International Journal of Image, Graphics and Signal Processing (IJIGSP)
IJIGSP Vol. 18, No. 1, 8 Feb. 2026
Cover page and Table of Contents: PDF (size: 1400KB)
Automated PCOS Detection Using Fine-Grained Deep Feature Extraction and Explainable AI: A Transformer-Based Ensemble Approach
PDF (1400KB), PP.88-105
Views: 0 Downloads: 0
Author(s)
Index Terms
PCOS Detection, Swin Transformer, Resnet50, Ensemble Learning, Explainable AI
Abstract
Polycystic Ovary Syndrome (PCOS) is a prevalent endocrine condition affecting women of reproductive age, hallmarked by hormonal abnormalities, ovarian cysts, and metabolic issues. Early diagnosis is essential to prevent long-term effects such as infertility, diabetes, and cardiovascular issues. Conventional diagnostic approaches relying on manual interpretation of ultrasound images are time-consuming and error-prone. To overcome these limitations, we propose an automated diagnostic framework leveraging deep feature extraction and ensemble learning. Initially, ResNet50 is utilized as a convolutional feature extractor, and its extracted features are classified using ensemble of Random Forest (RF) and Gradient Boosting (GB) classifiers. Subsequently, we also employed the Swin Transformer which is a hierarchical vision transformer to extract deep features from ultrasound images, which were fed to Random Forest and Gradient Boosting classifiers. These features were handled separately from those of ResNet50, and no feature concatenation was done. Compared to the ResNet50-based ensemble model, which achieved a classification accuracy of 99.2%, the Swin Transformer–based ensemble model performed better by attaining the accuracy of 99.87%. Furthermore, Explainable AI approaches (Grad-CAM) were applied to both ResNet50-based model and Swin Transformer-based model to highlight key regions contributing to the predictions. This scalable and interpretable system offers encouraging potential for advancing PCOS detection and other medical imaging applications.
Cite This Paper
Ifra Bilal Shah, Pramod Kumar Yadav, "Automated PCOS Detection Using Fine-Grained Deep Feature Extraction and Explainable AI: A Transformer-Based Ensemble Approach", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.18, No.1, pp. 88-105, 2026. DOI:10.5815/ijigsp.2026.01.06
Reference
[1]Stefano Palomba and et al. Complications and challenges associated with polycystic ovary syndrome: current perspectives. International Journal of Women’s Health, pages 745–763, 2015.
[2]Robert L. Rosenfieldand David A. Ehrmann. The pathogenesis of polycystic ovary syndrome (pcos): the hypothesis of pcos as functional ovarian hyperandrogenism revisited. Endocrine Reviews, 37(5):467–520, 2016.
[3]Ricardo Azziz and et al. Polycystic ovary syndrome. Nature Reviews Disease Primers, 2:1–18, 2016.
[4]Rogerio A Lobo and Enrico Carmina. The importance of diagnosing the polycystic ovary syndrome. Annals of internal medicine, 132(12):989–993, 2000.
[5]Samia Ahmed, Md Sazzadur Rahman, Ismate Jahan, M Shamim Kaiser, ASM Sanwar Hosen, Deepak Ghimire, and Seong-Heum Kim. A review on the detection techniques of polycystic ovary syndrome using machine learning. IEEE Access, 11:86522–86543, 2023.
[6]Yihui Xu, Ziyan Cao, Ting Chen, and Jiawei Ren. Trends in metabolic dysfunction in polycystic ovary syndrome: a bibliometric analysis. Frontiers in Endocrinology, 14:1245719, 2023.
[7]RummanAhmad,LameesAMaghrabi,IshfaqAhmadKhaja,LouaiAMaghrabi,andMusheerAhmad. Smote-based automated pcos prediction using lightweight deep learning models. Diagnostics, 14(19):2225, 2024.
[8]Bharti Panjwani, Jyoti Yadav, Vijay Mohan, Neha Agarwal, and Saurabh Agarwal. Optimized machine learning for the early detection of polycystic ovary syndrome in women. Sensors, 25(4):1166, 2025.
[9]Sayma Alam Suha and Muhammad Nazrul Islam. An extended machine learning technique for polycystic ovary syndrome detection using ovary ultrasound image. ScientificReports, 12(1):17123, 2022.
[10]B. Rachana and et al. Detection of polycystic ovarian syndrome using follicle recognition technique. Global Tran- sitions Proceedings, 2(2):304–308, 2021.
[11]C. Gopalakrishnan and M. Iyapparaja. Multilevel thresholding based follicle detection and classificationof polycys- tic ovary syndrome from the ultrasound images using machine learning. International Journal of System Assurance Engineering and Management, pages 1–8, 2021.
[12]Pratik Wagh, Megha Panjwani, and S. Amrutha. Early detection of pcod using machine learning techniques. In ArtificialIntelligence and Speech Technology, pages 9–20. CRC Press, 2021.
[13]S. Nasim, M. S. Almutairi, K. Munir, A. Raza, and F. Younas. A novel approach for polycystic ovary syndrome prediction using machine learning in bioinformatics. IEEE Access, 10:97610–97624, 2022.
[14]R. Subha, B. R. Nayana, R. Radhakrishnan, and P. Sumalatha. Computational intelligence for early detection of infertility in women. Engineering Applications of ArtificialIntelligence, 127:107400, 2024.
[15]Poonam Moral, Debjani Mustafi, and Sudip Kumar Sahana. Podboost: an explainable ai model for polycystic ovarian syndrome detection using grey wolf-based feature selection approach. Neural Computing and Applications, 36(30):18627–18644, 2024.
[16]S. Sreejith, H. K. Nehemiah, and A. Kannan. A clinical decision support system for polycystic ovarian syndrome using red deer algorithm and random forest classifier. Healthcare Analytics, 2:100102, 2022.
[17]V. V. Khanna, K. Chadaga, N. Sampathila, S. Prabhu, V. Bhandage, and G. K. Hegde. A distinctive explainable machine learning framework for detection of polycystic ovary syndrome. Applied System Innovation, 6(2):32, 2023.
[18]Abrar Alamoudi, Irfan Ullah Khan, Nida Aslam, Nourah Alqahtani, Hind S Alsaif, Omran Al Dandan, Mohammed Al Gadeeb, and Ridha Al Bahrani. A deep learning fusion approach to diagnosis the polycystic ovary syndrome (pcos). Applied Computational Intelligence and Soft Computing, 2023(1):9686697, 2023.
[19]Pradeep Bedi et al. An integrated adaptive bilateral filter-based framework and attention residual u-net for detecting polycystic ovary syndrome. Decision Analytics Journal, 10:100366, 2024.
[20]S. Umapathy, O. Alhajlah, F. Almutairi, S. Aslam, and A. RK. F-net: Follicles net an efficienttool for the diagnosis of polycystic ovarian syndrome using deep learning techniques. PLoS One, 19(8):Article e0307571, 2024.
[21]Dimitris Perdios and et al. Cnn-based image reconstruction method for ultrafast ultrasound imaging. IEEE Trans- actions on Ultrasonics, Ferroelectrics, and Frequency Control, 69(4):1154–1168, 2021.
[22]Sheldon Mascarenhas and Mukul Agarwal. A comparison between vgg16, vgg19 and resnet50 architecture frame- works for image classification. In 2021 International conference on disruptive technologies for multi-disciplinary research and applications (CENTCON), volume 1, pages 96–99. IEEE, 2021.
[23]Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
[24]Ze Liu, Yutong Lin, Yue Cao, Han Hu, YixuanWei, ZhengZhang, StephenLin, andBainingGuo. Swintransformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE/CVF international conference on computer vision, pages 10012–10022, 2021.
[25]AKM Salman Hosain, Md Humaion Kabir Mehedi, and Irteza Enan Kabir. Pconet: A convolutional neural network architecture to detect polycystic ovary syndrome (pcos) from ovarian ultrasound images. In 2022 International conference on engineering and emerging technologies (ICEET), pages 1–6. IEEE, 2022.
[26]A. B. Arrieta, N. D´ıaz-Rodr´ıguez, J. Del Ser, A. Bennetot, S. Tabik, A. Barbado, and F. Herrera. Explainable artificial intelligence (xai): Concepts, taxonomies, opportunities and challenges toward responsible ai. Information Fusion, 58:82–115, 2020.
[27]Pavel Hamet and Johanne Tremblay. Artificialintelligence in medicine. metabolism, 69:S36–S40, 2017.
[28]H. Hagras. Toward human-understandable, explainable ai. Computer, 51(9):28–36, 2018.
[29]Subhashis Suara, Aayush Jha, Pratik Sinha, and Arif Ahmed Sekh. Is grad-cam explainable in medical images? In International Conference on Computer Vision and Image Processing, pages 124–135. Springer, 2023.
[30]Mengying Xiao, Liyuan Zhang, Weili Shi, Jianhua Liu, Wei He, and Zhengang Jiang. A visualization method based on the grad-cam for medical image segmentation model. In 2021 International Conference on Electronic Information Engineering and Computer Science (EIECS), pages 242–247. IEEE, 2021.
[31]W. Lv, Y. Song, R. Fu, X. Lin, Y. Su, X. Jin, and G. Huang. Deep learning algorithm for automated detection of polycystic ovary syndrome using scleral images. Frontiers in Endocrinology, 12:789878, 2022.
[32]Jong-Chih Chien et al. The usefulness of gradient-weighted cam in assisting medical diagnoses. Applied Sciences, 12(15):7748, 2022.
[33]Mengcheng Cai, Zhexin Ni, Zike Yuan, Jin Yu, Danying Zhang, Ruipin Yao, Ling Zhou, and Chaoqin Yu. Past and present a bibliometric study on polycystic ovary syndrome. Journal of Ovarian Research, 16(1):42, 2023.