Automatic Meniscus Segmentation Using YOLO-Based Deep Learning Models with Ensemble Methods in Knee MRI Images
Küçük Resim Yok
Tarih
2025
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Mdpi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
The 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.
Açıklama
Anahtar Kelimeler
meniscus segmentation, magnetic resonance imaging, YOLO series, ensemble methods, voting methods
Kaynak
Applied Sciences-Basel
WoS Q Değeri
Q1
Scopus Q Değeri
Q1
Cilt
15
Sayı
5
