<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.4 20241031//EN"
        "https://jats.nlm.nih.gov/publishing/1.4/JATS-journalpublishing1-4.dtd">
<article  article-type="research-article"        dtd-version="1.4">
            <front>

                <journal-meta>
                                                                <journal-id>yyufbed</journal-id>
            <journal-title-group>
                                                                                    <journal-title>Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi</journal-title>
            </journal-title-group>
                            <issn pub-type="ppub">1300-5413</issn>
                                        <issn pub-type="epub">2667-467X</issn>
                                                                                            <publisher>
                    <publisher-name>Van Yüzüncü Yıl Üniversitesi</publisher-name>
                </publisher>
                    </journal-meta>
                <article-meta>
                                        <article-id pub-id-type="doi">10.53433/yyufbed.1858419</article-id>
                                                                <article-categories>
                                            <subj-group  xml:lang="en">
                                                            <subject>Decision Support and Group Support Systems</subject>
                                                            <subject>Data Structures and Algorithms</subject>
                                                    </subj-group>
                                            <subj-group  xml:lang="tr">
                                                            <subject>Karar Desteği ve Grup Destek Sistemleri</subject>
                                                            <subject>Veri Yapıları ve Algoritmalar</subject>
                                                    </subj-group>
                                    </article-categories>
                                                                                                                                                        <title-group>
                                                                                                                        <article-title>HydroKidneyNet: BT Görüntülemede Hidronefrozun Doğru Tespiti için Hibrit Yapay Zekâ Yöntemi</article-title>
                                                                                                                                                                                                <trans-title-group xml:lang="en">
                                    <trans-title>HydroKidneyNet: A Hybrid AI Method for Accurate Hydronephrosis Detection in CT Imaging</trans-title>
                                </trans-title-group>
                                                                                                    </title-group>
            
                                                    <contrib-group content-type="authors">
                                                                        <contrib contrib-type="author">
                                                                    <contrib-id contrib-id-type="orcid">
                                        https://orcid.org/0000-0001-8120-5101</contrib-id>
                                                                <name>
                                    <surname>Canayaz</surname>
                                    <given-names>Murat</given-names>
                                </name>
                                                                    <aff>Van Yüzüncü Yıl Üniversitesi</aff>
                                                            </contrib>
                                                    <contrib contrib-type="author">
                                                                    <contrib-id contrib-id-type="orcid">
                                        https://orcid.org/0000-0002-3164-7267</contrib-id>
                                                                <name>
                                    <surname>Yüksek</surname>
                                    <given-names>Mehmet</given-names>
                                </name>
                                                                    <aff>Van Bölge Eğitim ve Araştırma Hastanesi</aff>
                                                            </contrib>
                                                                                </contrib-group>
                        
                                        <pub-date pub-type="pub" iso-8601-date="20260429">
                    <day>04</day>
                    <month>29</month>
                    <year>2026</year>
                </pub-date>
                                        <volume>31</volume>
                                                    <fpage>126</fpage>
                                        <lpage>140</lpage>
                        
                        <history>
                                    <date date-type="received" iso-8601-date="20260108">
                        <day>01</day>
                        <month>08</month>
                        <year>2026</year>
                    </date>
                                                    <date date-type="accepted" iso-8601-date="20260413">
                        <day>04</day>
                        <month>13</month>
                        <year>2026</year>
                    </date>
                            </history>
                                        <permissions>
                    <copyright-statement>Copyright © 1995, Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi</copyright-statement>
                    <copyright-year>1995</copyright-year>
                    <copyright-holder>Yüzüncü Yıl Üniversitesi Fen Bilimleri Enstitüsü Dergisi</copyright-holder>
                </permissions>
            
                                                                                                <abstract><p>Hidronefroz, renal pelvis ve kalikslerin idrar akışının engellenmesi sonucu genişlemesiyle karakterize olup, tedavi edilmediğinde kalıcı böbrek hasarına yol açabilen önemli bir klinik durumdur. Bu çalışmada, kontrastsız bilgisayarlı tomografi (BT) görüntüleri kullanılarak hidronefrozun varlığına yönelik ikili sınıflandırma gerçekleştirilmiş ve çok aşamalı, yapay zekâ destekli bir analiz sistemi geliştirilmiştir. Önerilen yaklaşım, derin öğrenme tabanlı DenseNet mimarisi ile CBAM ve Squeeze-and-Excitation (SE) dikkat mekanizmalarının entegrasyonu sayesinde yüksek seviyeli öznitelik çıkarımı sağlamaktadır. Elde edilen derin özellikler üzerinde SelectKBest ve Principal Component Analysis (PCA) yöntemleri kullanılarak boyut indirgeme ve özellik seçimi uygulanmış; ardından Random Forest, Lojistik Regresyon ve Gradient Boosting gibi denetimli öğrenme algoritmaları ile sınıflandırma gerçekleştirilmiştir. Model performansı accuracy, precision, recall, F1-score ve ROC AUC metrikleri ile değerlendirilmiştir. Bulgular, SelectKBest tabanlı yaklaşımın sınıf ayrımında daha yüksek başarı sağladığını ve özellikle DenseNet169 tabanlı hibrit model ile birlikte %99,79 doğruluk ve F1-skoru değerine ulaşıldığını göstermektedir. PCA yöntemi ise daha düşük ancak oldukça rekabetçi performans sunarak modelin genelleme kabiliyetine katkı sağlamıştır. Ayrıca YOLOv11 tabanlı segmentasyon modeli ile hidronefrotik bölgeler yüksek doğrulukla belirlenmiş ve geliştirilen Flask tabanlı arayüz sayesinde sistemin klinik kullanım potansiyeli ortaya konmuştur. Elde edilen sonuçlar, uygun özellik seçimi yöntemleri ve hibrit yapay zekâ mimarilerinin birlikte kullanımının, hidronefrozun otomatik teşhisinde yüksek doğruluk, güçlü genelleme ve klinik uygulanabilirlik sunduğunu göstermektedir.</p></abstract>
                                                                                                                                    <trans-abstract xml:lang="en">
                            <p>Hydronephrosis is a clinically significant condition characterized by the dilation of the renal pelvis and calyces due to obstruction of urine flow, which can lead to permanent kidney damage if left untreated. In this study, a binary classification was performed to detect the presence of hydronephrosis using non-contrast computed tomography (CT) images, and a multi-stage artificial intelligence–based analysis system was developed. The proposed approach enables high-level feature extraction through the integration of a deep learning–based DenseNet architecture with CBAM (Convolutional Block Attention Module) and Squeeze-and-Excitation (SE) attention mechanisms. On the extracted deep features, dimensionality reduction and feature selection were performed using SelectKBest and Principal Component Analysis (PCA) methods, followed by classification using supervised learning algorithms such as Random Forest, Logistic Regression, and Gradient Boosting. Model performance was evaluated using accuracy, precision, recall, F1-score, and ROC AUC metrics. The results indicate that the SelectKBest-based approach provides higher class discrimination performance and achieves an accuracy and F1-score of 99.79%, particularly when combined with the DenseNet169-based hybrid model. The PCA method, on the other hand, yielded slightly lower yet highly competitive performance while contributing to the generalization capability of the model. In addition, the YOLOv11-based segmentation model successfully identified hydronephrotic regions with high accuracy, and the developed Flask-based interface demonstrated the clinical applicability of the system. The findings suggest that the combined use of appropriate feature selection methods and hybrid artificial intelligence architectures provides high accuracy, strong generalization, and clinical applicability for the automated diagnosis of hydronephrosis.</p></trans-abstract>
                                                            
            
                                                            <kwd-group>
                                                    <kwd>Hidronefroz</kwd>
                                                    <kwd>  Bilgisayarlı tomografi</kwd>
                                                    <kwd>  Makine öğrenmesi</kwd>
                                                    <kwd>  Özellik seçimi</kwd>
                                            </kwd-group>
                                                        
                                                                            <kwd-group xml:lang="en">
                                                    <kwd>Hydronephrosis</kwd>
                                                    <kwd>  CT</kwd>
                                                    <kwd>  Machine learning</kwd>
                                                    <kwd>  Feature extraction</kwd>
                                            </kwd-group>
                                                                                                            </article-meta>
    </front>
    <back>
                            <ref-list>
                                    <ref id="ref1">
                        <label>1</label>
                        <mixed-citation publication-type="journal">Alexa, R., Kranz, J., Kramann, R., Kuppe, C., Sanyal, R., Hayat, S., Casas Murillo, L. F., Hajili, T., Hoffmann, M., &amp; Saar, M. (2024). Harnessing artificial intelligence for enhanced renal analysis: Automated detection of hydronephrosis and precise kidney segmentation. European Urology Open Science, 62, 19–25. https://doi.org/10.1016/j.euros.2024.01.017</mixed-citation>
                    </ref>
                                    <ref id="ref2">
                        <label>2</label>
                        <mixed-citation publication-type="journal">Bugday, M. S., Akcicek, M., Bingol, H., &amp; Yildirim, M. (2023). Automatic diagnosis of ureteral stone and degree of hydronephrosis with proposed convolutional neural network, RelieF, and gradient-weighted class activation mapping based deep hybrid model. International Journal of Imaging Systems and Technology, 33(2), 760–769. https://doi.org/10.1002/ima.22847</mixed-citation>
                    </ref>
                                    <ref id="ref3">
                        <label>3</label>
                        <mixed-citation publication-type="journal">Canayaz, M. (2025). Attention-augmented DenseNet architectures with feature selection for high-performance image classification. In Proceedings of the International Symposium on AI-Driven Engineering Systems (June 19 20). Tokat, Turkey.</mixed-citation>
                    </ref>
                                    <ref id="ref4">
                        <label>4</label>
                        <mixed-citation publication-type="journal">Emir, H., &amp; Büyükünal, S. C. (2023). Doğum öncesi belirlenen hidronefrozun değerlendirilmesi. Türk Pediatri Arşivi, 41(1), 18–23. https://izlik.org/JA63TM96GA</mixed-citation>
                    </ref>
                                    <ref id="ref5">
                        <label>5</label>
                        <mixed-citation publication-type="journal">Huang, J., Geng, L., Hu, Y., Chen, Z., Geng, H., Cui, X., &amp; Fang, X. (2025). Deep learning algorithms to predict differential renal function &lt;40% in unilateral hydronephrosis based on key parameters of urinary tract ultrasound. Urology, 200, 179–185. https://doi.org/10.1016/j.urology.2025.04.009</mixed-citation>
                    </ref>
                                    <ref id="ref6">
                        <label>6</label>
                        <mixed-citation publication-type="journal">Khondker, A., Hua, S. B. Z., Kwong, J. C. C., Sheth, K., Alvarez, D., &amp; Velaer, K. N. (2025). Longitudinal image-based prediction of surgical intervention in infants with hydronephrosis using deep learning: Is a single ultrasound enough? PLOS Digital Health, 4(8), e0000939. https://doi.org/10.1371/journal.pdig.0000939</mixed-citation>
                    </ref>
                                    <ref id="ref7">
                        <label>7</label>
                        <mixed-citation publication-type="journal">Kumar, M., &amp; Puri, A.  (2020). Correlation of antenatal ultrasound parameters with the postnatal outcome of bilateral fetal hydronephrosis. J Obstet Gynecol India 70, 202–207. https://doi.org/10.1007/s13224-020-01318-4</mixed-citation>
                    </ref>
                                    <ref id="ref8">
                        <label>8</label>
                        <mixed-citation publication-type="journal">Lai, C., Hu, Z., Zhu, J., Dai, M., Qi, X., Zhai, Q., Luo, Y., Deng, C., Shi, J., Li, Z., Wu, Z., Liao, X., Zhao, Y., Bi, X., Zhou, Y., Liu, C., Huang, X., &amp; Xu, K. (2025). Development and validation of a deep learning-based automated computed tomography image segmentation and diagnostic model for infectious hydronephrosis: A retrospective multicentre cohort study. eClinicalMedicine, 82, 103146. https://doi.org/10.1016/j.eclinm.2025.103146</mixed-citation>
                    </ref>
                                    <ref id="ref9">
                        <label>9</label>
                        <mixed-citation publication-type="journal">Lee, YC.  (2021).  Ureteral stone with hydronephrosis and urolithiasis alone are risk factors for acute kidney injury in patients with urinary tract infection. Sci Rep 11, 23333 https://doi.org/10.1038/s41598-021-02647-8</mixed-citation>
                    </ref>
                                    <ref id="ref10">
                        <label>10</label>
                        <mixed-citation publication-type="journal">Lien, W.C., Chang, Y.C., Chou, H.H., Lin, L.C., Liu, Y.P., Liu, L., Chan, Y.T., &amp; Kuan, F.-S. (2023). Detecting hydronephrosis through ultrasound images using state-of-the-art deep learning models. Ultrasound in Medicine &amp; Biology, 49(3), 723–733. https://doi.org/10.1016/j.ultrasmedbio.2022.10.001</mixed-citation>
                    </ref>
                                    <ref id="ref11">
                        <label>11</label>
                        <mixed-citation publication-type="journal">Mahmud, S., Abbas, T. O., Chowdhury, M. E. H., Mushtak, A., Kabir, S., Muthiyal, S., Koko, A., Altyebh, A. B. A., Alqahtani, A., Khandakar, A., &amp; Islam, S. M. S. (2024). Automated grading of prenatal hydronephrosis severity from segmented kidney ultrasounds using deep learning. Expert Systems with Applications, 255, 124594. https://doi.org/10.1016/j.eswa.2024.124594</mixed-citation>
                    </ref>
                                    <ref id="ref12">
                        <label>12</label>
                        <mixed-citation publication-type="journal">Smail, L. C., Dhindsa, K., Braga, L. H., Becker, S., &amp; Sonnadara, R. R. (2020). Using deep learning algorithms to grade hydronephrosis severity: Toward a clinical adjunct. Frontiers in Pediatrics, 8, 1. https://doi.org/10.3389/fped.2020.00001</mixed-citation>
                    </ref>
                                    <ref id="ref13">
                        <label>13</label>
                        <mixed-citation publication-type="journal">Smith, D., &amp; Kasivisvanathan, V. (2019). Factors associated with spontaneous stone passage in a contemporary cohort of patients presenting with acute ureteric colic: results from the Multi-centre cohort study evaluating the role of Inflammatory Markers In patients presenting with acute ureteric Colic (MIMIC) study. BJU Int, 124: 504-513. https://doi.org/10.1111/bju.14777</mixed-citation>
                    </ref>
                                    <ref id="ref14">
                        <label>14</label>
                        <mixed-citation publication-type="journal">Song, S. H., Han, J. H., Kim, K. S., Cho, Y. A., Youn, H. J., Kim, Y. I., &amp; Kweon, J. (2022). Deep-learning segmentation of ultrasound images for automated calculation of the hydronephrosis area to renal parenchyma ratio. Investigative and Clinical Urology, 63(4), 455–463. https://doi.org/10.4111/icu.20220085</mixed-citation>
                    </ref>
                                    <ref id="ref15">
                        <label>15</label>
                        <mixed-citation publication-type="journal">Sun, H., Zhu, Z., Zhang, A., Liu, B., Lin, Z., Huang, L., Yang, M., Liu, L., Lin, S., &amp; Ding, W. (2026). KidMesh: computational mesh reconstruction for pediatric congenital hydronephrosis using deep neural networks. ArXiv, abs/2602.13299.</mixed-citation>
                    </ref>
                                    <ref id="ref16">
                        <label>16</label>
                        <mixed-citation publication-type="journal">Svrcek, P. T., Jang, P. T. J., Ge, P. T. J. C., Lee, P. T. J. C. H., Kim, P. T. J. C. H. Y. H. (2025). Combined application of deep learning and conventional computer vision for kidney ultrasound image classification in chronic kidney disease: preliminary study. Ultrasonography, 44(5), 346–353. https://doi.org/10.14366/usg.25074</mixed-citation>
                    </ref>
                                    <ref id="ref17">
                        <label>17</label>
                        <mixed-citation publication-type="journal">Xia, J., Deng, S., &amp; Hu, Y. (2026). A novel diagnostic model to grade the impairment of split renal function for patients with obstructive hydronephrosis based on enhanced CT imaging. Chinese Journal of Academic Radiology, 9, 31–41. https://doi.org/10.1007/s42058-025-00215-x</mixed-citation>
                    </ref>
                                    <ref id="ref18">
                        <label>18</label>
                        <mixed-citation publication-type="journal">Vallasciani, S., Tekin, A., &amp; Abbas, T. O. (2021). Hydronephrosis classifications: Has UTD overtaken APD and SFU? A worldwide survey. Frontiers in Pediatrics, 9, 646517. https://doi.org/10.3389/fped.2021.646517</mixed-citation>
                    </ref>
                                    <ref id="ref19">
                        <label>19</label>
                        <mixed-citation publication-type="journal">Yang, M., Zhu, Z., Huang, L., Sun, H., Lin, X., Li, N., Pan, L., Lin, S., &amp; Ding, W. (2026). Non-invasive urine flow dynamics characterization of pediatric hydronephrosis based on deep learning and computational fluid dynamics. Computer Methods and Programs in Biomedicine, 273, 109077. https://doi.org/10.1016/j.cmpb.2025.109077</mixed-citation>
                    </ref>
                            </ref-list>
                    </back>
    </article>
