Academic Journal
A multimodal feature fusion with deep representation learning approach for polycystic ovary syndrome diagnosis using ultrasound images.
| Title: | A multimodal feature fusion with deep representation learning approach for polycystic ovary syndrome diagnosis using ultrasound images. |
|---|---|
| Authors: | Kranthi S; Department of Information Technology, Siddhartha Academy of Higher Education, Deemed to be University Vijayawada, Kanuru, 520007, Andhra Pradesh, India., Sandeep Y; Department of Information Technology, Siddhartha Academy of Higher Education, Deemed to be University Vijayawada, Kanuru, 520007, Andhra Pradesh, India., Pranathi K; Department of Information Technology, Siddhartha Academy of Higher Education, Deemed to be University Vijayawada, Kanuru, 520007, Andhra Pradesh, India., Laxmi Lydia E; Department of Computer Science and Engineering, Vignan's Institute of Engineering for Women, Visakhapatnam, 530046, India., Joshi GP; Department Electronic and AI System Engineering, Kangwon National University, Samcheok, 25913, Republic of Korea. joshi@kangwon.ac.kr., Cho W; Department Electronic and AI System Engineering, Kangwon National University, Samcheok, 25913, Republic of Korea. wcho@kangwon.ac.kr. |
| Source: | Scientific reports [Sci Rep] 2026 Feb 20; Vol. 16 (1). Date of Electronic Publication: 2026 Feb 20. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : Nature Publishing Group, copyright 2011- |
| MeSH Terms: | Polycystic Ovary Syndrome*/diagnostic imaging , Polycystic Ovary Syndrome*/diagnosis , Image Processing, Computer-Assisted*/methods , Deep Learning*, Ultrasonography/methods ; Ovary/diagnostic imaging ; Female ; Humans |
| Abstract: | Nowadays, polycystic ovary syndrome (PCOS) is among the very first causes of female infertility, which is a hormone imbalance that affects women of childbearing age. The earlier diagnosis of many cysts using ovarian ultrasound image scans is the most predictable technique to make a precise identification of PCOS and to make a proper treatment plan to cure patients with this disorder. Nevertheless, the analysis depends on Rotterdam conditions, comprising a higher level of androgen hormones, polycystic ovaries, and ovulation failure on the ultrasound images. Nowadays, radiologists and physicians manually execute PCOS identification using ovarian ultrasound by calculating the follicle counts and defining their volume in the ovaries, which is the most challenging PCOS diagnostic condition. Still, the conventional processes used for identifying PCOS using computer-based methods depend on numerous image processing methods and then classic machine learning (ML) tactics for image classification, which is a repetitive procedure with comparatively lower performance. Currently, some scholars have applied deep learning (DL) techniques to discover PCOS from ultrasound images. In this manuscript, a Multi-Model Feature Engineering and Deep Learning for Diagnosis of Polycystic Ovary Syndrome (MMFEDL-DPCOS) model is proposed. The MMFEDL-DPCOS model aims to analyse and diagnose PCOS employing ultrasound images for a precise and pre-diagnosis stage. Primarily, the Gaussian filtering (GF) method is utilized in the image pre-processing phase for enhancing image quality by reducing the noise. Furthermore, the fusion of InceptionResNetv2, EfficientNetV2B3, VGG16, ResNet-50, and Inception‐V3 methods is employed for feature extraction. Finally, the regularized stacked autoencoder (RSAE) methodology is utilized for classification. The comparison analysis of the MMFEDL-DPCOS methodology portrayed a superior accuracy value of 98.68% over existing models under the PCOS dataset. |
| Competing Interests: | Declarations. Competing interests: The authors declare no competing interests. Ethics approval: This article does not contain any studies with human participants performed by any of the authors. Consent to participate: Not applicable. Informed consent: Not applicable. |
| References: | Suha, S. A. & Islam, M. N. An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image. Sci. Rep. 12 (1), 17123 (2022). (PMID: 10.1038/s41598-022-21724-0362243539556522) Alamoudi, I. U. et al. A deep learning fusion approach to diagnosis the polycystic ovary syndrome (PCOS). Appl. Comput. Intell. Soft Comput. 1 (2023), 9686697 (2023). Gopalakrishnan & Iyapparaja, M. Multilevel thresholding based follicle detection and classification of polycystic ovary syndrome from the ultrasound images using machine learning. Int. J. Syst. Assur. Eng. Manage. 1–8. https://doi.org/10.1007/s13198-021-01203-x (2021). Galagan, R., Andreiev, S., Stelmakh, N., Rafalska, Y. & Momot, A. Automation of polycystic ovary syndrome diagnostics through machine learning algorithms in ultrasound imaging. Appl. Comput. Sci. 20 (2), 194–204 (2024). (PMID: 10.35784/acs-2024-24) Choubey, S. B., Choubey, A., Nandan, D. & Mahajan, A. Polycystic Ovarian Syndrome Detection by Using Two-Stage Image Denoising. Traitement du Signal. 38 (4). https://doi.org/10.18280/ts.380433 (2021). Cheng, J. J. & Mahalingaiah, S. Data mining polycystic ovary morphology in electronic medical record ultrasound reports. Fertility Res. Pract. 5, 1–7 (2019). Moral, P., Mustafi, D., Mustafi, A. & Sahana, S. K. CystNet: An AI driven model for PCOS detection using multilevel thresholding of ultrasound images. Sci. Rep. 14 (1), 25012 (2024). (PMID: 10.1038/s41598-024-75964-33944362211499604) Sumathi, M., Chitra, P., Sheela, S. & Ishwarya, C. Study and implementation of automated system for detection of PCOS from ultrasound scan images using artificial intelligence. Imaging Sci. J. 72 (7), 828–839 (2024). (PMID: 10.1080/13682199.2023.2229016) Rachana, B. et al. Detection of polycystic ovarian syndrome using follicle recognition technique. Global Transitions Proc. 2 (2), 304–308 (2021). (PMID: 10.1016/j.gltp.2021.08.010) Goel, A., Wasim, J., Srivastava, P. K. & Sharma, A. Ultrasound image noise reduction and enhancement model based on yellow saddle goatfish optimization algorithm. Fusion: Practice and Applications. 12, 08–18 (2023). Reka, S., Praba, T. S., Prasanna, M., Reddy, V. N. N. & Amirtharajan, R. Automated high precision PCOS detection through a segment anything model on super resolution ultrasound ovary images. Sci. Rep. 15 (1), 1–17 (2025). (PMID: 10.1038/s41598-025-01744-2) Ghosh, A. & Srinivasan, K. EFFIDenseGENOP: ensemble transfer learning with hyperparameter tuning using genetic algorithm optimization for PCOS detection from ultrasound sonography images. IEEE Access. 13, 54285–54312. https://doi.org/10.1109/access.2025.3553895 (2025). (PMID: 10.1109/access.2025.3553895) Galagan, R., Andreiev, S., Stelmakh, N., Rafalska, Y. & Momot, A. Automation of polycystic ovary syndrome diagnostics through machine learning algorithms in ultrasound imaging. Appl. Comput. Sci. 20 (2), 194–204. https://doi.org/10.35784/acs-2024-24 (2024). (PMID: 10.35784/acs-2024-24) Karthik, Y. S. R and S. M, Polycystic Ovary Syndrome Prediction through CNN based Image Analysis: A Deep Learning Based Approach, 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), Kirtipur, Nepal, 2024, pp. 1547–1553, Kirtipur, Nepal, 2024, pp. 1547–1553, https://doi.org/10.1109/I-SMAC61858.2024.10714821 (2024). Subramani, S., Rarichan, A. & Chaithra, S. H. Utilizing deep learning techniques for detection of Polycystic Ovarian Syndrome using ovarian ultrasound image, International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), Chennai, India, 2023, pp. 1–7, Chennai, India, 2023, pp. 1–7, https://doi.org/10.1109/ICSES60034.2023.10465547 (2023). Mahesswari, G. U., Maheswari, P. U. & Priya, B. H. IV3BoostPCOS: A Comprehensive Polycystic Ovary Syndrome (PCOS) Detection Framework, 2024 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Chennai, India, pp. 192–197, https://doi.org/10.1109/WIECON-ECE64149.2024.10914947 (2024). Hoque, M. M. et al. Vision Models for Medical Imaging: A Hybrid Approach for PCOS Detection from Ultrasound Scans. arXiv preprint arXiv:2601 15119. https://doi.org/10.48550/arXiv.2601.15119 (2026). (PMID: 10.48550/arXiv.2601.15119) Zhao, B. et al. A deep learning-based automatic recognition model for polycystic ovary ultrasound images. Balkan Med. J. 42 (5), 419 (2025). (PMID: 4078523512402960) Kulkarni, M. et al. A study of machine learning and deep learning models for PCOS diagnosis, In Recent Advances in Computational Methods in Science and Technology, pp. 424–431, (2026). Sundari, M. S. et al. Transfer learning-enhanced CNN model for integrative ultrasound and biomarker-based diagnosis of polycystic ovarian disease. Sci. Rep. 15 (1), 34519 (2025). (PMID: 10.1038/s41598-025-17711-w4104430912494765) Lakshmi, V. & Pushpa, B. Explainable multimodal deep learning using cross-attention fusion of ultrasound and clinical features for PCOS classification. Discover Comput. 29 (1), 7 (2026). (PMID: 10.1007/s10791-025-09901-x) Jothimani, S., Sangeethaa, S. N., Balamurugan, M. & Kayalvili, S. Detection of Polycystic Ovarian Disease Using Probabilistic Optimum Deep Learning Feature Fusion. IETE J. Res. 1–15. https://doi.org/10.1080/03772063.2025.2462790 (2025). Saini, R. K., Saini, H. & Yadav, N. Innovative Image Recognition for Multi-Disease Detection with Algorithmic Precision. SN Comput. Sci. 7 (1), 75 (2026). (PMID: 10.1007/s42979-025-04690-y) Mahmud, W. M. H. W., Huong, A. & Jumadi, N. A. Preliminary analysis of ultrasound features for detection of polycystic ovary syndrome (PCOS) in women. In Biomedical Engineering: AI and Technological Innovations(eds Lai, K. W. & Yeoh, P. S. Q.) 137–151, Singapore: Springer Nature Singapore (2025). Amissah, D. K., Boante, L. M., Mensah, S., Owusu, E. & Appati, J. K. Dynamic Memory-Augmented Whale Optimization Algorithm (DMA‐WOA) as Feature Descriptor for Polycystic Ovary Syndrome Detection. Appl. AI Lett. 7 (1). https://doi.org/10.1002/ail2.70016 (2026). Gong, Y. et al. Study on an Intelligent Screening Method for Polycystic Ovary Syndrome Based on Deep PhysicsInformed Neural Network. IEEE. Signal. Process. Lett. 33, 266–270. https://doi.org/10.1109/LSP.2025.3636719 (2026). (PMID: 10.1109/LSP.2025.3636719) Alrikabi, H. A., Siraj, D. M. M. & Muqdad, A. H. M. E. D. Enhancing low-resolution images through noise filtering and feature preservation. J. Theor. Appl. Inf. Technol, 103(2), 732–739 (2025). Hassan, M., Salbitani, G., Carfagna, S. & Khan, J. A. Deep learning meets marine biology: Optimized fused features and LIME-driven insights for automated plankton classification. Comput. Biol. Med. 192, 110273 (2025). (PMID: 10.1016/j.compbiomed.2025.11027340315719) Sinamenye, J. H., Chatterjee, A. & Shrestha, R. Potato plant disease detection: leveraging hybrid deep learning models. BMC Plant Biol. 25, 647 (2025). (PMID: 10.1186/s12870-025-06679-44038008812082912) Chohan, K., Vats, S., Sharma, V. & Parmar, D. S. Optimized Detection of Tomato Leaf Diseases via VGG16 Neural Network, International Conference on Automation and Computation (AUTOCOM), Dehradun, India, 2025, pp. 1694–1698, Dehradun, India, 2025, pp. 1694–1698, https://doi.org/10.1109/AUTOCOM64127.2025.10956497 (2025). Ramana, R., Vasudevan, V. & Murugan, B. S. Spectral Pyramid Pooling and Fused Keypoint Generation in ResNet-50 for Robust 3D Object Detection. IETE J. Research 71, 1–13 (2025). (PMID: 10.1080/03772063.2025.2453897) Chaurasia, S. & Choudhary, S. Skin Lesions Classification Using Deep Ensemble Learning Model of VGG-16, ResNet-50 and Inception-V3., xxx, (2025). Abdussamad, A. et al. Regularized Stacked Autoencoder with Dropout-Layer to Overcome Overfitting in Numerical High-Dimensional Sparse Data. J. Adv. Res. Des. 129 (1), 60–74 (2025). https://figshare.com/articles/dataset/PCOS_Dataset/27682557?file=50407062. https://doi.org/10.6084/m9.figshare.27682557.v1. Nasim, S., Almutairi, M. S., Munir, K., Raza, A. & Younas, F. A novel approach for polycystic ovary syndrome prediction using machine learning in bioinformatics. IEEE Access. 10, 97610–97624 (2022). (PMID: 10.1109/ACCESS.2022.3205587) Ahmed, S. et al. A review on the detection techniques of polycystic ovary syndrome using machine learning. IEEE Access. 11, 86522–86543 (2023). (PMID: 10.1109/ACCESS.2023.3304536) |
| Contributed Indexing: | Keywords: Deep Learning; Feature Engineering; Image Pre-processing; Polycystic Ovary Syndrome Diagnosis; Ultrasound Image |
| Entry Date(s): | Date Created: 20260220 Date Completed: 20260628 Latest Revision: 20260628 |
| Update Code: | 20260628 |
| PubMed Central ID: | PMC13022374 |
| DOI: | 10.1038/s41598-026-40718-w |
| PMID: | 41721030 |
| Database: | MEDLINE |
| ISSN: | 2045-2322 |
|---|---|
| DOI: | 10.1038/s41598-026-40718-w |