HAREN: A Hybrid Attention Residual Ensemble Network for PCOS classification and Prediction
Abstract
Polycystic Ovary Syndrome (PCOS) is one of the most prevalent endocrine disorders affecting women of reproductive age and is a leading cause of infertility. Ultrasound imaging is widely used for PCOS diagnosis; however, visual assessment of ovarian morphology is highly subjective, time-consuming, and dependent on clinical expertise. Quality differences in ultrasound images, very near to similar visual patterns among PCOS and NOT PCOS images, and noise in the images increase the threat of improper diagnosis. These problems suggest a need for an accurate, automatic, and computer-assisted PCOS diagnostic system. This research aims to create a deep learning-assisted automatic PCOS diagnostic system which can detect and classify the Polycystic Ovary Syndrome from the gray-scale ultrasound ovarian images. In addition to high classification accuracy, the proposed framework incorporates an explicit explainability pipeline that highlights diagnostically relevant ovarian regions, such as follicular distributions and stromal patterns, thereby supporting clinically interpretable decision making. The proposed HAREN framework addresses the limitations of single backbone models, and attention augmented variants, such as vanilla ResNet50 and ResNet50 with hybrid attention by leveraging ensemble learning and residual feature fusion. HAREN combines three architecturally diverse and complementary pretrained CNN backbones (ResNet50, DenseNet121, and EfficientNetB0) to enhance feature diversity. In addition, a novel hybrid attention mechanism combining channel, spatial, and cross-scale attention is introduced to emphasize diagnostically relevant ovarian regions. A residual fusion strategy is employed to preserve discriminative features and stabilize training, and an explicit explainability pipeline is incorporated to support Grad CAM-based visual interpretation. This network first converts the ultrasound grayscale ovarian images to RGB , followed by the extraction of important features applying backbones, which are augmented with attention mechanisms. The network, trained with categorical crossentropy loss, was evaluated using comprehensive performance metrics on 11,784 ultrasound images (6,784 PCOS and 5,000 NOT PCOS). HAREN achieved 99.33% accuracy, 98.96% precision, 98.97% recall, 98.96% F1 score, and an AUC of 99.93%, outperforming conventional models. Overall, it delivers an accurate, reliable, and interpretable solution for automated PCOS detection, demonstrating strong potential for clinical decision support systems
Downloads
References
H. J. Teede et al., “Recommendations from the international evidence-based guideline for the assessment and management of polycystic ovary syndrome,” Human Reproduction, vol. 33, no. 9, pp. 1602–1618, Jul. 2018, https://doi.org/2010.1093/humrep/dey256.
R. Azziz et al., “The Androgen Excess and PCOS Society criteria for the polycystic ovary syndrome: the complete task force report,” Fertility and Sterility, vol. 91, no. 2, pp. 456–488, Oct. 2008, https://doi.org/10.1016/j.fertnstert.2008.06.035.
“Revised 2003 consensus on diagnostic criteria and long-term health risks related to polycystic ovary syndrome,” Fertility and Sterility, vol. 81, no. 1, pp. 19–25, Jan. 2004, https://doi.org/10.1016/j.fertnstert.2003.10.004.
Y. Kumar et al., “Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda,”Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 7, pp. 8459–8486, Jan. 2022, https://doi.org/10.1007/s12652-021-03612-z.
J. Kang et al.,“MRI-Based brain tumor classification using ensemble of deep features and machine learning classifiers,” Sensors, vol. 21, no. 6, p. 2222, Mar. 2021, https://doi.org/10.3390/s21062222.
X. Zhang et al.,"Attention-Based Multi-Model Ensemble for Automatic Cataract Detection in B-Scan Eye Ultrasound Images," 2020 International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, 2020, pp. 1-10, https://doi.org/10.1109/IJCNN48605.2020.9207696.
S. C. Lingamaiah et al., “Attention-based deep learning model for clinical assessment of focal liver lesions using ultrasound imaging,” Biomedical Signal Processing and Control, vol. 116, p. 109563, Jan. 2026, https://doi.org/10.1016/j.bspc.2026.109563.
H. Jia, J. Zhang, K. Ma, X. Qiao, L. Ren, and X. Shi, “ Application of convolutional neural networks in medical images: a bibliometric analysis,” Quant Imaging Med Surg. vol 14, no. 5, pp. 3501-3518, May 1 2024, https://doi.org/10.21037/qims-23-1600.
DR. Sarvamangala, RV. Kulkarni, “ Convolutional neural networks in medical image understanding: a survey,” Evol Intell. Vol. 15, no. 1, pp. 1-22, 2022, https://doi.org/10.1007/s12065-020-00540-3.
Z. Fan et al., “TMAN: A triple morphological feature attention network for fine-grained classification of breast ultrasound images,” Expert Systems with Applications, vol. 234, 2023, Art. no. 120969, https://doi.org/10.1016/j.eswa.2023.120969.
M. Zhao et al., “An attention-based hybrid deep learning framework integrating brain connectivity and activity of resting-state functional MRI data,” Med Image Anal. Vol. 78:102413, May 2022, https://doi.org/ 10.1016/j.media.2022.102413.
R.G. Akindele et al., “ A hybrid attention-based deep learning framework for precise early diagnosis of Alzheimer’s disease,”. Discov Appl Sci, Vol 7, 856, 2025, https://doi.org/10.1007/s42452-025-07492-2
Z. Chen, C. Zhang, Z. Li, J. Yang and H. Deng, “ Automatic segmentation of ovarian follicles using deep neural network combined with edge information,” Front. Reprod. Health Vol. 4,877216, 2022, https://doi.org/10.3389/frph.2022.877216.
C. Kamala and J.M. Shivaram, “Segmentation of ovarian cyst using improved U-NET and hybrid deep learning model,” Multimed Tools Appl, Vol. 83, pp. 42645–42679, 2024, https://doi.org/10.1007/s11042-023-16998-z
M. Azmoodeh-Kalati et al.,” Leveraging an ensemble of EfficientNetV1 and EfficientNetV2 models for classification and interpretation of breast cancer histopathology images,” Sci Rep vol. 15, 21541, 2025, https://doi.org/10.1038/s41598-025-06853-6.
SS. Koshy et al.,”HED-Net: a hybrid ensemble deep learning framework for breast ultrasound image classification,” Front. Artif. Intell., vol 8:1672488, 2026 https://doi.org/10.3389/frai.2025.1672488.
B. T. Z. Afif, W. Wiharto, and U. Salamah, “Classification of Ultrasound Images Using ResNet-50 with a Convolutional Block Attention Module(CBAM)”, j.electron.electromedical.eng. med.inform, vol. 8, no. 1, pp. 284-303, Jan. 2026, https://doi.org/10.35882/jeeemi.v8i1.1406.
S. Pawar, P. Dhane, D. Shelke, P. Dheple and N. Doshi, “ PCOS Detection using Hybrid CNN-XGBoost Model - A Multimodal Data Approach,”. Biomed Pharmacol J, Vol. 18, no. 3, 2025, https://dx.doi.org/10.13005/bpj/3252
H. Liu, P. Zhang, J. Hu et al., “ Attention residual network for medical ultrasound image segmentation,” Sci Rep Vol. 15, 22155, 2025, https://doi.org/10.1038/s41598-025-04086-1
M.A. Aslam, A. Naveed, N. Ahmed et al., “ A hybrid attention network for accurate breast tumor segmentation in ultrasound images,” Sci Rep vol 15, 39633, 2025, https://doi.org/10.1038/s41598-025-23213-6.
E. Silambarasan, G. Nirmala, I. Mishra, “Polycystic ovary syndrome detection using optimized SVM and DenseNet,” Int. j. inf. tecnol. Vol. 17, pp. 1039–1047, 2025, https://doi.org/10.1007/s41870-024-02143-y.
N. Kaur, G. Gupta and P. Kaur, "Transfer-Based Deep Learning Technique for PCOS Detection Using Ultrasound Images," 2023 International Conference on Network, Multimedia and Information Technology (NMITCON), Bengaluru, India, 2023, pp. 1-6, https://doi.org/2010.1109/NMITCON58196.2023.10276245
K. S. Meghana, T. T, G. Shravinya and S. S. S. Siri, "XAI-Enabled Deep Convolutional Model for Polycystic Ovary Syndrome Detection from Ultrasound Imaging," 2025 IEEE Recent Advances in Intelligent Computational Systems (RAICS), Cochin, India, 2025, pp. 254-261,
https://doi.org/10.1109/RAICS66191.2025.11332581.
P.B. Patil et al., “Explainable ensemble-based machine learning model for polycystic ovary syndrome detection using hybrid feature selection,” Int. j. inf. tecnol., 2025, https://doi.org/10.1007/s41870-025-03044-4
P. Jain et al, “ Xplainable AI for deep learning model on PCOD analysis,” pp. 131-152, January 2024, https://doi.org/10.1016/B978-0-323-95315-3.00012-7.
V. Lakshmi, and B. Pushpa, “Explainable multimodal deep learning using cross-attention fusion of ultrasound and clinical features for PCOS classification,”Discov Computing vol. 29, no. 7, 2026. https://doi.org/10.1007/s10791-025-09901-x
A. Choudhari, Pcos detection using ultrasound images. https://www.kaggle.com/datasets/anaghachoudhari/pcosdetectionusingultrasoundimages (2024)
B. Zhao et al., “A Deep Learning-Based Automatic Recognition Model for Polycystic Ovary Ultrasound Images,” Balkan Med J. vol. 42, no. 5, pp. 419-428, sep 2025, doi: 10.4274/balkanmedj.galenos.2025.2025-5-114.
A. Alamoudi et al., “A deep learning fusion approach to diagnosis the polycystic ovary syndrome (PCOS),” Applied Computational Intelligence and Soft Computing, vol. 2023, pp. 1–15, Feb. 2023, https://doi.org/10.1155/2023/9686697.
P. Moral et al., “CystNet: An AI driven model for PCOS detection using multilevel thresholding of ultrasound images,” Scientific Reports, vol. 14, no. 1, p. 25012, Oct. 2024, https://doi.org/10.1038/s41598-024-75964-3
P. Bedi et al., “An integrated adaptive bilateral filterbased framework and attention residual Unet for detecting polycystic ovary syndrome,” Decision Analytics Journal, vol. 10, p. 100366, Nov. 2023, https://doi.org/10.1016/j.dajour.2023.100366.
P. Pratibha et al.,"Deep Learning Technique for Interpretable Diagnosis of Polycystic Ovary Syndrome in Ultrasound Imaging," Aptisi Transactions on Technopreneurship, Vol. 7., 2025, 779792, https://doi.org/10.34306/att.v7i3.768.
R. Vijayakumar et al., “PCOSVision A Hybrid Deep Learning Model for Polycystic Ovary Syndrome Detection using MobileNetV2 and Clinical Data,” in Advances in computer science research, 2025, pp. 865–877. https://doi.org/10.2991/9789464637182_74.
A. M. Naser, "Color to grayscale image conversion based dimensionality reduction with Stationary Wavelet transform," 2016 Al-Sadeq International Conference on Multidisciplinary in IT and Communication Science and Applications (AIC-MITCSA), Baghdad, Iraq, 2016, pp. 1-5, https://doi.org/10.1109/AIC-MITCSA.2016.7759946.
B. Wong et al., "Rethinking Pre-Trained Feature Extractor Selection in Multiple Instance Learning for Whole Slide Image Classification," 2025 IEEE 22nd International Symposium on Biomedical Imaging (ISBI), Houston, TX, USA, 2025, pp. 1-5, https://doi.org/10.1109/ISBI60581.2025.10981015.
N. Das and S. Das, “Attention-UNet architectures with pretrained backbones for multi-class cardiac MR image segmentation,” Current Problems in Cardiology, vol. 49, no. 1, p. 102129, Oct. 2023, https://doi.org/10.1016/j.cpcardiol.2023.102129.
G. Li et al., “HAM: Hybrid attention module in deep convolutional neural networks for image classification,” Pattern Recognition, vol. 129, p. 108785, May 2022, https://doi.org/10.1016/j.patcog.2022.108785.
F. Chahkoutahi et al.,“Loss functions in classification: An comprehensive overview and comparative study,” Applied Soft Computing, vol. 84, p. 113778, Aug. 2025, https://doi.org/10.1016/j.asoc.2025.113778.
S. A. Hicks et al., “On evaluation metrics for medical applications of artificial intelligence,” Scientific Reports, vol. 12, no. 1, p. 5979, Apr. 2022, https://doi.org/10.1038/s41598-022-09954-8.
M. S. Mohosheu et al., "ROC Based Performance Evaluation of Machine Learning Classifiers for Multiclass Imbalanced Intrusion Detection Dataset," 2023 IEEE 8th International Conference on Recent Advances and Innovations in Engineering, Kuala Lumpur, Malaysia, 2023, pp. 1-6, https://doi.org/10.1109/ICRAIE59459.2023.10468177.
Copyright (c) 2026 Pragati Patil, Nandini Chaudhari
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:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
