Geri Dön

Detection and classification of femoral neck fracture using YOLOv8

YOLOv8 kullanarak femoral boyun kırığının tespiti ve sınıflandırılması

  1. Tez No: 900134
  2. Yazar: MOUSAB ABIBI ABDI
  3. Danışmanlar: PROF. DR. RAFET AKDENİZ
  4. Tez Türü: Yüksek Lisans
  5. Konular: Bilgisayar Mühendisliği Bilimleri-Bilgisayar ve Kontrol, Computer Engineering and Computer Science and Control
  6. Anahtar Kelimeler: Belirtilmemiş.
  7. Yıl: 2024
  8. Dil: İngilizce
  9. Üniversite: İstanbul Aydın Üniversitesi
  10. Enstitü: Lisansüstü Eğitim Enstitüsü
  11. Ana Bilim Dalı: Bilgisayar Mühendisliği Ana Bilim Dalı
  12. Bilim Dalı: Bilgisayar Mühendisliği Bilim Dalı
  13. Sayfa Sayısı: Belirtilmemiş.

Özet

Femoral neck fractures are considered to be one of the most challenging orthopedic conditions because of the technical difficulties in the management of these injuries and possible complications, including nonunion and avascular necrosis. These fractures are common in elderly patients and they mostly occur due to low energy trauma such as falls. Early diagnosis and identification of femoral neck fractures are critical to proper clinical management and in reducing complications. This study employs the YOLOv8 model, which is a recent advancement in object detection, to detect and classify femoral neck fractures in X-ray images. The YOLOv8 model shows impressive results, with the mean Average Precision mAP50 of 97. 9%, a precision of 93. 5%, and a mAP50-95 of 62. 5%. Our proposed system encompasses several stages: data collecting, data preprocessing, model training, model validation, and model deployment. In the process of data preprocessing several data augmentation methods was performed to improve the model's resilience. The YOLOv8 model was then trained with this dataset and further rigorous testing conducted to determine the efficiency of the model. The results show that the proposed model has great potential for the automatic detection and classification of femoral neck fractures, which will be helpful for radiologists. When implemented in clinical environments, this system may increase diagnostic accuracy, decrease the workload, and consequently, benefit patients.

Özet (Çeviri)

Femoral neck fractures are considered to be one of the most challenging orthopedic conditions because of the technical difficulties in the management of these injuries and possible complications, including nonunion and avascular necrosis. These fractures are common in elderly patients and they mostly occur due to low energy trauma such as falls. Early diagnosis and identification of femoral neck fractures are critical to proper clinical management and in reducing complications. This study employs the YOLOv8 model, which is a recent advancement in object detection, to detect and classify femoral neck fractures in X-ray images. The YOLOv8 model shows impressive results, with the mean Average Precision mAP50 of 97. 9%, a precision of 93. 5%, and a mAP50-95 of 62. 5%. Our proposed system encompasses several stages: data collecting, data preprocessing, model training, model validation, and model deployment. In the process of data preprocessing several data augmentation methods was performed to improve the model's resilience. The YOLOv8 model was then trained with this dataset and further rigorous testing conducted to determine the efficiency of the model. The results show that the proposed model has great potential for the automatic detection and classification of femoral neck fractures, which will be helpful for radiologists. When implemented in clinical environments, this system may increase diagnostic accuracy, decrease the workload, and consequently, benefit patients.

Benzer Tezler

  1. Acil serviste proksimal femur fraktürlerinin tespitinde yapay zekanın kullanımı

    The use of artificial intelligence in the detection of proximal femur fractures in the emergency department

    EKREM BUĞRA GÖKÇEK

    Tıpta Uzmanlık

    Türkçe

    Türkçe

    2025

    Acil TıpAfyonkarahisar Sağlık Bilimleri Üniversitesi

    Acil Tıp Ana Bilim Dalı

    DOÇ. DR. AYŞE ERTEKİN

  2. Temel boyutlarıyla müziksel işitmenin incelenmesi

    Research in musical audibility with it's basic dimensions

    MEHLİKA DÜNDAR

    Yüksek Lisans

    Türkçe

    Türkçe

    1986

    MüzikGazi Üniversitesi

    SAADETTİN ÜNAL

  3. NaI (TI) dedektörleri için toplam verim ve tüm enerji pik duyarlığının Monte Carlo metodu ile elde edilmesi

    Başlık çevirisi yok

    N. REMZİYE ERGÜL

    Yüksek Lisans

    Türkçe

    Türkçe

    1987

    Fizik ve Fizik MühendisliğiUludağ Üniversitesi

    Fizik Ana Bilim Dalı

    PROF. DR. CİHAN ÖZMUTLU

  4. Lohusalıkta anneye verilen sağlık eğitiminin annenin doğum sonrası döneme ilişkin bilgi düzeyine etkisinin incelenmesi

    Başlık çevirisi yok

    HANDAN GÜLER

    Yüksek Lisans

    Türkçe

    Türkçe

    1987

    HemşirelikCumhuriyet Üniversitesi

    Hemşirelik Ana Bilim Dalı

    Y.DOÇ.DR. MELİHA ATALAY

  5. Boğazdan izole edilen coliform bakterilerin B- laktamaz enzim aktivitelerinin tesbit edilmesi ve B-laktamaz pozitif coliformların penisilinetkisinin inaktivasyonunun in vitro deneylerle gösterilmesi

    The Detection of beta-lactamasa activity of coliform bacteria isolated from th roat cultures and slovving the inactivation of penicilin by this beta lactamase produced by this caliform organisms

    GÜVEN URAZ

    Doktora

    Türkçe

    Türkçe

    1986

    MikrobiyolojiGazi Üniversitesi

    Genel Biyoloji Ana Bilim Dalı

    DOÇ. DR. ERDOĞAN BERKMAN