Retrospective Study
Copyright ©The Author(s) 2022. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastrointest Endosc. May 16, 2022; 14(5): 311-319
Published online May 16, 2022. doi: 10.4253/wjge.v14.i5.311
Recognition of esophagitis in endoscopic images using transfer learning
Elena Caires Silveira, Caio Fellipe Santos Corrêa, Leonardo Madureira Silva, Bruna Almeida Santos, Soraya Mattos Pretti, Fabrício Freire de Melo
Elena Caires Silveira, Caio Fellipe Santos Corrêa, Leonardo Madureira Silva, Bruna Almeida Santos, Soraya Mattos Pretti, Fabrício Freire de Melo, Multidisciplinary Institute of Health, Federal University of Bahia, Vitória da Conquista 45029-094, Bahia, Brazil
Author contributions: Caires Silveira E proceeded the data collection/entry, performed data analysis and data interpretation, developed the proposed predictive model and participated in preparation and review of manuscript; Santos Corrêa CF and Madureira Silva L participated in preparation of manuscript and wrote the literature analysis/search; Mattos Pretti S and Almeida Santos B participated in review of manuscript; Freire de Melo F designed the research and participated in review of manuscript.
Institutional review board statement: For this study, there was no need for an appraisal by an ethics committee, since only publicly available anonymized data were used.
Informed consent statement: The present manuscript used anonymous images to produce its analyzes and results, in a method that obeys the norms of medical bioethics. Thus, there was no direct or even indirect contact between researchers and patients, with no necessity for "Signed Informed Consent Form" to carry out our study.
Conflict-of-interest statement: The authors have no financial relationships to disclose.
Data sharing statement: No additional data are available.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See:
Corresponding author: Fabrício Freire de Melo, PhD, Professor, Multidisciplinary Institute of Health, Federal University of Bahia, Hormindo Barros Street, 58, Candeias, Vitória da Conquista 45029-094, Bahia, Brazil.
Received: May 13, 2021
Peer-review started: May 13, 2021
First decision: July 4, 2021
Revised: July 15, 2021
Accepted: April 27, 2022
Article in press: April 27, 2022
Published online: May 16, 2022
Research background

Computer vision allied with deep learning, especially through the use of deep convolutional neural networks, has been increasingly employed in the automation of medical image analysis. Among these are endoscopic images, which are of great importance in the evaluation of a number of gastroenterological diseases.

Research motivation

Endoscopic findings constitute the diagnostic definition for esophagitis, a multietiological condition with significant impacts on quality of life and the possibility of evolution to a series of complications. Automating the identification of findings suggestive of esophageal inflammation using artificial intelligence could add great value to the evaluation and management of this clinical condition.

Research objectives

To identify whether a densely connected convolutional neural network with pre-trained and fine-tuned weights is able to binary classify esophageal Z-line endoscopic images according to the presence or absence of esophagitis.

Research methods

Endoscopic images of 1932 patients with a diagnosis of esophagitis and 1663 patients were splitted in training (80%) and test (20%) and used to develop and evaluate a binary deep learning classifier built using a pre-trained DenseNet-201 architecture. The classifier model performance was evaluated in the test set according to accuracy, sensitivity, specificity and area under the receiver operating characteristic curve.

Research results

The proposed model was able to diagnose esophagitis in the validation set with sensitivity of 93.18 and specificity of 93.46, demonstrating the feasibility of using deep transfer learning to discriminate normal from damaged mucosa in endoscopic images of the same anatomical segment. It remains to be investigated whether, by means of a more diverse set of images, this technique can be proposed to identify different types of esophageal abnormalities, and potentially in other organs.

Research conclusions

Convolutional neural networks with transfer learning for automated analysis of endoscopic images, as proposed in this study, demonstrate potential for incorporation into clinical practice as a clinical decision support tool, mainly benefiting scarce resources settings.

Research perspectives

Sets of endoscopic images representative of various clinical conditions should be published, in order to allow the findings of this study to be externally validated and for new models with different classificatory approaches to emerge.