Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology

Background: In medical imaging, classifying images of colon cancer pathology is still an essential challenge, especially for facilitating early diagnosis and successful intervention. Recently, Vision Transformer (ViT) models have demonstrated great promise for a variety of computer vision tasks, in...

Full description

Saved in:
Bibliographic Details
Main Authors: Rudy Eko Prasetya, M. Arief Soeleman, Farrikh Al Zami, Affandy Affandy, Aris Marjuni, Mohammad Iqbal Saryuddin Assaqty
Format: Article
Language:English
Published: Universitas Nusantara PGRI Kediri 2025-07-01
Series:Intensif: Jurnal Ilmiah Penelitian Teknologi dan Penerapan Sistem Informasi
Subjects:
Online Access:https://ojs.unpkediri.ac.id/index.php/intensif/article/view/24918
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849319580405596160
author Rudy Eko Prasetya
M. Arief Soeleman
Farrikh Al Zami
Affandy Affandy
Aris Marjuni
Mohammad Iqbal Saryuddin Assaqty
author_facet Rudy Eko Prasetya
M. Arief Soeleman
Farrikh Al Zami
Affandy Affandy
Aris Marjuni
Mohammad Iqbal Saryuddin Assaqty
author_sort Rudy Eko Prasetya
collection DOAJ
description Background: In medical imaging, classifying images of colon cancer pathology is still an essential challenge, especially for facilitating early diagnosis and successful intervention. Recently, Vision Transformer (ViT) models have demonstrated great promise for a variety of computer vision tasks, including the classification of medical images. However, the lack of annotated medical datasets and the intrinsic unpredictability of histopathology pictures sometimes restrict their performance. Objective: This study aims to enhance the performance of ViT models in colon cancer pathology classification by introducing a targeted data augmentation strategy, with a particular focus on rotation-based augmentation. Methods: We proposed a data augmentation pipeline that uses controlled changes to improve the number and diversity of training data. Like Rotation, Flip and Geometry are emphasized to replicate the real-world tissue orientation variations that are frequently seen in colon pathology slides. 10,000 JPEG pictures of colon cancer pathology, each with a resolution of 768 x 768 pixels, are used to train the models. We use models trained with and without the suggested augmentation pipeline to compare ViT performance across accuracy, sensitivity, and specificity in order to assess the impact of augmentation. Results: According to study results, rotation-based augmentation enhances ViT performance, achieving up to 99.30% accuracy and 99.50% sensitivity while preserving training times. In real-world pathology settings, where slide orientation varies greatly and can affect categorization consistency, these enhancements are especially pertinent. Conclusion: The proposed rotation-centric data augmentation technique enhances the performance of the ViT model in the classification of images showing colon cancer pathology.
format Article
id doaj-art-eb06a389f8f64ba895bca132dce82f98
institution Kabale University
issn 2580-409X
2549-6824
language English
publishDate 2025-07-01
publisher Universitas Nusantara PGRI Kediri
record_format Article
series Intensif: Jurnal Ilmiah Penelitian Teknologi dan Penerapan Sistem Informasi
spelling doaj-art-eb06a389f8f64ba895bca132dce82f982025-08-20T03:50:22ZengUniversitas Nusantara PGRI KediriIntensif: Jurnal Ilmiah Penelitian Teknologi dan Penerapan Sistem Informasi2580-409X2549-68242025-07-019210.29407/intensif.v9i2.24918Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer PathologyRudy Eko Prasetya0https://orcid.org/0009-0001-5303-0890M. Arief Soeleman1https://orcid.org/0000-0001-6099-7023Farrikh Al Zami2https://orcid.org/0000-0003-2669-3864Affandy Affandy3https://orcid.org/0000-0003-1897-8261Aris Marjuni4https://orcid.org/0000-0002-4072-3081Mohammad Iqbal Saryuddin Assaqty5https://orcid.org/0000-0001-7274-6299Unuversitas Dian NuswantoroUniversitas Dian Nuswantoro SemarangUniversitas Dian Nuswantoro SemarangUniversitas Dian Nuswantoro SemarangUniversitas Dian Nuswantoro SemarangSouth China University of Technology Background: In medical imaging, classifying images of colon cancer pathology is still an essential challenge, especially for facilitating early diagnosis and successful intervention. Recently, Vision Transformer (ViT) models have demonstrated great promise for a variety of computer vision tasks, including the classification of medical images. However, the lack of annotated medical datasets and the intrinsic unpredictability of histopathology pictures sometimes restrict their performance. Objective: This study aims to enhance the performance of ViT models in colon cancer pathology classification by introducing a targeted data augmentation strategy, with a particular focus on rotation-based augmentation. Methods: We proposed a data augmentation pipeline that uses controlled changes to improve the number and diversity of training data. Like Rotation, Flip and Geometry are emphasized to replicate the real-world tissue orientation variations that are frequently seen in colon pathology slides. 10,000 JPEG pictures of colon cancer pathology, each with a resolution of 768 x 768 pixels, are used to train the models. We use models trained with and without the suggested augmentation pipeline to compare ViT performance across accuracy, sensitivity, and specificity in order to assess the impact of augmentation. Results: According to study results, rotation-based augmentation enhances ViT performance, achieving up to 99.30% accuracy and 99.50% sensitivity while preserving training times. In real-world pathology settings, where slide orientation varies greatly and can affect categorization consistency, these enhancements are especially pertinent. Conclusion: The proposed rotation-centric data augmentation technique enhances the performance of the ViT model in the classification of images showing colon cancer pathology. https://ojs.unpkediri.ac.id/index.php/intensif/article/view/24918Vision TransformerData AugmentationImages ClassificationColon Cancer
spellingShingle Rudy Eko Prasetya
M. Arief Soeleman
Farrikh Al Zami
Affandy Affandy
Aris Marjuni
Mohammad Iqbal Saryuddin Assaqty
Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology
Intensif: Jurnal Ilmiah Penelitian Teknologi dan Penerapan Sistem Informasi
Vision Transformer
Data Augmentation
Images Classification
Colon Cancer
title Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology
title_full Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology
title_fullStr Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology
title_full_unstemmed Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology
title_short Enhancing Vision Transformer Performance with Rotation Based Augmentation for Classifying Images of Colon Cancer Pathology
title_sort enhancing vision transformer performance with rotation based augmentation for classifying images of colon cancer pathology
topic Vision Transformer
Data Augmentation
Images Classification
Colon Cancer
url https://ojs.unpkediri.ac.id/index.php/intensif/article/view/24918
work_keys_str_mv AT rudyekoprasetya enhancingvisiontransformerperformancewithrotationbasedaugmentationforclassifyingimagesofcoloncancerpathology
AT mariefsoeleman enhancingvisiontransformerperformancewithrotationbasedaugmentationforclassifyingimagesofcoloncancerpathology
AT farrikhalzami enhancingvisiontransformerperformancewithrotationbasedaugmentationforclassifyingimagesofcoloncancerpathology
AT affandyaffandy enhancingvisiontransformerperformancewithrotationbasedaugmentationforclassifyingimagesofcoloncancerpathology
AT arismarjuni enhancingvisiontransformerperformancewithrotationbasedaugmentationforclassifyingimagesofcoloncancerpathology
AT mohammadiqbalsaryuddinassaqty enhancingvisiontransformerperformancewithrotationbasedaugmentationforclassifyingimagesofcoloncancerpathology