IAESONLINEIAESONLINE

Indonesian Journal of Electrical Engineering and Informatics (IJEEI)Indonesian Journal of Electrical Engineering and Informatics (IJEEI)

Polycystic Ovarian Syndrome (PCOS) is a hormone-related health condition in women, commonly classified as an endocrine disorder. It is most prevalent during the childbearing years, typically between the ages of 15 and 44. PCOS leads to hormonal imbalances that cause irregular menstrual cycles, hair loss, and other symptoms, and it is associated with long-term health risks such as heart disease and diabetes. Recent advances in deep learning have shown promising results in accurately recognizing and differentiating ovarian cysts from other ovarian tumours. This study proposes a novel technique for PCOS symptom detection by analysing ovarian images through feature extraction, classification, and metaheuristic-based optimization. Ovarian images are first pre-processed for noise removal and smoothing, followed by feature extraction and classification using a Convolutional Wavelet Attention Neural Network with a Naïve Bayes Fuzzy Autoencoder (CWANN–NBFA). Optimization is then performed using the Metaheuristic Multilevel Hawks Algae Optimization (MMHAO) algorithm. Experimental evaluations were conducted on multiple ovarian image datasets. The proposed technique achieved an accuracy of over 98% across the PCOSUSG, KFHU, and MMOTU datasets, demonstrating its robustness and effectiveness in addressing the challenges of PCOS detection.

This study presents a hybrid deep learning framework, CWANN–NBFA MMHAO, for accurate PCOS diagnosis from ultrasound images.The framework achieves superior performance across three benchmark datasets, with accuracies ranging from 98.Statistical analysis confirms the significance of these improvements.The proposed method demonstrates robustness and effective handling of uncertain data, outperforming classical image processing, CNN-based, and hybrid machine learning approaches.

Further research should focus on expanding the dataset to include more diverse patient samples to improve the robustness of the model. Investigating the integration of multi-modal data, such as clinical data alongside ultrasound images, could provide a more comprehensive diagnostic approach. Additionally, exploring methods to enhance model interpretability is crucial for building trust and facilitating clinical adoption. These advancements will contribute to the development of a more reliable and clinically applicable PCOS detection system, ultimately improving patient care and outcomes by enabling earlier and more accurate diagnoses. The proposed framework can be extended to incorporate transformer- or transfer learning-based models for further performance enhancement, and large-scale multi-centre clinical validation is needed to assess its real-world applicability.

  1. Transfer learning scenarios on deep learning for ultrasoundbased image segmentation | Bani Unggul | IAES... doi.org/10.11591/ijai.v13.i3.pp3273-3282Transfer learning scenarios on deep learning for ultrasoundbased image segmentation Bani Unggul IAES doi 10 11591 ijai v13 i3 pp3273 3282
  2. Medical X-ray images enhancement based on super resolution convolution neural network | Rani | International... doi.org/10.11591/ijict.v13i2.pp257-263Medical X ray images enhancement based on super resolution convolution neural network Rani International doi 10 11591 ijict v13i2 pp257 263
  3. A model for classifying breast masses in ultrasound images | Morsy | International Journal of Advances... doi.org/10.11591/ijaas.v13.i3.pp566-578A model for classifying breast masses in ultrasound images Morsy International Journal of Advances doi 10 11591 ijaas v13 i3 pp566 578
Read online
File size821.16 KB
Pages13
DMCAReport

Related /

JURIS Assessment of Readability of Vietnamese Text 2026More at 2026

POLNAMPOLNAM Aplikasi dan implikasi hasil studi ini dapat memberi manfaat bagi penyusun buku teks yang sedang mengembangkan buku K‑12 baru, termasuk siswa, guru,Aplikasi dan implikasi hasil studi ini dapat memberi manfaat bagi penyusun buku teks yang sedang mengembangkan buku K‑12 baru, termasuk siswa, guru,

JURIS Enhancing rice plant disease detection through transfer learning and image segmentation with YOLOv11 2026More at 2026

STTMCILEUNGSISTTMCILEUNGSI Perbaikan masa depan harus fokus pada peningkatan akurasi spasial dan ketangguhan melalui generasi data sintetik dan optimisasi arsitektur. Model YOLOv11-segPerbaikan masa depan harus fokus pada peningkatan akurasi spasial dan ketangguhan melalui generasi data sintetik dan optimisasi arsitektur. Model YOLOv11-seg

JURIS Explainable DDoS Detection with a CNN LSTM Hybrid Model and SHAP Interpretation 2026More at 2026

IAIIIAII The proposed method integrates Convolutional Neural Networks (CNN) to capture local traffic patterns and Long Short-Term Memory (LSTM) networks to modelThe proposed method integrates Convolutional Neural Networks (CNN) to capture local traffic patterns and Long Short-Term Memory (LSTM) networks to model

JURIS Enhanced Multi Class Pulmonary Disorder Detection Using Hard Voting Ensemble of CNN Models on X Ray Images 2025More at 2025

IAESONLINEIAESONLINE The proposed approach integrates five convolutional neural network (CNN) architectures—EfficientNetB0, DenseNet201, ResNet50, MobileNetV2, and InceptionV3—withinThe proposed approach integrates five convolutional neural network (CNN) architectures—EfficientNetB0, DenseNet201, ResNet50, MobileNetV2, and InceptionV3—within

JURIS Deep Learning Model for Face Anti Spoofing in Overcoming Domain Generalisation with Depth Estimation and Generative Adversarial Network 2025More at 2025

ITHBITHB Untuk model yang diimplementasikan dengan skenario simulasi intraset, hasil pengujian untuk dua dataset publik, yaitu NUAA dan CASIA, memberikan hasilUntuk model yang diimplementasikan dengan skenario simulasi intraset, hasil pengujian untuk dua dataset publik, yaitu NUAA dan CASIA, memberikan hasil

JURIS Algorithms for Question Answering to Factoid Question 2025More at 2025

ICSEJOURNALICSEJOURNAL Penelitian ini menggunakan metode SEMMA (Sample, Explore, Modify, Model, Assess) untuk memastikan proses analisis berjalan secara sistematis dan efisien.Penelitian ini menggunakan metode SEMMA (Sample, Explore, Modify, Model, Assess) untuk memastikan proses analisis berjalan secara sistematis dan efisien.

JURIS Image Segmentation in Aerial Imagery A Review 2023More at 2023

UMBUMB Objek tertentu juga mungkin terlihat mirip dari jarak jauh, seperti sungai dan jalan. Ada juga masalah kontras rendah, seperti perbedaan antara lapanganObjek tertentu juga mungkin terlihat mirip dari jarak jauh, seperti sungai dan jalan. Ada juga masalah kontras rendah, seperti perbedaan antara lapangan

JURIS Sentimen Ulasan Destinasi Wisata Pulau Bali Menggunakan Bidirectional Long Short Term Memory 2022More at 2022

BUMIGORABUMIGORA Penelitian dimulai dari pengumpulan data, perancangan alur program, preprocessing, pretraining Word2Vec, pembagian data uji dan data latih, pelatihan danPenelitian dimulai dari pengumpulan data, perancangan alur program, preprocessing, pretraining Word2Vec, pembagian data uji dan data latih, pelatihan dan

Useful /

JURIS Nilai Pendidikan Anak Berdasarkan QS Luqman 13 14 Di Era Digital 2026More at 2026

STIQ ALMULTAZAMSTIQ ALMULTAZAM Luqman: 13-14. Pendekatan kualitatif deskriptif digunakan dengan teknik pengumpulan data observasi dan wawancara. Hasil menunjukkan bahwa nilai QS. Luqman:13Luqman: 13-14. Pendekatan kualitatif deskriptif digunakan dengan teknik pengumpulan data observasi dan wawancara. Hasil menunjukkan bahwa nilai QS. Luqman:13

JURIS Stroke Prediction Using Machine Learning Method with Extreme Gradient Boosting Algorithm 2022More at 2022

BUMIGORABUMIGORA Hasilnya menunjukkan bahwa klasifikasi menggunakan XGBoost (Xtreme Gradient Boosting) mencapai akurasi terbaik sebesar 96%, yang merupakan hasil yang lebihHasilnya menunjukkan bahwa klasifikasi menggunakan XGBoost (Xtreme Gradient Boosting) mencapai akurasi terbaik sebesar 96%, yang merupakan hasil yang lebih

JURIS Sentiment Analysis of Food Order Tweets to Find Out Demographic Customer Profile Using SVM 2022More at 2022

BUMIGORABUMIGORA The Support Vector Machine (SVM) algorithm is used for text classification. Tweets are collected into data sets, training data, and testing data, thenThe Support Vector Machine (SVM) algorithm is used for text classification. Tweets are collected into data sets, training data, and testing data, then

JURIS Pengujian Kualitatif Aplikasi Informasi Gempa Bumi dalam Bentuk Suara untuk Tunanetra 2022More at 2022

BUMIGORABUMIGORA Penelitian ini menyimpulkan bahwa perangkat lunak untuk mengubah teks ke suara gempa bumi dapat bekerja sesuai harapan dan membantu penyandang tunanetraPenelitian ini menyimpulkan bahwa perangkat lunak untuk mengubah teks ke suara gempa bumi dapat bekerja sesuai harapan dan membantu penyandang tunanetra

ads-block-test