Cargando…

A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models

Endoscopic procedures for diagnosing gastrointestinal tract findings depend on specialist experience and inter-observer variability. This variability can cause minor lesions to be missed and prevent early diagnosis. In this study, deep learning-based hybrid stacking ensemble modeling has been propos...

Descripción completa

Detalles Bibliográficos
Autores principales: Sivari, Esra, Bostanci, Erkan, Guzel, Mehmet Serdar, Acici, Koray, Asuroglu, Tunc, Ercelebi Ayyildiz, Tulin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9954881/
https://www.ncbi.nlm.nih.gov/pubmed/36832205
http://dx.doi.org/10.3390/diagnostics13040720
_version_ 1784894222513471488
author Sivari, Esra
Bostanci, Erkan
Guzel, Mehmet Serdar
Acici, Koray
Asuroglu, Tunc
Ercelebi Ayyildiz, Tulin
author_facet Sivari, Esra
Bostanci, Erkan
Guzel, Mehmet Serdar
Acici, Koray
Asuroglu, Tunc
Ercelebi Ayyildiz, Tulin
author_sort Sivari, Esra
collection PubMed
description Endoscopic procedures for diagnosing gastrointestinal tract findings depend on specialist experience and inter-observer variability. This variability can cause minor lesions to be missed and prevent early diagnosis. In this study, deep learning-based hybrid stacking ensemble modeling has been proposed for detecting and classifying gastrointestinal system findings, aiming at early diagnosis with high accuracy and sensitive measurements and saving workload to help the specialist and objectivity in endoscopic diagnosis. In the first level of the proposed bi-level stacking ensemble approach, predictions are obtained by applying 5-fold cross-validation to three new CNN models. A machine learning classifier selected at the second level is trained according to the obtained predictions, and the final classification result is reached. The performances of the stacking models were compared with the performances of the deep learning models, and McNemar’s statistical test was applied to support the results. According to the experimental results, stacking ensemble models performed with a significant difference with 98.42% ACC and 98.19% MCC in the KvasirV2 dataset and 98.53% ACC and 98.39% MCC in the HyperKvasir dataset. This study is the first to offer a new learning-oriented approach that efficiently evaluates CNN features and provides objective and reliable results with statistical testing compared to state-of-the-art studies on the subject. The proposed approach improves the performance of deep learning models and outperforms the state-of-the-art studies in the literature.
format Online
Article
Text
id pubmed-9954881
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-99548812023-02-25 A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models Sivari, Esra Bostanci, Erkan Guzel, Mehmet Serdar Acici, Koray Asuroglu, Tunc Ercelebi Ayyildiz, Tulin Diagnostics (Basel) Article Endoscopic procedures for diagnosing gastrointestinal tract findings depend on specialist experience and inter-observer variability. This variability can cause minor lesions to be missed and prevent early diagnosis. In this study, deep learning-based hybrid stacking ensemble modeling has been proposed for detecting and classifying gastrointestinal system findings, aiming at early diagnosis with high accuracy and sensitive measurements and saving workload to help the specialist and objectivity in endoscopic diagnosis. In the first level of the proposed bi-level stacking ensemble approach, predictions are obtained by applying 5-fold cross-validation to three new CNN models. A machine learning classifier selected at the second level is trained according to the obtained predictions, and the final classification result is reached. The performances of the stacking models were compared with the performances of the deep learning models, and McNemar’s statistical test was applied to support the results. According to the experimental results, stacking ensemble models performed with a significant difference with 98.42% ACC and 98.19% MCC in the KvasirV2 dataset and 98.53% ACC and 98.39% MCC in the HyperKvasir dataset. This study is the first to offer a new learning-oriented approach that efficiently evaluates CNN features and provides objective and reliable results with statistical testing compared to state-of-the-art studies on the subject. The proposed approach improves the performance of deep learning models and outperforms the state-of-the-art studies in the literature. MDPI 2023-02-14 /pmc/articles/PMC9954881/ /pubmed/36832205 http://dx.doi.org/10.3390/diagnostics13040720 Text en © 2023 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
Sivari, Esra
Bostanci, Erkan
Guzel, Mehmet Serdar
Acici, Koray
Asuroglu, Tunc
Ercelebi Ayyildiz, Tulin
A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models
title A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models
title_full A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models
title_fullStr A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models
title_full_unstemmed A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models
title_short A New Approach for Gastrointestinal Tract Findings Detection and Classification: Deep Learning-Based Hybrid Stacking Ensemble Models
title_sort new approach for gastrointestinal tract findings detection and classification: deep learning-based hybrid stacking ensemble models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9954881/
https://www.ncbi.nlm.nih.gov/pubmed/36832205
http://dx.doi.org/10.3390/diagnostics13040720
work_keys_str_mv AT sivariesra anewapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT bostancierkan anewapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT guzelmehmetserdar anewapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT acicikoray anewapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT asuroglutunc anewapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT ercelebiayyildiztulin anewapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT sivariesra newapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT bostancierkan newapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT guzelmehmetserdar newapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT acicikoray newapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT asuroglutunc newapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels
AT ercelebiayyildiztulin newapproachforgastrointestinaltractfindingsdetectionandclassificationdeeplearningbasedhybridstackingensemblemodels