Automatic Meniscus Segmentation Using YOLO-Based Deep Learning Models with Ensemble Methods in Knee MRI Images

Basit Öğe Kaydı
dc.authoridDincel, Yasar Mahsut/0000-0001-6576-1802
dc.contributor.authorSimsek, Mehmet Ali
dc.contributor.authorSertbas, Ahmet
dc.contributor.authorSasani, Hadi
dc.contributor.authorDincel, Yasar Mahsut
dc.date.accessioned2025-04-06T12:23:40Z
dc.date.available2025-04-06T12:23:40Z
dc.date.issued2025
dc.departmentTekirdağ Namık Kemal Üniversitesi
dc.description.abstractThe meniscus is a C-shaped connective tissue with a cartilage-like structure in the knee joint. This study proposes an innovative method based on You Only Look Once (YOLO) series models and ensemble methods for meniscus segmentation from knee magnetic resonance imaging (MRI) images to improve segmentation performance and evaluate generalization capability. In this study, five different segmentation models were trained, and masks were created from the YOLO series. These masks are combined with pixel-based voting, weighted multiple voting, and dynamic weighted multiple voting optimized by grid search. Tests were conducted on internal and external sets and various metrics. The dynamic weighted multiple voting method optimized with grid search performed the best on both the test set (DSC: 0.8976 +/- 0.0071, PPV: 0.8561 +/- 0.0121, Sensitivity: 0.9467 +/- 0.0077) and the external set (DSC: 0.9004 +/- 0.0064, PPV: 0.8876 +/- 0.0134, Sensitivity: 0.9200 +/- 0.0119). The proposed ensemble methods offer high accuracy, reliability, and generalization capability for meniscus segmentation.
dc.identifier.doi10.3390/app15052752
dc.identifier.issn2076-3417
dc.identifier.issue5
dc.identifier.scopus2-s2.0-86000647125
dc.identifier.scopusqualityQ1
dc.identifier.urihttps://doi.org/10.3390/app15052752
dc.identifier.urihttps://hdl.handle.net/20.500.11776/17125
dc.identifier.volume15
dc.identifier.wosWOS:001442660800001
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherMdpi
dc.relation.ispartofApplied Sciences-Basel
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250406
dc.subjectmeniscus segmentation
dc.subjectmagnetic resonance imaging
dc.subjectYOLO series
dc.subjectensemble methods
dc.subjectvoting methods
dc.titleAutomatic Meniscus Segmentation Using YOLO-Based Deep Learning Models with Ensemble Methods in Knee MRI Images
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu