Application of VGG16 Deep Learning Architecture and K-Means for PCOS Severity Clustering Based on Ovarian Ultrasound Images
Keywords:
PCOS, VGG16, K-Means, Clustering, SVM, Ultrasound ImageAbstract
Polycystic Ovary Syndrome (PCOS) is a complex hormonal disorder that significantly impacts the reproductive and metabolic health of women. A primary challenge in PCOS analysis is the reliance on subjective manual observations of ultrasound (USG) images, which are prone to inconsistency due to the lack of objective standards. This study proposes an automated, unsupervised framework to stratify the morphological characteristics of PCOS ultrasound images without predefined clinical labels. The method integrates feature extraction using the VGG16 deep learning architecture with K-Means clustering. The structural integrity of the computational clusters was quantitatively evaluated, achieving a Silhouette Score of 0.4248 and a Davies-Bouldin Index (DBI) of 0.9175, indicating the successful formation of distinct morphological groupings. Furthermore, an evaluation using a Support Vector Machine (SVM) to assess the internal consistency and linear separability of the extracted features yielded a test accuracy of 97.54%. The results demonstrate that the integration of VGG16 and K-Means effectively partitions PCOS ultrasound images into objective, computationally stable morphological groups. This approach is designed to function as a standardized clinical decision support tool, mitigating visual subjectivity and providing a measurable baseline for women's reproductive health management.
Downloads
References
[1] M. Bashir, F. Amin, H. Amin, T. A. Teli, and T. A. Tali, “Polycystic ovary syndrome: a comprehensive review of pathophysiology, diagnosis, and emerging management strategies,” Int. J. Reprod. Contracept. Obstet. Gynecol., vol. 14, no. 10, pp. 3618–3623, Sep. 2025, doi: 10.18203/2320-1770.ijrcog20253125.
[2] World Health Organization, “Polycystic ovary syndrome.” Accessed: May 01, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/polycystic-ovary-syndrome
[3] D. A. Sari, E. Y. Kurniawati, and M. A. Ashari, “SKRINING DAN DETERMINAN KEJADIAN SINDROM OVARIUM POLIKISTIK (SOPK) PADA REMAJA,” Jurnal Ilmu Kebidanan, vol. 9, no. 2, 2023, doi: 10.48092/jik.v9i2.211.
[4] Habiburrahman Said, Rheina Weisch Fedre, Saurie Hernandez, Sophia Lucille Rodriguez, Fatimah Mursyid, and Irna Nettles, “The Prevalence and Risk Factors for Polycystic Ovary Syndrome (PCOS) among Adolescents in Indonesia: Implications for Early Intervention,” Sriwijaya Journal of Obstetrics and Gynecology, vol. 1, no. 2, 2023, doi: 10.59345/sjog.v1i2.83.
[5] H. Bai, H. Ding, and M. Wang, “Polycystic Ovary Syndrome (PCOS): Symptoms, Causes, and Treatment,” 2024, IMR Press Limited. doi: 10.31083/j.ceog5105126.
[6] K. M. Hoeger, A. Dokras, and T. Piltonen, “Update on PCOS: Consequences, Challenges, and Guiding Treatment,” Mar. 01, 2021, Endocrine Society. doi: 10.1210/clinem/dgaa839.
[7] S. A. Suha and M. N. Islam, “An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image,” Sci. Rep., vol. 12, no. 1, Dec. 2022, doi: 10.1038/s41598-022-21724-0.
[8] K. Shanmugavadivel, M. D. M S, M. T R, T. Al-Shehari, N. A. Alsadhan, and T. E. Yimer, “Optimized polycystic ovarian disease prognosis and classification using AI based computational approaches on multi-modality data,” BMC Med. Inform. Decis. Mak., vol. 24, no. 1, Dec. 2024, doi: 10.1186/s12911-024-02688-9.
[9] J. Kermanshahchi, A. J. Reddy, J. Xu, G. K. Mehrok, and F. Nausheen, “Development of a Machine Learning-Based Model for Accurate Detection and Classification of Polycystic Ovary Syndrome on Pelvic Ultrasound,” Cureus, Jul. 2024, doi: 10.7759/cureus.65134.
[10] K. V. Suvika and D. G. Jyothi, “A Machine Learning Approach for Efficient Identification and Severity Grading of PCOS and PCOD Using Optimized Features,” Journal of Machine and Computing, vol. 5, no. 4, pp. 1994–2005, Oct. 2025, doi: 10.53759/7669/jmc202505156.
[11] D. N. Varshitha et al., “Automated Detection of Polycystic Ovary Syndrome Using Convolutional Neural Networks on Ultrasound Images,” Salud, Ciencia y Tecnologia, vol. 5, Jan. 2025, doi: 10.56294/saludcyt20252272.
[12] Ibadeus, “PCOS-XAI Ultrasound: Real-World Training Dataset.” Accessed: Nov. 12, 2025. [Online]. Available: https://www.kaggle.com/datasets/ibadeus/pcos-xai-ultrasound-dataset
[13] A. A. Al-Jaburi and A. H. Al-Sudani, “Medical Ultrasound Image Quality Enhancement and Regions Segmentation,” Iraqi Journal of Science, vol. 63, no. 10, pp. 4518–4533, 2022, doi: 10.24996/ijs.2022.63.10.35.
[14] K. Sikhakhane, S. Rimer, M. Gololo, K. Ouahada, and A. M. Abu-Mahfouz, “Evaluation of Speckle Noise Reduction Filters and Machine Learning Algorithms for Ultrasound Images,” IEEE Access, vol. 12, pp. 81293–81312, 2024, doi: 10.1109/ACCESS.2024.3411709.
[15] T. B. Nguyen-Tat, T. Q. Hung, P. T. Nam, and V. M. Ngo, “Evaluating pre-processing and deep learning methods in medical imaging: Combined effectiveness across multiple modalities,” Alexandria Engineering Journal, vol. 119, pp. 558–586, Apr. 2025, doi: 10.1016/j.aej.2025.01.090.
[16] A. Chauhan and I. Kumar, “Deep feature extraction and optimized VGG16-SVM architecture for breast cancer characterization,” Discover Computing, vol. 28, no. 1, Dec. 2025, doi: 10.1007/s10791-025-09736-6.
[17] M. S. K. Inan, F. I. Alam, and R. Hasan, “Deep Integrated Pipeline of Segmentation Guided Classification of Breast Cancer from Ultrasound Images,” Feb. 2022, doi: 10.1016/j.bspc.2022.103553.
[18] M. J. Ramesh, D. R. Manavalan, and D. K. M. Prabusankarlal, “Feature Extraction Of Ultrasound Prostate Image Using Modified Vgg-19 Transfer Learning,” 2021.
[19] H. Liu, J. Chen, J. Dy, and Y. Fu, “Transforming Complex Problems Into K-Means Solutions,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 45, no. 7, pp. 9149–9168, Jul. 2023, doi: 10.1109/TPAMI.2023.3237667.
[20] C. Wongoutong, “The impact of neglecting feature scaling in k-means clustering,” PLoS One, vol. 19, no. 12, Dec. 2024, doi: 10.1371/journal.pone.0310839.
[21] B. M. S. Hasan and A. M. Abdulazeez, “A Review of Principal Component Analysis Algorithm for Dimensionality Reduction,” Journal of Soft Computing and Data Mining, vol. 2, no. 1, pp. 20–30, Apr. 2021, doi: 10.30880/jscdm.2021.02.01.003.
[22] M. Zubair, M. A. Iqbal, A. Shil, M. J. M. Chowdhury, M. A. Moni, and I. H. Sarker, “An Improved K-means Clustering Algorithm Towards an Efficient Data-Driven Modeling,” Annals of Data Science, vol. 11, no. 5, 2024, doi: 10.1007/s40745-022-00428-2.
[23] S. Suraya, M. Sholeh, and U. Lestari, “Evaluation of Data Clustering Accuracy using K-Means Algorithm,” International Journal of Multidisciplinary Approach Research and Science, vol. 2, no. 01, pp. 385–396, Dec. 2023, doi: 10.59653/ijmars.v2i01.504.
[24] K. R. Shahapure and C. Nicholas, “Cluster Quality Analysis Using Silhouette Score,” 2020. doi: 10.1109/DSAA49011.2020.00096.
[25] A. Sujjada, G. Purnama Insany, and S. Noer, “Analisis Clustering Data Penyandang Disabilitas Menggunakan Metode Agglomerative Hierarchical Clustering dan K-means,” Jurnal Teknologi dan Manajemen Informatika, vol. 10, pp. 1–12, 2024, doi: https://doi.org/10.26905/jtmi.v10i1.10654.
[26] C. H. Yeh, S. X. Yu, and M. C. Lin, “Meibography phenotyping and classification from unsupervised discriminative feature learning,” Transl. Vis. Sci. Technol., vol. 10, no. 2, pp. 1–11, Feb. 2021, doi: 10.1167/tvst.10.2.4.
[27] K. L. Du, B. Jiang, J. Lu, J. Hua, and M. N. S. Swamy, “Exploring Kernel Machines and Support Vector Machines: Principles, Techniques, and Future Directions,” Dec. 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/math12243935.
[28] S. Pal, L. H. Trang, V. T. Hieu, D. D. Nguyen, D. Q. Vu, and I. Prakash, “Investigation of Support Vector Machines with Different Kernel Functions for Prediction of Compressive Strength of Concrete,” Journal of Science and Transport Technology, vol. 4, no. 2, 2024, doi: 10.58845/jstt.utt.2024.en.4.2.55-68.
[29] S. Avcı Azkeskin and Z. Aladag, “Evaluating regional sustainable energy potential through hierarchical clustering and machine learning,” Environ. Res. Commun., vol. 7, no. 1, 2025, doi: 10.1088/2515-7620/ada2e5.
[30] S. Simhadri, M. Ponnam, R. Rajitha, and R. Balamurugan, “Enhanced Multi-Class Model Evaluation: Analyzing BERT, GPT-2, and LLaMA with Precision, Recall, and F1-Score Metrics,” in Proceedings of the 4th International Conference on Innovative Mechanisms for Industry Applications, ICIMIA 2025, 2025. doi: 10.1109/ICIMIA67127.2025.11200914.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
(1)Â Copyright of the published articles will be transferred to the journal as the publisher of the manuscripts. Therefore, the author confirms that the copyright has been managed by the journal.
(2) Publisher of JTMI: Jurnal Teknologi dan Manajemen Informatika is University of Merdeka Malang.
(3) The copyright follows Creative Commons Attribution–ShareAlike License (CC BY SA): This license allows to Share — copy and redistribute the material in any medium or format, Adapt — remix, transform, and build upon the material, for any purpose, even commercially.
