Cargando…

A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images

The first step in the diagnosis of gastric abnormalities is the detection of various abnormalities in the human gastrointestinal tract. Manual examination of endoscopy images relies on a medical practitioner’s expertise to identify inflammatory regions on the inner surface of the gastrointestinal tr...

Descripción completa

Detalles Bibliográficos
Autores principales: Ramamurthy, Karthik, George, Timothy Thomas, Shah, Yash, Sasidhar, Parasa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9600128/
https://www.ncbi.nlm.nih.gov/pubmed/36292006
http://dx.doi.org/10.3390/diagnostics12102316
_version_ 1784816764373172224
author Ramamurthy, Karthik
George, Timothy Thomas
Shah, Yash
Sasidhar, Parasa
author_facet Ramamurthy, Karthik
George, Timothy Thomas
Shah, Yash
Sasidhar, Parasa
author_sort Ramamurthy, Karthik
collection PubMed
description The first step in the diagnosis of gastric abnormalities is the detection of various abnormalities in the human gastrointestinal tract. Manual examination of endoscopy images relies on a medical practitioner’s expertise to identify inflammatory regions on the inner surface of the gastrointestinal tract. The length of the alimentary canal and the large volume of images obtained from endoscopic procedures make traditional detection methods time consuming and laborious. Recently, deep learning architectures have achieved better results in the classification of endoscopy images. However, visual similarities between different portions of the gastrointestinal tract pose a challenge for effective disease detection. This work proposes a novel system for the classification of endoscopy images by focusing on feature mining through convolutional neural networks (CNN). The model presented is built by combining a state-of-the-art architecture (i.e., EfficientNet B0) with a custom-built CNN architecture named Effimix. The proposed Effimix model employs a combination of squeeze and excitation layers and self-normalising activation layers for precise classification of gastrointestinal diseases. Experimental observations on the HyperKvasir dataset confirm the effectiveness of the proposed architecture for the classification of endoscopy images. The proposed model yields an accuracy of 97.99%, with an F1 score, precision, and recall of 97%, 97%, and 98%, respectively, which is significantly higher compared to the existing works.
format Online
Article
Text
id pubmed-9600128
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96001282022-10-27 A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images Ramamurthy, Karthik George, Timothy Thomas Shah, Yash Sasidhar, Parasa Diagnostics (Basel) Article The first step in the diagnosis of gastric abnormalities is the detection of various abnormalities in the human gastrointestinal tract. Manual examination of endoscopy images relies on a medical practitioner’s expertise to identify inflammatory regions on the inner surface of the gastrointestinal tract. The length of the alimentary canal and the large volume of images obtained from endoscopic procedures make traditional detection methods time consuming and laborious. Recently, deep learning architectures have achieved better results in the classification of endoscopy images. However, visual similarities between different portions of the gastrointestinal tract pose a challenge for effective disease detection. This work proposes a novel system for the classification of endoscopy images by focusing on feature mining through convolutional neural networks (CNN). The model presented is built by combining a state-of-the-art architecture (i.e., EfficientNet B0) with a custom-built CNN architecture named Effimix. The proposed Effimix model employs a combination of squeeze and excitation layers and self-normalising activation layers for precise classification of gastrointestinal diseases. Experimental observations on the HyperKvasir dataset confirm the effectiveness of the proposed architecture for the classification of endoscopy images. The proposed model yields an accuracy of 97.99%, with an F1 score, precision, and recall of 97%, 97%, and 98%, respectively, which is significantly higher compared to the existing works. MDPI 2022-09-26 /pmc/articles/PMC9600128/ /pubmed/36292006 http://dx.doi.org/10.3390/diagnostics12102316 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Ramamurthy, Karthik
George, Timothy Thomas
Shah, Yash
Sasidhar, Parasa
A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images
title A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images
title_full A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images
title_fullStr A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images
title_full_unstemmed A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images
title_short A Novel Multi-Feature Fusion Method for Classification of Gastrointestinal Diseases Using Endoscopy Images
title_sort novel multi-feature fusion method for classification of gastrointestinal diseases using endoscopy images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9600128/
https://www.ncbi.nlm.nih.gov/pubmed/36292006
http://dx.doi.org/10.3390/diagnostics12102316
work_keys_str_mv AT ramamurthykarthik anovelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages
AT georgetimothythomas anovelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages
AT shahyash anovelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages
AT sasidharparasa anovelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages
AT ramamurthykarthik novelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages
AT georgetimothythomas novelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages
AT shahyash novelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages
AT sasidharparasa novelmultifeaturefusionmethodforclassificationofgastrointestinaldiseasesusingendoscopyimages