Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers

The rapid increase in the number of medical image repositories nowadays has led to problems in managing and retrieving medical visual data. This has proved the necessity of Content-Based Image Retrieval (CBIR) with the aim of facilitating the investigation of such medical imagery. One of the most se...

Full description

Saved in:
Bibliographic Details
Main Authors: Ahmed Yahya, Dalya Khaled, Waleed Al-Azzawi, Tawfeeq Alghazali, H. Sabah Jabr, R. Madhat Abdulla, M. Kadhim Abbas Al-Maeeni, N. Hussin Alwan, S. Saad Najeeb, Kh. T. Falih
Format: Article
Language:English
Published: OICC Press 2022-09-01
Series:Majlesi Journal of Electrical Engineering
Subjects:
Online Access:https://oiccpress.com/mjee/article/view/4956
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850283557557108736
author Ahmed Yahya
Dalya Khaled
Waleed Al-Azzawi
Tawfeeq Alghazali
H. Sabah Jabr
R. Madhat Abdulla
M. Kadhim Abbas Al-Maeeni
N. Hussin Alwan
S. Saad Najeeb
Kh. T. Falih
author_facet Ahmed Yahya
Dalya Khaled
Waleed Al-Azzawi
Tawfeeq Alghazali
H. Sabah Jabr
R. Madhat Abdulla
M. Kadhim Abbas Al-Maeeni
N. Hussin Alwan
S. Saad Najeeb
Kh. T. Falih
author_sort Ahmed Yahya
collection DOAJ
description The rapid increase in the number of medical image repositories nowadays has led to problems in managing and retrieving medical visual data. This has proved the necessity of Content-Based Image Retrieval (CBIR) with the aim of facilitating the investigation of such medical imagery. One of the most serious challenges that require special attention is the representational quality of the embeddings generated by the retrieval pipelines. These embeddings should include global and local features to obtain more useful information from the input data. To fill this gap, in this paper, we propose a CBIR framework that utilizes the power of deep neural networks to efficiently classify and fetch the most related medical images with respect to a query image. Our proposed model is based on combining Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) and learns to capture both the locality and also the globality of high-level feature maps. Our method is trained to encode the images in the database and outputs a ranking list containing the most similar image to the least similar one to the query. To conduct our experiments, an intermodal dataset containing ten classes with five different modalities is used to train and assess the proposed framework. The results show an average classification accuracy of 95.32 % and a mean average precision of 0.61. Our proposed framework can be very effective in retrieving multimodal medical images with the images of different organs in the body.
format Article
id doaj-art-2e57c121452b4654b15e5341dd4c2749
institution OA Journals
issn 2345-377X
2345-3796
language English
publishDate 2022-09-01
publisher OICC Press
record_format Article
series Majlesi Journal of Electrical Engineering
spelling doaj-art-2e57c121452b4654b15e5341dd4c27492025-08-20T01:47:45ZengOICC PressMajlesi Journal of Electrical Engineering2345-377X2345-37962022-09-0116310.30486/mjee.2022.696500Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision TransformersAhmed Yahya0Dalya Khaled1Waleed Al-Azzawi2Tawfeeq Alghazali3H. Sabah Jabr4R. Madhat Abdulla5M. Kadhim Abbas Al-Maeeni6N. Hussin Alwan7S. Saad Najeeb8Kh. T. Falih9Department of nursing, Al-Hadba University College, IraqAl-Manara College for Medical Sciences, Maysan, IraqMedical Lab. Techniques department, College of Medical Technology, Al-Farahidi University, IraqCollege of Media, Department of Journalism, The Islamic University in Najaf, Najaf, IraqAnesthesia Techniques Department, Al-Mustaqbal University College, Babylon, IraqThe University of Mashreq, Baghdad, IraqAl-Nisour University College, Baghdad, IraqDepartment of Nursing, Al-Zahrawi University College, Karbala, IraqAl-Esraa University College, Baghdad, IraqNew Era and Development in Civil Engineering Research Group, Scientific Research Center, Al-Ayen University, Thi-Qar, Iraq.The rapid increase in the number of medical image repositories nowadays has led to problems in managing and retrieving medical visual data. This has proved the necessity of Content-Based Image Retrieval (CBIR) with the aim of facilitating the investigation of such medical imagery. One of the most serious challenges that require special attention is the representational quality of the embeddings generated by the retrieval pipelines. These embeddings should include global and local features to obtain more useful information from the input data. To fill this gap, in this paper, we propose a CBIR framework that utilizes the power of deep neural networks to efficiently classify and fetch the most related medical images with respect to a query image. Our proposed model is based on combining Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) and learns to capture both the locality and also the globality of high-level feature maps. Our method is trained to encode the images in the database and outputs a ranking list containing the most similar image to the least similar one to the query. To conduct our experiments, an intermodal dataset containing ten classes with five different modalities is used to train and assess the proposed framework. The results show an average classification accuracy of 95.32 % and a mean average precision of 0.61. Our proposed framework can be very effective in retrieving multimodal medical images with the images of different organs in the body.https://oiccpress.com/mjee/article/view/4956Content-based image retrievalConvolutional neural networksEnsemble Learningmedical image retrievalsimilarity-based visual searchvision transformers. deep learning
spellingShingle Ahmed Yahya
Dalya Khaled
Waleed Al-Azzawi
Tawfeeq Alghazali
H. Sabah Jabr
R. Madhat Abdulla
M. Kadhim Abbas Al-Maeeni
N. Hussin Alwan
S. Saad Najeeb
Kh. T. Falih
Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers
Majlesi Journal of Electrical Engineering
Content-based image retrieval
Convolutional neural networks
Ensemble Learning
medical image retrieval
similarity-based visual search
vision transformers. deep learning
title Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers
title_full Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers
title_fullStr Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers
title_full_unstemmed Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers
title_short Medical Image Retrieval Based on Ensemble Learning using Convolutional Neural Networks and Vision Transformers
title_sort medical image retrieval based on ensemble learning using convolutional neural networks and vision transformers
topic Content-based image retrieval
Convolutional neural networks
Ensemble Learning
medical image retrieval
similarity-based visual search
vision transformers. deep learning
url https://oiccpress.com/mjee/article/view/4956
work_keys_str_mv AT ahmedyahya medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT dalyakhaled medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT waleedalazzawi medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT tawfeeqalghazali medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT hsabahjabr medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT rmadhatabdulla medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT mkadhimabbasalmaeeni medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT nhussinalwan medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT ssaadnajeeb medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers
AT khtfalih medicalimageretrievalbasedonensemblelearningusingconvolutionalneuralnetworksandvisiontransformers