Analysis of Image Augmentation Effects on MobileNetV2 for Gastroesophageal Reflux Disease Endoscopy Image Classification
DOI:
10.33395/sinkron.v10i3.16510Keywords:
Deep Learning Classification, GERD, Image Augmentation, Medical Image Classification, MobileNetV2, RecallAbstract
Gastroesophageal Reflux Disease (GERD) is a common digestive tract disorder, and endoscopic image-based diagnosis still faces challenges due to variations in lighting, image capture angles, and limited data that can cause deep learning models to overfit and reduce generalization capabilities. While previous studies frequently prioritize overall accuracy, this study distinguishes itself by focusing on increasing recall as a critical indicator of clinical sensitivity for positive case detection. This study aims to analyze the effect of applying image augmentation on the performance of GERD endoscopic image classification using a lightweight MobileNetV2 architecture, offering a practical solution for resource-constrained clinical settings. The research methods include data collection, class mapping, 80:20 data split, and standardized preprocessing stages. Two training scenarios were compared: without augmentation and with strategic on-the-fly augmentation applied through a transfer learning approach. Evaluation was carried out using accuracy, precision, recall, F1-score, and ROC-AUC. The results showed that augmentation improved model performance, with accuracy increasing from 76.72% to 78.06%, recall increasing from 79.33% to 85.27%, F1-score increasing from 77.86% to 80.04%, and AUC increasing from 0.8317 to 0.8481. These findings indicate that the augmentation strategy effectively improves the generalization of the lightweight model, significantly reducing missed diagnoses to support early detection of GERD. In addition, the results demonstrate that applying augmentation techniques can help the model learn more robust visual features from limited medical image datasets. This approach also contributes to reducing overfitting and improving model reliability in practical clinical image analysis scenarios.
Downloads
References
Abbas, Muhammad John, Hend Alshaya, Wided Bouchelligua, Nehal Hassan, and Inzamam Mashood Nasir. 2025. “Hierarchical Multi-Stage Attention and Dynamic Expert Routing for Explainable Gastrointestinal Disease Diagnosis.” Diagnostics 15(21):1–26. doi: 10.3390/diagnostics15212714.
Abdulahi, Abdulrahman Tosho, Roseline Oluwaseun Ogundokun, and Ajiboye Raimot Adenike. 2024. “PulmoNet : A Novel Deep Learning Based Pulmonary Diseases Detection Model.” BMC Medical Imaging 1–19. doi: 10.1186/s12880-024-01227-2.
Ali Hasan, Hildan Adisqi, Risqy Siwi Pradini, and Mochammad Anshori. 2025. “Klasifikasi Spesies Jamur Beracun Agaricus Xanthodermus Dan Amanita Muscaria Menggunakan Transfer Learning Dengan Arsitektur MobileNetV2.” Jurnal Pendidikan Dan Teknologi Indonesia 5(9):2443–51. doi: 10.52436/1.jpti.785.
Bichri, Houda, Adil Chergui, and Mustapha Hain. 2024. “Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets.” International Journal of Advanced Computer Science and Applications 15(2):331–39. doi: 10.14569/IJACSA.2024.0150235.
Bisht, Akshaj Singh. 2025. “DeepGastroNet : A Deep Learning Network for Improved Gastroesophageal Reflux Disease and Gastrointestinal Polyps Classification Using Endoscopic Images.” 2025 4th International Conference on Applied Artificial Intelligence and Computing (ICAAIC) 1412–17. doi: 10.1109/ICAAIC64647.2025.11331233.
Budd, Charlie, Luis C. Garcia-Peraza Herrera, Martin Huber, Sebastien Ourselin, and Tom Vercauteren. 2023. “Rapid and Robust Endoscopic Content Area Estimation: A Lean GPU-Based Pipeline and Curated Benchmark Dataset.” Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization 11(4):1215–24. doi: 10.1080/21681163.2022.2156393.
Fang, Yu-jen, Kun-hua Lee, Riya Karmakar, Arvind Mukundan, Yaswanth Nagisetti, Chien-wei Huang, and Hsiang-chen Wang. 2025. “Transforming Endoscopic Image Classification with Spectrum-Aided Vision for Early and Accurate Cancer Identification.” Diagnostics 15(21):1–23. doi: 10.3390/diagnostics15212732.
Hicks, Steven A., Inga Strümke, Vajira Thambawita, Malek Hammou, Michael A. Riegler, Pål Halvorsen, and Sravanthi Parasa. 2022. “On Evaluation Metrics for Medical Applications of Artificial Intelligence.” Scientific Reports 12(1):1–9. doi: 10.1038/s41598-022-09954-8.
Kadar, Abdul, Abu Kowshir Bitto, Shafiqul Islam Talukder, Fokrul Islam, Mohammed Shamsul Alam, and Khandaker Mohammad. 2025. “An Explainable AI Based Deep Ensemble Transformer Framework for Gastrointestinal Disease Prediction from Endoscopic Images.” EAI Endorsed Transactioons 4:1–9. doi: 10.4108/airo.9795.
Kadar, Abdul, Muhammad Masum, Fokrul Islam Khan, Ruhul Rabbi, Arif Hossen, Khandaker Mohammad, Mohi Uddin, and Abu Kowshir Bitto. 2025. “Enhancing Endoscopic Diagnosis of GERD and Polyps : A Comparative Study of Deep Learning Models for Multi-Class Classification.” 2025 8th International Conference on Control, Robotics and Informatics (ICCRI) 16–20. doi: 10.1109/ICCRI67201.2025.11262505.
Kebaili, Aghiles, Jérôme Lapuyade-Lahorgue, and Su Ruan. 2023. “Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review.” Journal of Imaging 9(4):81. doi: 10.3390/jimaging9040081.
Khalifa, Nour Eldeen, Mohamed Loey, and Seyedali Mirjalili. 2022. “A Comprehensive Survey of Recent Trends in Deep Learning for Digital Images Augmentation.” Artificial Intelligence Review 55(3):2351–77. doi: 10.1007/s10462-021-10066-4.
Kocak, Burak, Michail E. Klontzas, Arnaldo Stanzione, Aymen Meddeb, Nathaniel Mercaldo, Oliver Díaz, and Renato Cuocolo. 2025. “Evaluation Metrics in Medical Imaging AI : Fundamentals , Pitfalls , Misapplications , and Recommendations.” European Journal of Radiology Artificial Intelligence 3(June). doi: 10.1016/j.ejrai.2025.100030.
Kowshir, Abu, Hasan Imam, Kamrul Hassan, Aka Das, and Syed Minhaz. 2025. “GastroEndoNet : Comprehensive Endoscopy Image Dataset for GERD and Polyp Detection.” Data in Brief 60:111572. doi: 10.1016/j.dib.2025.111572.
Lv, Hui, Pengfei Shan, Hongfang Shi, and Li Zhao. 2022. “An Adaptive Bilateral Filtering Method Based on Improved Convolution Kernel Used for Infrared Image Enhancement.” Signal, Image and Video Processing 16(8):2231–37. doi: 10.1007/s11760-022-02188-1.
Magalhães, Bruno, Alexandre Neto, and António Cunha. 2023. “Generative Adversarial Networks for Augmenting Endoscopy Image Datasets of Stomach Precancerous Lesions: A Review.” IEEE Access 11(November):136292–307. doi: 10.1109/ACCESS.2023.3338545.
Malik, Hassaan, Ahmad Naeem, Abolghasem Sadeghi-niaraki Rizwan, Ali Naqvi, Seung-won Lee, and Seung-won Lee. 2024. “Multi-Classification Deep Learning Models for Detection of Ulcerative Colitis , Polyps , and Dyed-Lifted Polyps Using Wireless Capsule Endoscopy Images.” Complex & Intelligent Systems 10(2):2477–97. doi: 10.1007/s40747-023-01271-5.
Müller, Dominik, Iñaki Soto-Rey, and Frank Kramer. 2022. “Towards a Guideline for Evaluation Metrics in Medical Image Segmentation.” BMC Research Notes 15(1):1–8. doi: 10.1186/s13104-022-06096-y.
Niu, Ke, Zeyun Liu, Xue Feng, Heng Li, and Kaize Shi. 2025. “Endoscopic Depth Estimation Based on Deep Learning: A Survey.” ArXiv 3613:0–3.
Oza, Parita, Paawan Sharma, Samir Patel, Festus Adedoyin, and Alessandro Bruno. 2022. “Image Augmentation Techniques for Mammogram Analysis.” Journal of Imaging 8(5):1–22. doi: 10.3390/jimaging8050141.
Pallikkavaliyaveetil, Nazreen, and Sriram Chandrasekaran. 2026. “Small Data , Big Challenges : Machine- and Deep-Learning Strategies for Data-Limited Drug Discovery.” Advanced Drug Delivery Reviews 229(September 2025):115762. doi: 10.1016/j.addr.2025.115762.
Park, Hyun Cheol, In Pyo Hong, Sahadev Poudel, and Chang Choi. 2023. “Data Augmentation Based on Generative Adversarial Networks for Endoscopic Image Classification.” IEEE Access 11(April):49216–25. doi: 10.1109/ACCESS.2023.3275173.
Pogorelov, Konstantin, Thomas De Lange, Dag Johansen, Peter Thelin Schmidt, Michael Riegler, Mathias Lux, and Pål Halvorsen. 2017. “Kvasir : A Multi-Class Image Dataset for Computer Aided Gastrointestinal Disease Detection.” Association for Computing Machinery 164–169. doi: 10.1145/3083187.3083212.
Sandler, Mark, Andrew Howard, Menglong Zhu, and Andrey Zhmoginov. 2018. “MobileNetV2: Inverted Residuals and Linear Bottlenecks.” ArXiv 4510–20. doi: https://doi.org/10.48550/arXiv.1801.04381.
Saputra, Kurniawan Aji, Farrikh Al Zami, Defri Kurniawan, and Muhammad Naufal. 2026. “Multi-Disease Retinal Classification Using EfficientNet-B3 and Targeted Albumentations : A Benchmark on Kaggle Retinal Fundus Images Dataset.” Sinkron : Jurnal Dan Penelitian Teknik Informatika 10(1):232–41. doi: 10.33395/sinkron.v10i1.15530.
Shaqran, Tariq M., Mustafa M. Ismaeel, Aljoharh Abdulaziz Alnuaman, Fatimah A. Al Ahmad, Ghadeer A. Albalawi, Jori N. Almubarak, Rakan S. AlHarbi, Rayan S. Alaqidi, Yaqin A. AlAli, Khaled S. Alfawaz, and Abdulrhman A. Daghriri. 2023. “Epidemiology, Causes, and Management of Gastro-Esophageal Reflux Disease: A Systematic Review.” Cureus 15(10). doi: 10.7759/cureus.47420.
Siboni, S., M. Sozzi, P. Visaggi, R. De Maron, and E. Asti. 2025. “New Tools for the Grading and Scoring of Gastro-Esophageal Reflux Disease.” Revista de Gastroenterología de México (English Edition) 90(3):412–27. doi: 10.1016/j.rgmxen.2025.09.005.
Tsuneki, Masayuki. 2022. “Deep Learning Models in Medical Image Analysis.” Journal of Oral Biosciences 64(3):312–20. doi: 10.1016/j.job.2022.03.003.
Yen, Hsu Heng, Hui Yu Tsai, Chi Chih Wang, Ming Chang Tsai, and Ming Hseng Tseng. 2022. “An Improved Endoscopic Automatic Classification Model for Gastroesophageal Reflux Disease Using Deep Learning Integrated Machine Learning.” Diagnostics 12(11):1–15. doi: 10.3390/diagnostics12112827.
Yen, Timothy, Blake Jones, Jeannine M. Espinoza, Sarguni Singh, Jonathan Pell, Anna Duloy, Sachin Wani, Frank I. Scott, and Swati G. Patel. 2023. “Optimizing Endoscopy Procedure Documentation Improves Guideline ‑ Adherent Care in Upper Gastrointestinal Bleeding American Society of Anesthesiologists.” Digestive Diseases and Sciences 68(6):2264–75. doi: 10.1007/s10620-023-07823-6.
Zhou, Guoping, Qiyu He, Xiaoli Liu, Xinghua Kai, Weikang Cao, Junning Ding, Bufeng Zhuang, Shuhua Xu, and Myo Thwin. 2024. “Optimizing MobileNetV2 for Improved Accuracy in Early Gastric Cancer Detection Based on Dynamic Pelican Optimizer.” Heliyon 10(16):e35854. doi: 10.1016/j.heliyon.2024.e35854.
Zhu, Qiming, Hongwei Zhuang, Mi Zhao, Shuangchao Xu, and Rui Meng. 2024. “A Study on Expression Recognition Based on Improved MobilenetV2 Network.” Scientific Reports 14(1):1–11. doi: 10.1038/s41598-024-58736-x.
Downloads
|
How to Cite
Issue
Section
License
Copyright (c) 2026 Dinda Chesar Putri Ramadhani, Risqy Siwi Pradini, M. Syauqi Haris
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Muhammad Khoiruddin harahap
Google Scholar 
Moraref
PKP Index
Garuda Kemdikbud
Indonesia OneSearch
OCLC Worldcat
Dimensions
Index Copernicus
Scilit
