26:54ZNew polyp image classification technique using transfer learning of network-in-network structure in endoscopic images10.1038/s41598-021-83199-92045-2322https://doaj.org/article/5f8f89d4669f4c1aaa3962a6ee25b6d32021-02-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-83199-9https://doaj.org/toc/2045-2322Abstract While colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.Young Jae KimJang Pyo BaeJun-Won ChungDong Kyun ParkKwang Gi KimYoon Jae KimNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-8 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Young Jae Kim Jang Pyo Bae Jun-Won Chung Dong Kyun Park Kwang Gi Kim Yoon Jae Kim New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images
description	Abstract While colorectal cancer is known to occur in the gastrointestinal tract. It is the third most common form of cancer of 27 major types of cancer in South Korea and worldwide. Colorectal polyps are known to increase the potential of developing colorectal cancer. Detected polyps need to be resected to reduce the risk of developing cancer. This research improved the performance of polyp classification through the fine-tuning of Network-in-Network (NIN) after applying a pre-trained model of the ImageNet database. Random shuffling is performed 20 times on 1000 colonoscopy images. Each set of data are divided into 800 images of training data and 200 images of test data. An accuracy evaluation is performed on 200 images of test data in 20 experiments. Three compared methods were constructed from AlexNet by transferring the weights trained by three different state-of-the-art databases. A normal AlexNet based method without transfer learning was also compared. The accuracy of the proposed method was higher in statistical significance than the accuracy of four other state-of-the-art methods, and showed an 18.9% improvement over the normal AlexNet based method. The area under the curve was approximately 0.930 ± 0.020, and the recall rate was 0.929 ± 0.029. An automatic algorithm can assist endoscopists in identifying polyps that are adenomatous by considering a high recall rate and accuracy. This system can enable the timely resection of polyps at an early stage.
format	article
author	Young Jae Kim Jang Pyo Bae Jun-Won Chung Dong Kyun Park Kwang Gi Kim Yoon Jae Kim
author_facet	Young Jae Kim Jang Pyo Bae Jun-Won Chung Dong Kyun Park Kwang Gi Kim Yoon Jae Kim
author_sort	Young Jae Kim
title	New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images
title_short	New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images
title_full	New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images
title_fullStr	New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images
title_full_unstemmed	New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images
title_sort	new polyp image classification technique using transfer learning of network-in-network structure in endoscopic images
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/5f8f89d4669f4c1aaa3962a6ee25b6d3
work_keys_str_mv	AT youngjaekim newpolypimageclassificationtechniqueusingtransferlearningofnetworkinnetworkstructureinendoscopicimages AT jangpyobae newpolypimageclassificationtechniqueusingtransferlearningofnetworkinnetworkstructureinendoscopicimages AT junwonchung newpolypimageclassificationtechniqueusingtransferlearningofnetworkinnetworkstructureinendoscopicimages AT dongkyunpark newpolypimageclassificationtechniqueusingtransferlearningofnetworkinnetworkstructureinendoscopicimages AT kwanggikim newpolypimageclassificationtechniqueusingtransferlearningofnetworkinnetworkstructureinendoscopicimages AT yoonjaekim newpolypimageclassificationtechniqueusingtransferlearningofnetworkinnetworkstructureinendoscopicimages
_version_	1718391312328163328

New polyp image classification technique using transfer learning of network-in-network structure in endoscopic images

Ejemplares similares