Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms

Abstract The treatment plan of colorectal neoplasm differs based on histology. Although new endoscopic imaging systems have been developed, there are clear diagnostic thresholds and requirements in using them. To overcome these limitations, we trained convolutional neural networks (CNNs) with endosc...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Seong Ji Choi, Eun Sun Kim, Kihwan Choi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/55fb76bc4ec44200b0fe0e43125cedff
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:55fb76bc4ec44200b0fe0e43125cedff
record_format	dspace
spelling	oai:doaj.org-article:55fb76bc4ec44200b0fe0e43125cedff2021-12-02T15:54:12ZPrediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms10.1038/s41598-021-84299-22045-2322https://doaj.org/article/55fb76bc4ec44200b0fe0e43125cedff2021-03-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-84299-2https://doaj.org/toc/2045-2322Abstract The treatment plan of colorectal neoplasm differs based on histology. Although new endoscopic imaging systems have been developed, there are clear diagnostic thresholds and requirements in using them. To overcome these limitations, we trained convolutional neural networks (CNNs) with endoscopic images and developed a computer-aided diagnostic (CAD) system which predicts the pathologic histology of colorectal adenoma. We retrospectively collected colonoscopic images from two tertiary hospitals and labeled 3400 images into one of 4 classes according to the final histology: normal, low-grade dysplasia, high-grade dysplasia, and adenocarcinoma. We implemented a CAD system based on ensemble learning with three CNN models which transfer the knowledge learned from common digital photography images to the colonoscopic image domain. The deep learning models were trained to classify the colorectal adenoma into these 4 classes. We compared the outcomes of the CNN models to those of two endoscopist groups having different years of experience, and visualized the model predictions using Class Activation Mapping. In our multi-center study, our CNN-CAD system identified the histology of colorectal adenoma with as sensitivity 77.25%, specificity of 92.42%, positive predictive value of 77.16%, negative predictive value of 92.58% averaged over the 4 classes, and mean diagnostic time of 0.12 s per image. Our experiments demonstrate that the CNN-CAD showed a similar performance to that of endoscopic experts and outperformed that of trainees. The model visualization results also showed reasonable regions of interest to explain the classification decisions of CAD systems. We suggest that CNN-CAD system can predict the histology of colorectal adenoma.Seong Ji ChoiEun Sun KimKihwan ChoiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Seong Ji Choi Eun Sun Kim Kihwan Choi Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms
description	Abstract The treatment plan of colorectal neoplasm differs based on histology. Although new endoscopic imaging systems have been developed, there are clear diagnostic thresholds and requirements in using them. To overcome these limitations, we trained convolutional neural networks (CNNs) with endoscopic images and developed a computer-aided diagnostic (CAD) system which predicts the pathologic histology of colorectal adenoma. We retrospectively collected colonoscopic images from two tertiary hospitals and labeled 3400 images into one of 4 classes according to the final histology: normal, low-grade dysplasia, high-grade dysplasia, and adenocarcinoma. We implemented a CAD system based on ensemble learning with three CNN models which transfer the knowledge learned from common digital photography images to the colonoscopic image domain. The deep learning models were trained to classify the colorectal adenoma into these 4 classes. We compared the outcomes of the CNN models to those of two endoscopist groups having different years of experience, and visualized the model predictions using Class Activation Mapping. In our multi-center study, our CNN-CAD system identified the histology of colorectal adenoma with as sensitivity 77.25%, specificity of 92.42%, positive predictive value of 77.16%, negative predictive value of 92.58% averaged over the 4 classes, and mean diagnostic time of 0.12 s per image. Our experiments demonstrate that the CNN-CAD showed a similar performance to that of endoscopic experts and outperformed that of trainees. The model visualization results also showed reasonable regions of interest to explain the classification decisions of CAD systems. We suggest that CNN-CAD system can predict the histology of colorectal adenoma.
format	article
author	Seong Ji Choi Eun Sun Kim Kihwan Choi
author_facet	Seong Ji Choi Eun Sun Kim Kihwan Choi
author_sort	Seong Ji Choi
title	Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms
title_short	Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms
title_full	Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms
title_fullStr	Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms
title_full_unstemmed	Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms
title_sort	prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/55fb76bc4ec44200b0fe0e43125cedff
work_keys_str_mv	AT seongjichoi predictionofthehistologyofcolorectalneoplasminwhitelightcolonoscopicimagesusingdeeplearningalgorithms AT eunsunkim predictionofthehistologyofcolorectalneoplasminwhitelightcolonoscopicimagesusingdeeplearningalgorithms AT kihwanchoi predictionofthehistologyofcolorectalneoplasminwhitelightcolonoscopicimagesusingdeeplearningalgorithms
_version_	1718385448837971968

Prediction of the histology of colorectal neoplasm in white light colonoscopic images using deep learning algorithms

Ejemplares similares