Comparison of Hybrid Models with Multi-Feature Fusion Using Covid-19 Radiography Database

Fatma Günseli Yaşar Çıklaçandır; Gözde Ulutagay

Makale detayları

Comparison of Hybrid Models with Multi-Feature Fusion Using Covid-19 Radiography Database

Yazarlar:

Fatma Günseli Yaşar Çıklaçandır | Gözde Ulutagay

Yayıncı:

Dokuz Eylul University

Ana Başlıklar:

Bilgisayar Görüşü ve Çoklu Ortam Hesaplama (Diğer)

Dergi:

Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 80, pp.326-336

Belge Tipi:

Makale

Yayın Tarihi:

5/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348195

pISSN:

1302-9304

Anahtar kelimeler:

Özet:

 COVID-19, which emerged in 2019 and was subsequently classified as a pandemic, has affected millions of individuals worldwide. Different variations of the illness continue to persist, even though it may seem to have subsided at the moment. Hence, it remains essential to promptly and precisely diagnose COVID-19. Chest imaging has been proven to clearly demonstrate COVID-19 infection even in the early stages of the disease, assisting physicians and radiologists in making quicker and more accurate judgements. This study proposes a hybrid model with feature fusion based on Convolutional Neural Network based models and classifiers to accurately distinguish infected patients from healthy people. The extracted features from two different Convolutional Neural Network based models are concatenated, or added before feature selection. On a publicly accessible radiography database containing 21168 images of the four classes Covid, Lung_Opacity, Normal, and Viral Pneumonia, extensive tests utilizing five fold cross-validation have been conducted. According to the tests, an accuracy rate of about 96 has been obtained. The findings also demonstrate that the proposed approach can contribute significantly to the rapidly expanding workload in health-care systems.

 COVID-19, which emerged in 2019 and was subsequently classified as a pandemic, has affected millions of individuals worldwide. Different variations of the illness continue to persist, even though it may seem to have subsided at the moment. Hence, it remains essential to promptly and precisely diagnose COVID-19. Chest imaging has been proven to clearly demonstrate COVID-19 infection even in the early stages of the disease, assisting physicians and radiologists in making quicker and more accurate judgements. This study proposes a hybrid model with feature fusion based on Convolutional Neural Network based models and classifiers to accurately distinguish infected patients from healthy people. The extracted features from two different Convolutional Neural Network based models are concatenated, or added before feature selection. On a publicly accessible radiography database containing 21168 images of the four classes Covid, Lung_Opacity, Normal, and Viral Pneumonia, extensive tests utilizing five fold cross-validation have been conducted. According to the tests, an accuracy rate of about 96 has been obtained. The findings also demonstrate that the proposed approach can contribute significantly to the rapidly expanding workload in health-care systems.

 COVID-19, which emerged in 2019 and was subsequently classified as a pandemic, has affected millions of individuals worldwide. Different variations of the illness continue to persist, even though it may seem to have subsided at the moment. Hence, it remains essential to promptly and precisely diagnose COVID-19. Chest imaging has been proven to clearly demonstrate COVID-19 infection even in the early stages of the disease, assisting physicians and radiologists in making quicker and more accurate judgements. This study proposes a hybrid model with feature fusion based on Convolutional Neural Network based models and classifiers to accurately distinguish infected patients from healthy people. The extracted features from two different Convolutional Neural Network based models are concatenated, or added before feature selection. On a publicly accessible radiography database containing 21168 images of the four classes Covid, Lung_Opacity, Normal, and Viral Pneumonia, extensive tests utilizing five fold cross-validation have been conducted. According to the tests, an accuracy rate of about 96 has been obtained. The findings also demonstrate that the proposed approach can contribute significantly to the rapidly expanding workload in health-care systems.

 COVID-19, dünya çapında milyonlarca kişiyi etkiledi. Şu anda azalmış gibi görünse de hastalığın farklı varyasyonları devam ediyor. Bu nedenle, COVID-19u hızlı ve kesin bir şekilde teşhis etmek hala hayati önem taşıyor. Göğüs görüntülemenin, hastalığın erken evrelerinde bile COVID-19 enfeksiyonunu açıkça gösterdiği, doktorların ve radyologların daha hızlı ve daha doğru kararlar almasına yardımcı olduğu kanıtlanmıştır. Bu çalışma, enfekte hastaları sağlıklı insanlardan doğru bir şekilde ayırt etmek için Evrişimsel Sinir Ağı tabanlı modellere ve sınıflandırıcılara dayalı özellik füzyonuna sahip hibrit bir model önermektedir. İki farklı Evrişimsel Sinir Ağı tabanlı modelden çıkarılan özellikler birleştirilir veya özellik seçiminden önce eklenir. Dört sınıftan Covid, Lung_Opacity, Normal ve Viral Pneumonia 21.168 görüntüyü içeren, kamuya açık bir radyografi veritabanında, beş kat çapraz doğrulamayı kullanan kapsamlı testler yapılmıştır. Yapılan testlere göre yaklaşık 96 oranında doğruluk oranı elde edildi. Bulgular ayrıca önerilen yaklaşımın sağlık sistemlerinde hızla artan iş yüküne önemli ölçüde katkıda bulunabileceğini göstermektedir.

Makale detayları

Comparison of Hybrid Models with Multi-Feature Fusion Using Covid-19 Radiography Database

Yazarlar:

Fatma Günseli Yaşar Çıklaçandır | Gözde Ulutagay

Yayıncı:

Dokuz Eylul University

Ana Başlıklar:

Bilgisayar Görüşü ve Çoklu Ortam Hesaplama (Diğer)

Dergi:

Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 80, pp.326-336

Belge Tipi:

Makale

Yayın Tarihi:

5/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348195

pISSN:

1302-9304

Feature Extraction

Feature Fusion

Deep LearningÖznitelik Çıkarma

Öznitelik Füzyonu

Derin Öğrenme

Sayı

Makale detayları

Comparison of Hybrid Models with Multi-Feature Fusion Using Covid-19 Radiography Database

Yazarlar: Fatma Günseli Yaşar Çıklaçandır | Gözde Ulutagay

Yayıncı: Dokuz Eylul University

Ana Başlıklar: Bilgisayar Görüşü ve Çoklu Ortam Hesaplama (Diğer)

Dergi: Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 80, pp.326-336

Belge Tipi: Makale

Yayın Tarihi: 5/2025

Belge Dili: İngilizce

Document ID (Org No.): 2001348195

pISSN: 1302-9304

Feature Extraction

Feature Fusion

Deep LearningÖznitelik Çıkarma

Öznitelik Füzyonu

Derin Öğrenme

Sayı

Yazarlar:

Fatma Günseli Yaşar Çıklaçandır | Gözde Ulutagay

Yayıncı:

Dokuz Eylul University

Ana Başlıklar:

Bilgisayar Görüşü ve Çoklu Ortam Hesaplama (Diğer)

Dergi:

Dokuz Eylül Üniversitesi Mühendislik Fakültesi Fen ve Mühendislik Dergisi Vol.27 Issue 80, pp.326-336

Belge Tipi:

Makale

Yayın Tarihi:

5/2025

Belge Dili:

İngilizce

Document ID (Org No.):

2001348195

pISSN:

1302-9304