Leveraging Synthetic Mammograms to Enhance Deep-Learning Performance for Breast Cancer Classification Using EfficientNetV2L Architecture

Raymond Sutjiadi; Siti Sendari; Heru Wahyu Herwanto; Yosi Kristian

doi:10.4108/airo.9749

Authors

Raymond Sutjiadi State University of Malang
Siti Sendari State University of Malang
Heru Wahyu Herwanto State University of Malang
Yosi Kristian Institut Sains dan Teknologi Terpadu Surabaya

DOI:

https://doi.org/10.4108/airo.9749

Keywords:

Breast Cancer Detection, Synthetic Mammograms, EfficientNetV2L, Denoising Diffusion Probabilistic Models (DDPM), Deep Learning in Medical Imaging

Abstract

INTRODUCTION: To improve survival rates for breast cancer, a leading cause of female mortality globally, early detection is essential. This study presents a deep learning framework for classifying mammogram images as normal or abnormal.

OBJECTIVES: This research aims to enhance the performance of a deep learning model for breast cancer classification by augmenting a real mammogram dataset with synthetic images. The study evaluates the impact of progressively increasing the number of synthetic mammograms on the model's accuracy, precision, recall, and F1-score.

METHODS: The approach utilizes the EfficientNetV2L model for classification. Data augmentation was performed by generating synthetic mammograms using Denoising Diffusion Probabilistic Models (DDPM). A baseline dataset of 410 real mammograms from the INbreast public dataset was augmented with an increasing number of synthetic images across four experimental scenarios.

RESULTS: The model demonstrated substantial performance gains directly linked to the use of synthetic data. The best performance was achieved when 500 synthetic images were used, resulting in all evaluation metrics exceeding a score of 0.90. The results confirm that incorporating more synthetic images is a key factor in achieving both higher classification accuracy and more stable training convergence.

CONCLUSION: These findings highlight the significant potential of synthetic image augmentation to address data scarcity, class imbalance, and model generalisation in medical image analysis. This method provides a scalable and privacy-preserving solution for breast cancer screening systems.

Downloads

Download data is not yet available.

References

[1] Kim J, Harper A, McCormack V, Sung H, Houssami N, Morgan E, et al. Global patterns and trends in breast cancer incidence and mortality across 185 countries. Nat Med. 2025 Feb 24;

[2] Guo F, Kuo Y, Shih YCT, Giordano SH, Berenson AB. Trends in breast cancer mortality by stage at diagnosis among young women in the United States. Cancer. 2018 Sep 6;124(17):3500–9.

[3] Nicosia L, Gnocchi G, Gorini I, Venturini M, Fontana F, Pesapane F, et al. History of Mammography: Analysis of Breast Imaging Diagnostic Achievements over the Last Century. Healthcare. 2023 May 30;11(11):1596.

[4] Wang J. Breast cancer detection via wavelet energy and feed-forward neural network trained by genetic algorithm. EAI Endorsed Transactions on AI and Robotics. 2023 Sep 5;2.

[5] Ginsburg O, Yip C, Brooks A, Cabanes A, Caleffi M, Dunstan Yataco JA, et al. Breast cancer early detection: A phased approach to implementation. Cancer. 2020 May 15;126(S10):2379–93.

[6] Iranmakani S, Mortezazadeh T, Sajadian F, Ghaziani MF, Ghafari A, Khezerloo D, et al. A review of various modalities in breast imaging: technical aspects and clinical outcomes. Egyptian Journal of Radiology and Nuclear Medicine. 2020 Dec 16;51(1):57.

[7] Kavitha T, Mathai PP, Karthikeyan C, Ashok M, Kohar R, Avanija J, et al. Deep Learning Based Capsule Neural Network Model for Breast Cancer Diagnosis Using Mammogram Images. Interdiscip Sci. 2022 Mar 2;14(1):113–29.

[8] Jose Escorcia-Gutierrez, F. Mansour R, Beleno K, Jimenez-Cabas J, Perez M, Madera N, et al. Automated Deep Learning Empowered Breast Cancer Diagnosis Using Biomedical Mammogram Images. Computers, Materials & Continua [Internet]. 2022;71(3):4221–35. Available from: https://www.techscience.com/cmc/v71n3/46473

[9] El Houby EMF, Yassin NIR. Malignant and nonmalignant classification of breast lesions in mammograms using convolutional neural networks. Biomed Signal Process Control. 2021 Sep;70:102954.

[10] Qasrawi R, Daraghmeh O, Qdaih I, Thwib S, Vicuna Polo S, Owienah H, et al. Hybrid ensemble deep learning model for advancing breast cancer detection and classification in clinical applications. Heliyon. 2024 Oct;10(19):e38374.

[11] Montesinos López OA, Montesinos López A, Crossa J. Overfitting, Model Tuning, and Evaluation of Prediction Performance. In: Multivariate Statistical Machine Learning Methods for Genomic Prediction. Cham: Springer International Publishing; 2022. p. 109–39.

[12] Zhang N, Zhang E, Li F. A Soybean Classification Method Based on Data Balance and Deep Learning. Applied Sciences. 2023 May 24;13(11):6425.

[13] Fan FJ, Shi Y. Effects of data quality and quantity on deep learning for protein-ligand binding affinity prediction. Bioorg Med Chem. 2022 Oct;72:117003.

[14] Sendari S, Buana FK, Wirawan IM, Wibowo FS, Tibyani. Smart Parking: Symbol Detection Using Haar Cascade Classifier Algorithm To Monitor Empty Parking Slots. In: 2021 7th International Conference on Electrical, Electronics and Information Engineering (ICEEIE). IEEE; 2021. p. 431–5.

[15] Utama ABP, Wibawa AP, Handayani AN, Chuttur MY. Exploring the Role of Deep Learning in Forecasting for Sustainable Development Goals: A Systematic Literature Review. International Journal of Robotics and Control Systems. 2024 Mar 31;4(1):365–400.

[16] World Medical Association. World Medical Association Declaration of Helsinki. JAMA. 2013 Nov 27;310(20):2191.

[17] Moreira IC, Amaral I, Domingues I, Cardoso A, Cardoso MJ, Cardoso JS. INbreast: Toward a Full-field Digital Mammographic Database. Acad Radiol. 2012 Feb;19(2):236–48.

[18] Suckling J, Parker J, Dance D, Astley S, Hutt I, Boggis C, et al. Mammographic Image Analysis Society (MIAS) database v1.21. [Dataset]. Apollo - University of Cambridge Repository. University of Cambridge; 2015.

[19] Lee RS, Gimenez F, Hoogi A, Miyake KK, Gorovoy M, Rubin DL. A curated mammography data set for use in computer-aided detection and diagnosis research. Sci Data. 2017 Dec 19;4(1):170177.

[20] Iswahyudi W, Farhan Ali Irfani M, Dwi Mahandi Y, Ari Elbaith Zaeni I, Sendari S, Widiyaningtyas T. Analyzing the Effectiveness of MobileNetV2, Xception, and DenseNet for Classifying Chest Diseases: Pneumonia, Pneumothorax,and Cardiomegaly. In: 2024 International Conference on Electrical Engineering and Computer Science (ICECOS). IEEE; 2024. p. 251–5.

[21] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial networks. Commun ACM. 2020 Oct 22;63(11):139–44.

[22] Ho J, Jain A, Abbeel P. Denoising Diffusion Probabilistic Models. In: Advances in Neural Information Processing Systems 33. 2020.

[23] Kingma DP, Welling M. An Introduction to Variational Autoencoders. Foundations and Trends® in Machine Learning. 2019;12(4):307–92.

[24] Yi X, Walia E, Babyn P. Generative adversarial network in medical imaging: A review. Med Image Anal. 2019 Dec;58:101552.

[25] Cheng ST, Yeh CW. Two-Stage Metal Surface Defect Detection and Classification System Based on VAEGAN and Class-Embedding. EAI Endorsed Transactions on AI and Robotics. 2023 Nov 29;2.

[26] Yilmaz B, Korn R. A Comprehensive guide to Generative Adversarial Networks (GANs) and application to individual electricity demand. Expert Syst Appl. 2024 Sep;250:123851.

[27] Rais K, Amroune M, Benmachiche A, Haouam MY. Exploring Variational Autoencoders for Medical Image Generation: A Comprehensive Study. In: Proceedings of ACN International Conference. Istanbul; 2024. p. 1–5.

[28] Müller-Franzes G, Niehues JM, Khader F, Arasteh ST, Haarburger C, Kuhl C, et al. A multimodal comparison of latent denoising diffusion probabilistic models and generative adversarial networks for medical image synthesis. Sci Rep. 2023 Dec 1;13(1).

[29] Xiao Z, Kreis K, Vahdat A. Tackling the Generative Learning Trilemma with Denoising Diffusion GANs. In: International Conference on Learning Representations (ICLR). 2022.

[30] Sutjiadi R, Sendari S, Herwanto HW, Kristian Y. Generating High-quality Synthetic Mammogram Images Using Denoising Diffusion Probabilistic Models: a Novel Approach for Augmenting Deep Learning Datasets. In: 2024 International Conference on Information Technology Systems and Innovation (ICITSI). IEEE; 2024. p. 386–92.

[31] Sutjiadi R, Sendari S, Herwanto HW, Kristian Y. Deep Learning for Segmentation and Classification in Mammograms for Breast Cancer Detection: A Systematic Literature Review. Advanced Ultrasound in Diagnosis and Therapy. 2024;8(3):94–105.

[32] Tan M, Le Q V. EfficientNetV2: Smaller Models and Faster Training. Proceedings of the 38th International Conference on Machine Learning [Internet]. 2021 Apr 1;10096–106. Available from: http://arxiv.org/abs/2104.00298