Hybrid Machine Learning (Ml)-Based System for Detection of Uterine Fibroids from Ultrasound Images Using Convolutional Neural Network (CNN) and Attention Mechanism

Uterine fibroids are among the most common benign tumors affecting women of reproductive age, and their timely detection is crucial for effective clinical management. Traditional diagnostic practices rely on expert interpretation of ultrasound images, which is often time-intensive and subject to variability. This study presents a hybrid machine learning system for the early detection of uterine fibroids using transabdominal and transvaginal ultrasound images. The proposed system integrates Convolutional Neural Networks (CNN) with advanced feature refinement techniques (Attention Mechenism) to improve diagnostic accuracy and reliability. A curated dataset obtained from the Kaggle repository was used, and preprocessing methods such as contrast normalization and noise reduction were applied to enhance image quality. Experimental results demonstrated strong performance, with an accuracy of 94%, precision of 92%, recall of 90%, and an F1-score of 91%. These balanced metrics highlight the robustness of the hybrid approach, offering consistent detection of fibroid-positive cases while minimizing false positives and negatives. The system shows promise as a clinical decision-support tool, particularly in resource-limited settings where radiological expertise is scarce. Future research will focus on expanding the dataset, incorporating explainable AI methods for greater transparency, and validating the model across diverse populations and imaging protocols.

Uterine fibroids, ultrasound imaging, convolutional neural network, machine learning, tumor detection, medical image analysis, diagnostic support system.

1. E. Giuliani, S. As-Sanie, and E. E. Marsh, “Epidemiology and management of uterine fibroids,” International Journal of Gynecology & Obstetrics, vol. 149, no. 1, pp. 3–9, 2020, doi: 10.1002/ijgo.13102. [Google Scholar] [Crossref]

2. E. A. Stewart, C. L. Cookson, R. A. Gandolfo, and R. Schulze-Rath, “Epidemiology of uterine fibroids: a systematic review,” BJOG: An International Journal of Obstetrics & Gynaecology, vol. 124, no. 10, pp. 1501–1512, Mar. 2017, doi: 10.1111/1471-0528.14640. [Google Scholar] [Crossref]

3. Z. Lou et al., “Global, regional, and national time trends in incidence, prevalence, years lived with disability for uterine fibroids, 1990–2019: an age-period-cohort analysis for the global burden of disease 2019 study,” BMC Public Health, vol. 23, no. 916, May 2023, doi: 10.1186/s12889-023-15754-0. [Google Scholar] [Crossref]

4. C. Cai et al., “Artificial intelligence–assisted radiation imaging pathways for distinguishing uterine fibroids and malignant lesions in patients presenting with cancer pain: a literature review,” Frontiers in Oncology, vol. 15, Jun. 2025, doi: 10.3389/fonc.2025.1621642. [Google Scholar] [Crossref]

5. T. Huo et al., “Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study,” Scientific Reports, vol. 13, no. 3714, Mar. 2023, doi: 10.1038/s41598-023-30735-2. [Google Scholar] [Crossref]

6. P. Cai et al., “A lightweight hybrid model for the automatic recognition of uterine fibroid ultrasound images based on deep learning,” Journal of Clinical Ultrasound, Apr. 2024, doi: 10.1002/jcu.23703. [Google Scholar] [Crossref]

7. A. Mohanty, P. Pattnayak, and B. Ambudkar, “Deep convolutional neural networks for automatic detection of uterine fibroids in ultrasound images,” Journal of International Medical Research, vol. 19, no. 3, 2024, doi: 10.1177/18724981241309994. [Google Scholar] [Crossref]

8. A. Shahzad et al., “Automated uterine fibroids detection in ultrasound images using deep convolutional neural networks,” Healthcare, vol. 11, no. 10, p. 1493, May 2023, doi: 10.3390/healthcare11101493. [Google Scholar] [Crossref]

9. A. Tinelli et al., “Artificial Intelligence and Uterine Fibroids: A Useful Combination for Diagnosis and Treatment,” Journal of Clinical Medicine, vol. 14, no. 10, article 3454, May 2025, doi: 10.3390/jcm14103454. [Google Scholar] [Crossref]

10. H. Xi and W. Wang, “Deep learning based uterine fibroid detection in ultrasound images,” BMC Medical Imaging, vol. 24, no. 218, pp. 1–10, 2024, doi: 10.1186/s12880-024-01196-3. [Google Scholar] [Crossref]

11. M. L. Chinna and J. P. P. Mary, “Efficient feature extraction and hybrid deep learning for identification of uterine fibroids in ultrasound images,” International Journal of Imaging Systems and Technology, Mar. 2024, doi: 10.1002/ima.23073. [Google Scholar] [Crossref]

12. P. Kido, T. Togashi, and H. Konishi, “Imaging of uterine fibroids,” European Radiology, vol. 28, pp. 4313–4325, 2018, doi: 10.1007/s00330-018-5494-8. [Google Scholar] [Crossref]

13. J. R. Reinhold and M. M. McCarthy, “Diagnostic imaging pitfalls in gynecology: A radiologist’s perspective,” Radiographics, vol. 38, no. 6, pp. 1903–1924, 2018, doi: 10.1148/rg.2018180053. [Google Scholar] [Crossref]

14. T. J. Tamai et al., “Differentiation of uterine sarcomas from benign leiomyomas with multiparametric MR imaging,” European Radiology, vol. 29, no. 3, pp. 1549–1559, 2019, doi: 10.1007/s00330-018-5669-3. [Google Scholar] [Crossref]

15. F. B. Baird and D. A. Dunson, “Why fibroids matter: A review of the evidence,” Seminars in Reproductive Medicine, vol. 35, no. 6, pp. 483–490, 2017, doi: 10.1055/s-0037-1607296. [Google Scholar] [Crossref]

16. G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, vol. 42, pp. 60–88, Dec. 2017, doi: 10.1016/j.media.2017.07.005. [Google Scholar] [Crossref]

17. D. Criado-Ramón et al., “A Novel Non-Intrusive Load Monitoring Algorithm for Unsupervised Disaggregation of Household Appliances,” Energies, vol. 13, no. 5, p. 1165, 2020, doi: 10.3390/en13051165. [Google Scholar] [Crossref]

18. V. Gulshan et al., “Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs,” JAMA, vol. 316, no. 22, pp. 2402–2410, 2018, doi: 10.1001/jama.2016.17216. [Google Scholar] [Crossref]

19. J. De Fauw et al., “Clinically applicable deep learning for diagnosis and referral in retinal disease,” Nature Medicine, vol. 24, pp. 1342–1350, 2018, doi: 10.1038/s41591-018-0107-6. [Google Scholar] [Crossref]

20. X. Liu et al., “A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis,” The Lancet Digital Health, vol. 1, no. 6, pp. e271–e297, 2019, doi: 10.1016/S2589-7500(19)30123-2. [Google Scholar] [Crossref]

21. A. K. R. Talo et al., “Transfer learning in medical image classification: a literature review,” BMC Medical Imaging, vol. 22, no. 93, 2022, doi: 10.1186/s12880-022-00850-y. [Google Scholar] [Crossref]

22. T. Huo et al., “Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study,” Scientific Reports, vol. 13, no. 3714, 2023, doi: 10.1038/s41598-022-26771-1. [Google Scholar] [Crossref]

23. V. O. Ukwenya et al., “Prevalence of uterine fibroid in a South-Western Nigerian population: A sonographic study,” Journal of Experimental and Clinical Anatomy, vol. 14, no. 1, pp. 24–29, 2015, doi: 10.4103/1596-2393.158926. [Google Scholar] [Crossref]

24. M. Okon, J. E. Olotu, and I. E. Edet, “Anatomical location of uterine fibroids among women attending a tertiary health facility in a Southern Nigerian population,” GSC Biological and Pharmaceutical Sciences, vol. 14, no. 2, pp. 7–15, 2024. [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet