Abstract：In polycystic ovary syndrome(PCOS) clinical data analysis, many models often suffer from underfitting, while convolutional neural networks are limited by their receptive fields. To address these issues, a stamen-pistil convolutional network(SPCNet) is proposed. The design of SPCNet is inspired by the collaborative structure of stamens and pistils in flowers. The pistil convolution passes vertically through the main information stream to extract global features, while the stamen convolution performs supplementary sampling from the horizontal neighborhood. The structure of floral reproductive organs is adopted in the design of convolutional operators to improve feature extraction. By expanding the sampling space in both longitudinal and transverse directions, SPCNet effectively compensates for the limitations of existing PCOS processing approaches. Experiments on two public PCOS datasets show that SPCNet improves computational efficiency and achieves higher prediction accuracy with lightweight structure, thereby better meeting the needs for instant analysis of complex PCOS clinical data.
[1] 袁莹莹,赵君利. 多囊卵巢综合征流行病学特点. 中国实用妇科与产科杂志, 2019, 35(3): 261-264. (YUAN Y Y, ZHAO J L. Epidemiological Features of Polycystic Ovary Syndrome. Chinese Journal of Practical Gynecology and Obstetrics, 2019, 35(3): 261-264.) [2] 吴效科,周珊英,苏延华. 多囊卵巢综合征患者的胰岛素抵抗. 中华妇产科杂志, 1999(11): 698-701. (WU X K, ZHOU S Y, SU Y H. Insulin Resistance in Patients with Polycystic Ovary Syndrome. Chinese Journal of Obstetrics and Gynecology, 1999(11): 698-701.) [3] RAO D, DAYMA R R, PENDEKANTI S K, et al. Deep Learning Model for Diagnosing Polycystic Ovary Syndrome Using a Comprehensive Dataset from Kerala Hospitals. International Journal of Electrical and Computer Engineering(IJECE), 2024, 14(5): 5715-5727. [4] HUSSAIN A, MAHTO A K, SINHA K, et al. Exploring Machine Learning Models for Efficient Polycystic Ovary Syndrome Diagnosis. Journal of Propulsion Technology, 2024, 45(2): 1490-1501. [5] ERDEMIR E, ERDAŞÇ B. Evaluation of Deep Learning Techniques in the Diagnosis of Polycystic Ovary Syndrome // Proc of the Medical Technologies Congress. Washington, USA: IEEE, 2023. DOI: 10.1109/TIPTEKNO59875.2023.10359221. [6] GARZIA E, GALIANO V, MARFIA G, et al. Hyperandrogenism and Menstrual Imbalance Are the Best Predictors of Metformin Response in PCOS Patients. Reproductive Biology and Endocrinology, 2022, 20(1). DOI: 10.2139/ssrn.3696909. [7] HUANG C C, YANG P K, HUANG Y S, et al. The Role of Circulating miRNAs in Mechanism of Action and Prediction of Therapeutic Responses of Metformin in Polycystic Ovarian Syndrome. Fertility and Sterility, 2023, 119(5): 858-868. [8] SHARMA A, KRICK B, LI Y, et al. The Use of Ceramides to Predict Metabolic Response to Metformin in Women with PCOS. Journal of the Endocrine Society, 2022, 6(11). DOI: 10.1210/jendso/bvac131. [9] LIM J, Li J Y, FENG X, et al. Machine Learning Classification of polycystic Ovary Syndrome Based on Radial Pulse Wave Analysis. BMC Complementary Medicine and Therapies, 2023, 23(1). DOI: 10.1186/s12906-023-04249-5. [10] BIÇER N Ç, ERMIŞ A A, BAŞ D. The Role of Different Methods in Defining Cardiometabolic Risk and Metabolic Syndrome in Women with Polycystic Ovary Syndrome. Life, 2023, 13(10). DOI: 10.3390/life13101959. [11] GONZÁLEZ-MARTÍN J M, TORRES-MATA L B, CAZORLA-RI-VERO S, et al. An Artificial Intelligence Prediction Model of Insulin Sensitivity, Insulin Resistance, and Diabetes Using Genes Obtained through Differential Expression. Genes, 2023, 14(12). DOI: 10.3390/genes14122119. [12] NA Z J, JIANG H Y, MENG Y X, et al. Association of Galactose and Insulin Resistance in Polycystic Ovary Syndrome: A Case-Control Study. eClinicalMedicine, 2022, 47. DOI: 10.1016/j.eclinm.2022.101379. [13] PRASHER S, NELSON L. Follicle Prediction for Polycystic Ovary Syndrome Diagnosis from Ovarian Ultrasound Images Using CNN // Proc of the 10th International Conference on Computing for Sustainable Global Development. Washington, USA: IEEE, 2023: 789-793. [14] BHOSALE S, JOSHI L, SHIVSHARAN A. PCOS (Polycystic Ovarian Syndrome) Detection Using Deep Learning. International Research Journal of Moderinization in Engineering Technology and Science, 2022, 4(1): 195-200. [15] 张阳,凌娜,张国华,等. 基于深度学习多囊卵巢综合征辨证分型的构建与实现. 辽宁中医药大学学报, 2019, 21(5): 13-16. (ZHANG Y, LING N, ZHANG G H, et al. Construction and Implementation of Dialectical Classification of Polycystic Ovary Syndrome Based on Deep Learning. Journal of Liaoning University of TCM, 2019, 21(5): 13-16.) [16] 郭姗珊,陈厚儒,王书云,等. 中医信息系统对多囊卵巢综合征的分型研究. 北京生物医学工程, 2023, 42(2): 170-177. (GUO S S, CHEN H R, WANG S Y, et al. Classification of Polycystic Ovary Syndrome by TCM Information System. Beijing Biomedical Engineering, 2023, 42(2): 170-177.) [17] 陆玉婷,盛正和,黄菲,等. 基于6种机器学习算法的早发性卵巢功能不全影响因素分析. 郑州大学学报(医学版), 2024, 59(2): 246-251. (LU Y T, SHENG Z H, HUANG F, et al. Analysis of Influencing Factors of Premature Ovarian Insufficiency Based on 6 Machine Learning Algorithms. Journal of Zhengzhou University(Medical Sciences), 2024, 59(2): 246-251.) [18] 范明皓,袁军梅,任丽红,等. PCOS不孕患者外周血NLRP3、CTRP6、IL-1β水平与IVF-ET妊娠结局的关系分析. 中国妇产科临床杂志, 2025, 26(3): 239-242. (FAN M H, YUAN J M, REN L H, et al. Relationship between Peripheral Blood NLRP3, CTRP6, IL-1β and Pregnancy Outcomes of IVF-ET in Infertility Patients with PCOS. Chinese Journal of Clinical Obstetrics and Gynecology, 2025, 26(3): 239-242.) [19] TROCKMAN A, KOLTER J Z. Patches Are All You Need?[C/OL]. [2025-07-12]. https://arxiv.org/pdf/2201.09792. [20] CHEN S F, XIE E Z, GE C J, et al. CycleMLP: A MLP-Like Architecture for Dense Visual Predictions. IEEE Transactions on Pa-ttern Analysis and Machine Intelligence, 2023, 45(12): 14284-14300. [21] WANG Z Y, JIANG W H, ZHU Y M, et al. DynaMixer: A Vision MLP Architecture with Dynamic Mixing // Proc of the 39th International Conference on Machine Learning. San Francisco, USA: Morgan Kaufmann, 2022: 22691-22701. [22] RAO Y M, ZHAO W L, ZHU Z, et al. GFNet: Global Filter Networks for Visual Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(9): 10960-10973. [23] LIU H X, DAI Z H, SO D R, et al. Pay Attention to MLPs[C/OL].[2025-07-12]. https://arxiv.org/pdf/2105.08050. [24] TOLSTIKHIN I, HOULSBY N, KOLESNIKOV A, et al. MLP-Mixer: An All-MLP Architecture for Vision // Proc of the 35th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2021: 24261-24272. [25] MUNIR M, AVERY W, MARCULESCU R. MobileViG: Graph-Based Sparse Attention for Mobile Vision Applications // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Washington, USA: IEEE, 2023: 2211-2219. [26] TATSUNAMI Y, TAKI M. Sequencer: Deep LSTM for Image Cla-ssification // Proc of the 36th International Conference on Neural Information Processing Systems. Cambridge, USA: MIT Press, 2022: 38204-38217.
2025, Vol. 38 
