PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy image

Colon polyps are small, precancerous growths in the colon that can indicate colorectal cancer (CRC), a disease that has a significant impact on public health. A colonoscopy is a medical procedure that helps detect colon polyps. However, the manual examination for identifying the type of polyps can b...

Full description

Saved in:
Bibliographic Details
Main Authors: Khaled Eabne Delowar, Mohammed Borhan Uddin, Md Khaliluzzaman, Riadul Islam Rabbi, Md Jakir Hossen, M. Moazzam Hossen
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Informatics in Medicine Unlocked
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352914825000425
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850126496889307136
author Khaled Eabne Delowar
Mohammed Borhan Uddin
Md Khaliluzzaman
Riadul Islam Rabbi
Md Jakir Hossen
M. Moazzam Hossen
author_facet Khaled Eabne Delowar
Mohammed Borhan Uddin
Md Khaliluzzaman
Riadul Islam Rabbi
Md Jakir Hossen
M. Moazzam Hossen
author_sort Khaled Eabne Delowar
collection DOAJ
description Colon polyps are small, precancerous growths in the colon that can indicate colorectal cancer (CRC), a disease that has a significant impact on public health. A colonoscopy is a medical procedure that helps detect colon polyps. However, the manual examination for identifying the type of polyps can be time-consuming, tedious, and prone to human error. Automatic classification of polyps through colonoscopy images can be more efficient. However, there are currently no specialized methods for the classification of polyps from colonoscopy; however, several state-of-the-art CNN models can classify polyps. We are introducing a new CNN-based model called PolyNet, a model that shows the best accuracy of the polyps classification from the multiple models and which also performs better than pre-trained models such as VGG16, ResNet50, DenseNetV3, MobileNetV3, and InceptionV3, as well as nine other customized CNN-based models for classification. This study provides a sensitivity analysis to demonstrate how slight modifications in the network's architecture can impact the balance between accuracy and performance. We examined different CNN architectures and developed a good convolutional neural network (CNN) model for correctly predicting colon polyps using the Kvasir dataset. The self-attention mechanism is incorporated in the best CNN model, i.e., PolypNet, to ensure better accuracy. To compare, DenseNetV3, MobileNet-V3, Inception-V3, VGG16, and ResNet50 get 73.87 %, 69.38 %, 61.12 %, 84.00 %, and 86.12 % of accuracy on the Kvasir dataset, while PolypNet with attention archives 86 % accuracy, 86 % precision, 85 % recall, and an 86 % F1-score.
format Article
id doaj-art-841f4361607b4274b0e737b2cec2bdfe
institution OA Journals
issn 2352-9148
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Informatics in Medicine Unlocked
spelling doaj-art-841f4361607b4274b0e737b2cec2bdfe2025-08-20T02:33:55ZengElsevierInformatics in Medicine Unlocked2352-91482025-01-015610165410.1016/j.imu.2025.101654PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy imageKhaled Eabne Delowar0Mohammed Borhan Uddin1Md Khaliluzzaman2Riadul Islam Rabbi3Md Jakir Hossen4M. Moazzam Hossen5Chittagong University of Engineering and Technology (CUET), Chittagong, Bangladesh; International Islamic University Chittagong (IIUC), Chittagong, BangladeshChittagong University of Engineering and Technology (CUET), Chittagong, Bangladesh; International Islamic University Chittagong (IIUC), Chittagong, BangladeshInternational Islamic University Chittagong (IIUC), Chittagong, BangladeshFaculty of Engineering and Technology, Multimedia University, Melaka, MalaysiaFaculty of Engineering and Technology, Multimedia University, Melaka, Malaysia; Corresponding author.International Islamic University Chittagong (IIUC), Chittagong, BangladeshColon polyps are small, precancerous growths in the colon that can indicate colorectal cancer (CRC), a disease that has a significant impact on public health. A colonoscopy is a medical procedure that helps detect colon polyps. However, the manual examination for identifying the type of polyps can be time-consuming, tedious, and prone to human error. Automatic classification of polyps through colonoscopy images can be more efficient. However, there are currently no specialized methods for the classification of polyps from colonoscopy; however, several state-of-the-art CNN models can classify polyps. We are introducing a new CNN-based model called PolyNet, a model that shows the best accuracy of the polyps classification from the multiple models and which also performs better than pre-trained models such as VGG16, ResNet50, DenseNetV3, MobileNetV3, and InceptionV3, as well as nine other customized CNN-based models for classification. This study provides a sensitivity analysis to demonstrate how slight modifications in the network's architecture can impact the balance between accuracy and performance. We examined different CNN architectures and developed a good convolutional neural network (CNN) model for correctly predicting colon polyps using the Kvasir dataset. The self-attention mechanism is incorporated in the best CNN model, i.e., PolypNet, to ensure better accuracy. To compare, DenseNetV3, MobileNet-V3, Inception-V3, VGG16, and ResNet50 get 73.87 %, 69.38 %, 61.12 %, 84.00 %, and 86.12 % of accuracy on the Kvasir dataset, while PolypNet with attention archives 86 % accuracy, 86 % precision, 85 % recall, and an 86 % F1-score.http://www.sciencedirect.com/science/article/pii/S2352914825000425Colon polypConvolutional neural network (CNN)Self-attentionTransfer learningColonoscopy
spellingShingle Khaled Eabne Delowar
Mohammed Borhan Uddin
Md Khaliluzzaman
Riadul Islam Rabbi
Md Jakir Hossen
M. Moazzam Hossen
PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy image
Informatics in Medicine Unlocked
Colon polyp
Convolutional neural network (CNN)
Self-attention
Transfer learning
Colonoscopy
title PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy image
title_full PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy image
title_fullStr PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy image
title_full_unstemmed PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy image
title_short PolyNet: A self-attention based CNN model for classifying the colon polyp from colonoscopy image
title_sort polynet a self attention based cnn model for classifying the colon polyp from colonoscopy image
topic Colon polyp
Convolutional neural network (CNN)
Self-attention
Transfer learning
Colonoscopy
url http://www.sciencedirect.com/science/article/pii/S2352914825000425
work_keys_str_mv AT khaledeabnedelowar polynetaselfattentionbasedcnnmodelforclassifyingthecolonpolypfromcolonoscopyimage
AT mohammedborhanuddin polynetaselfattentionbasedcnnmodelforclassifyingthecolonpolypfromcolonoscopyimage
AT mdkhaliluzzaman polynetaselfattentionbasedcnnmodelforclassifyingthecolonpolypfromcolonoscopyimage
AT riadulislamrabbi polynetaselfattentionbasedcnnmodelforclassifyingthecolonpolypfromcolonoscopyimage
AT mdjakirhossen polynetaselfattentionbasedcnnmodelforclassifyingthecolonpolypfromcolonoscopyimage
AT mmoazzamhossen polynetaselfattentionbasedcnnmodelforclassifyingthecolonpolypfromcolonoscopyimage