Anatomical classification of upper gastrointestinal organs under various image capture conditions using AlexNet.
Anatomical classification
Artificial intelligence
Convolutional neural network (CNN)
Endoscopy
Upper gastrointestinal tract
Journal
Computers in biology and medicine
ISSN: 1879-0534
Titre abrégé: Comput Biol Med
Pays: United States
ID NLM: 1250250
Informations de publication
Date de publication:
09 2020
09 2020
Historique:
received:
21
05
2020
revised:
28
07
2020
accepted:
28
07
2020
pubmed:
18
8
2020
medline:
26
5
2021
entrez:
18
8
2020
Statut:
ppublish
Résumé
Machine learning has led to several endoscopic studies about the automated localization of digestive lesions and prediction of cancer invasion depth. Training and validation dataset collection are required for a disease in each digestive organ under a similar image capture condition; this is the first step in system development. This data cleansing task in data collection causes a great burden among experienced endoscopists. Thus, this study classified upper gastrointestinal (GI) organ images obtained via routine esophagogastroduodenoscopy (EGD) into precise anatomical categories using AlexNet. In total, 85,246 raw upper GI endoscopic images from 441 patients with gastric cancer were collected retrospectively. The images were manually classified into 14 categories: 0) white-light (WL) stomach with indigo carmine (IC); 1) WL esophagus with iodine; 2) narrow-band (NB) esophagus; 3) NB stomach with IC; 4) NB stomach; 5) WL duodenum; 6) WL esophagus; 7) WL stomach; 8) NB oral-pharynx-larynx; 9) WL oral-pharynx-larynx; 10) WL scaling paper; 11) specimens; 12) WL muscle fibers during endoscopic submucosal dissection (ESD); and 13) others. AlexNet is a deep learning framework and was trained using 49,174 datasets and validated using 36,072 independent datasets. The accuracy rates of the training and validation dataset were 0.993 and 0.965, respectively. A simple anatomical organ classifier using AlexNet was developed and found to be effective in data cleansing task for collection of EGD images. Moreover, it could be useful to both expert and non-expert endoscopists as well as engineers in retrospectively assessing upper GI images.
Sections du résumé
BACKGROUND
Machine learning has led to several endoscopic studies about the automated localization of digestive lesions and prediction of cancer invasion depth. Training and validation dataset collection are required for a disease in each digestive organ under a similar image capture condition; this is the first step in system development. This data cleansing task in data collection causes a great burden among experienced endoscopists. Thus, this study classified upper gastrointestinal (GI) organ images obtained via routine esophagogastroduodenoscopy (EGD) into precise anatomical categories using AlexNet.
METHOD
In total, 85,246 raw upper GI endoscopic images from 441 patients with gastric cancer were collected retrospectively. The images were manually classified into 14 categories: 0) white-light (WL) stomach with indigo carmine (IC); 1) WL esophagus with iodine; 2) narrow-band (NB) esophagus; 3) NB stomach with IC; 4) NB stomach; 5) WL duodenum; 6) WL esophagus; 7) WL stomach; 8) NB oral-pharynx-larynx; 9) WL oral-pharynx-larynx; 10) WL scaling paper; 11) specimens; 12) WL muscle fibers during endoscopic submucosal dissection (ESD); and 13) others. AlexNet is a deep learning framework and was trained using 49,174 datasets and validated using 36,072 independent datasets.
RESULTS
The accuracy rates of the training and validation dataset were 0.993 and 0.965, respectively.
CONCLUSIONS
A simple anatomical organ classifier using AlexNet was developed and found to be effective in data cleansing task for collection of EGD images. Moreover, it could be useful to both expert and non-expert endoscopists as well as engineers in retrospectively assessing upper GI images.
Identifiants
pubmed: 32798923
pii: S0010-4825(20)30285-7
doi: 10.1016/j.compbiomed.2020.103950
pii:
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
103950Informations de copyright
Copyright © 2020 Elsevier Ltd. All rights reserved.