This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Kalyani Agarawal,
Parima Verma,
Sri Geetha M,
Lakshmi Mohandas,
Abstract
PCOS is a common endocrine disorder that impacts women in their reproductive years characterized by irregular menstrual cycles, hyperandrogenism, and polycystic ovaries. The full diagnostic plan is mainly a combination of a pelvic ultrasound besides blood tests of specific parameters that indicate the presence of PCOS. Since PCOS is a hard-to-diagnose widespread hormonal disorder, blood tests, symptoms, and other parameters with the help of a computer can form a new and easy method to diagnose it. This study integrates ultrasound image analysis and numerical data exploration to provide a comprehensive understanding of PCOS.
Ultrasound images were pre-processed using Python-based libraries like OpenCV, with techniques such as cropping, edge detection, pixel intensity analysis, and follicle overlay. These methods highlighted structural differences between normal and PCOS ovaries. Numerical attributes, including BMI, hormonal levels, and lifestyle factors, were analysed.
The findings reveal significant differences in follicle distribution and intensity patterns in ultrasound images of PCOS-affected ovaries compared to normal ones. Statistical analysis further identified BMI, hormonal imbalances, and exercise habits as critical factors linked to PCOS.
This research paves the way for advanced diagnostic tools and contributing to better management of PCOS in clinical practice. Our study employs Teachable Machine to classify PCOS and non-PCOS images, achieving an accuracy of 100%.
Keywords: PCOS, ultrasound image analysis, Python, follicle distribution, BMI, hormonal imbalances
[This article belongs to Research and Reviews : Journal of Computational Biology ]
Kalyani Agarawal, Parima Verma, Sri Geetha M, Lakshmi Mohandas. A Python-Based Investigation of Clinical Data and Ultrasound Images for PCOS Diagnosis. Research and Reviews : Journal of Computational Biology. 2025; 14(02):-.
Kalyani Agarawal, Parima Verma, Sri Geetha M, Lakshmi Mohandas. A Python-Based Investigation of Clinical Data and Ultrasound Images for PCOS Diagnosis. Research and Reviews : Journal of Computational Biology. 2025; 14(02):-. Available from: https://journals.stmjournals.com/rrjocb/article=2025/view=213119
References
1. Mustafa WA, Alkhayyat A, Al-Azzawi W, Alquran HH. Detection of Polycystic Ovary Syndrome (PCOS) Using Machine Learning Algorithms. In: Proceedings of the International Conference on Emerging Trends and Applications in Engineering Technology and Applied Sciences (IICETA); 2022. https://doi.org/10.1109/IICETA54559.2022.9888677
2. Suha SA, Islam MN. An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image. Scientific Reports. 2022 Oct 12;12(1):17123.
3. Sakthivel V, Prakash P, Vishnukumar K, Min D. Advanced Diagnosis of Polycystic Ovarian Syndrome using Machine Learning and Multimodal Data Integration. International Journal of Advanced Computer Science & Applications. 2024 Jun 1;15(6).
4. Bairagi VK, Vanjale MS, Dolas A, Zende S, Nanthaamornphong A, Harpale S. Polycystic ovarian syndrome (PCOS) detection through deep learning. 2024.
5. Hoeger KM, Dokras A, Piltonen T. Update on PCOS: consequences, challenges, and guiding treatment. J Clin Endocrinol Metab. 2021;106(3):e1071-e1083.
6. Diamanti-Kandarakis E. PCOS in adolescents. Best Pract Res Clin Obstet Gynaecol. 2010;24(2):173-183.
7. Rosenfield RL, Ehrmann DA. The pathogenesis of polycystic ovary syndrome (PCOS): the hypothesis of PCOS as functional ovarian hyperandrogenism revisited. Endocr Rev. 2016;37(5):467-520.
8. Widodo CE, Adi K, Gernowo R. Medical image processing using Python and OpenCV. In: J Phys Conf Ser. 2020 Apr;1524(1):012003. IOP Publishing.
9. Bernardino G, Garcia D. PyMUST: an open-source Python Library for the Simulation and Analysis of Ultrasound. In: 2024 IEEE Ultrasonics, Ferroelectrics, and Frequency Control Joint Symposium (UFFC-JS); 2024 Sep. p. 1-4.
10. Krivanek A, Sonka M. Ovarian ultrasound image analysis: Follicle segmentation. IEEE Trans Med Imaging. 1998;17(6):935-944.
11. Purnama B, Wisesti UN, Nhita F, Gayatri A, Mutiah T. A classification of polycystic Ovary Syndrome based on follicle detection of ultrasound images. In2015 3rd International conference on information and communication technology (ICoICT) 2015 May 27 (pp. 396-401). IEEE.
12. Dangeti P, Yu A, Chung C, Yim A, Petrou T. Numerical Computing with Python: Harness the power of Python to analyze and find hidden patterns in the data. Packt Publishing Ltd; 2018 Dec 21.
13. Shen D, Wu G, Suk HI. Deep learning in medical image analysis. Annu Rev Biomed Eng. 2017;19(1):221-248.
14. Carney M, Webster B, Alvarado I, Phillips K, Howell N, Griffith J, et al. Teachable machine: Approachable web-based tool for exploring machine learning classification. In: Extended abstracts of the 2020 CHI Conference on Human Factors in Computing Systems; 2020 Apr. p. 1-8.
15. Agustian D, Pertama PPGP, Crisnapati PN, Novayanti PD. Implementation of machine learning using Google’s Teachable Machine based on Android. In: 2021 3rd International Conference on Cybernetics and Intelligent System (ICORIS); 2021 Oct. p. 1-7.
Research and Reviews : Journal of Computational Biology
| Volume | 14 |
| Issue | 02 |
| Received | 25/03/2025 |
| Accepted | 01/04/2025 |
| Published | 12/06/2025 |
| Publication Time | 79 Days |
Login
PlumX Metrics