An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image Analysis

Peptic ulcers and stomach cancer are common conditions that impact the gastrointestinal (GI) system. Wireless capsule endoscopy (WCE) has emerged as a widely used, noninvasive technique for diagnosing these issues, providing valuable insights through the detailed imaging of the GI tract. Therefore,...

Full description

Saved in:
Bibliographic Details
Main Authors: Sameh Abd El-Ghany, Mahmood A. Mahmood, A. A. Abd El-Aziz
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/22/10243
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850149312937328640
author Sameh Abd El-Ghany
Mahmood A. Mahmood
A. A. Abd El-Aziz
author_facet Sameh Abd El-Ghany
Mahmood A. Mahmood
A. A. Abd El-Aziz
author_sort Sameh Abd El-Ghany
collection DOAJ
description Peptic ulcers and stomach cancer are common conditions that impact the gastrointestinal (GI) system. Wireless capsule endoscopy (WCE) has emerged as a widely used, noninvasive technique for diagnosing these issues, providing valuable insights through the detailed imaging of the GI tract. Therefore, an early and accurate diagnosis of GI diseases is crucial for effective treatment. This paper introduces the Intelligent Learning Rate Controller (ILRC) mechanism that optimizes the training of deep learning (DL) models by adaptively adjusting the learning rate (LR) based on training progress. This helps improve convergence speed and reduce the risk of overfitting. The ILRC was applied to four DL models: EfficientNet-B0, ResNet101v2, InceptionV3, and InceptionResNetV2. These models were further enhanced using transfer learning, freezing layers, fine-tuning techniques, residual learning, and modern regularization methods. The models were evaluated on two datasets, the Kvasir-Capsule and KVASIR v2 datasets, which contain WCE images. The results demonstrated that the models, particularly when using ILRC, outperformed existing state-of-the-art methods in accuracy. On the Kvasir-Capsule dataset, the models achieved accuracies of up to 99.906%, and on the Kvasir-v2 dataset, they achieved up to 98.062%. This combination of techniques offers a robust solution for automating the detection of GI abnormalities in WCE images, significantly enhancing diagnostic efficiency and accuracy in clinical settings.
format Article
id doaj-art-4ebb32ae50d341eeb74db38a8dea030c
institution OA Journals
issn 2076-3417
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-4ebb32ae50d341eeb74db38a8dea030c2025-08-20T02:26:58ZengMDPI AGApplied Sciences2076-34172024-11-0114221024310.3390/app142210243An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image AnalysisSameh Abd El-Ghany0Mahmood A. Mahmood1A. A. Abd El-Aziz2Department of Information Systems, College of Computer and Information Sciences, Jouf University, Sakakah 72388, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, Jouf University, Sakakah 72388, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, Jouf University, Sakakah 72388, Saudi ArabiaPeptic ulcers and stomach cancer are common conditions that impact the gastrointestinal (GI) system. Wireless capsule endoscopy (WCE) has emerged as a widely used, noninvasive technique for diagnosing these issues, providing valuable insights through the detailed imaging of the GI tract. Therefore, an early and accurate diagnosis of GI diseases is crucial for effective treatment. This paper introduces the Intelligent Learning Rate Controller (ILRC) mechanism that optimizes the training of deep learning (DL) models by adaptively adjusting the learning rate (LR) based on training progress. This helps improve convergence speed and reduce the risk of overfitting. The ILRC was applied to four DL models: EfficientNet-B0, ResNet101v2, InceptionV3, and InceptionResNetV2. These models were further enhanced using transfer learning, freezing layers, fine-tuning techniques, residual learning, and modern regularization methods. The models were evaluated on two datasets, the Kvasir-Capsule and KVASIR v2 datasets, which contain WCE images. The results demonstrated that the models, particularly when using ILRC, outperformed existing state-of-the-art methods in accuracy. On the Kvasir-Capsule dataset, the models achieved accuracies of up to 99.906%, and on the Kvasir-v2 dataset, they achieved up to 98.062%. This combination of techniques offers a robust solution for automating the detection of GI abnormalities in WCE images, significantly enhancing diagnostic efficiency and accuracy in clinical settings.https://www.mdpi.com/2076-3417/14/22/10243gastrointestinalwireless capsule endoscopyEfficientNet-B0balancingdata augmentation
spellingShingle Sameh Abd El-Ghany
Mahmood A. Mahmood
A. A. Abd El-Aziz
An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image Analysis
Applied Sciences
gastrointestinal
wireless capsule endoscopy
EfficientNet-B0
balancing
data augmentation
title An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image Analysis
title_full An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image Analysis
title_fullStr An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image Analysis
title_full_unstemmed An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image Analysis
title_short An Accurate Deep Learning-Based Computer-Aided Diagnosis System for Gastrointestinal Disease Detection Using Wireless Capsule Endoscopy Image Analysis
title_sort accurate deep learning based computer aided diagnosis system for gastrointestinal disease detection using wireless capsule endoscopy image analysis
topic gastrointestinal
wireless capsule endoscopy
EfficientNet-B0
balancing
data augmentation
url https://www.mdpi.com/2076-3417/14/22/10243
work_keys_str_mv AT samehabdelghany anaccuratedeeplearningbasedcomputeraideddiagnosissystemforgastrointestinaldiseasedetectionusingwirelesscapsuleendoscopyimageanalysis
AT mahmoodamahmood anaccuratedeeplearningbasedcomputeraideddiagnosissystemforgastrointestinaldiseasedetectionusingwirelesscapsuleendoscopyimageanalysis
AT aaabdelaziz anaccuratedeeplearningbasedcomputeraideddiagnosissystemforgastrointestinaldiseasedetectionusingwirelesscapsuleendoscopyimageanalysis
AT samehabdelghany accuratedeeplearningbasedcomputeraideddiagnosissystemforgastrointestinaldiseasedetectionusingwirelesscapsuleendoscopyimageanalysis
AT mahmoodamahmood accuratedeeplearningbasedcomputeraideddiagnosissystemforgastrointestinaldiseasedetectionusingwirelesscapsuleendoscopyimageanalysis
AT aaabdelaziz accuratedeeplearningbasedcomputeraideddiagnosissystemforgastrointestinaldiseasedetectionusingwirelesscapsuleendoscopyimageanalysis