PneumoNet: Automated Detection of Pneumonia using Deep Neural Networks from Chest X-Ray Images

Zehra Kadiroğlu; Erkan Deniz; Mazhar Kayaoğlu; Hanifi Güldemir; Abdurrahman Şenyiğit; Abdülkadir Şengür

Makale detayları

PneumoNet: Automated Detection of Pneumonia using Deep Neural Networks from Chest X-Ray Images

Yazarlar:

Zehra Kadiroğlu | Erkan Deniz | Mazhar Kayaoğlu | Hanifi Güldemir | Abdurrahman Şenyiğit | Abdülkadir Şengür

Yayıncı:

Fırat University

Ana Başlıklar:

Computing Applications in Health

Dergi:

Turkish Journal of Science and Technology Vol.19 Issue 2, pp.325-338

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328533

pISSN:

1308-9080

Anahtar kelimeler:

Özet:

 Pneumonia is a dangerous disease that causes severe inflammation of the air sacs in the lungs. It is one of the infectious diseases with high morbidity and mortality in all age groups worldwide. Chest X-ray CXR is a diagnostic and imaging modality widely used in diagnosing pneumonia due to its low dose of ionizing radiation, low cost, and easy accessibility. Many deep learning methods have been proposed in various medical applications to assist clinicians in detecting and diagnosing pneumonia from CXR images. We have proposed a novel PneumoNet using a convolutional neural network CNN to detect pneumonia using CXR images accurately. Transformer-based deep learning methods, which have yielded high performance in natural language processing NLP problems, have recently attracted the attention of researchers. In this work, we have compared our results obtained using the CNN model with transformer-based architectures. These transformer architectures are vision transformer ViT, gated multilayer perceptron gMLP, MLP-mixer, and FNet. In this study, we have used the healthy and pneumonia CXR images from public and private databases to develop the model. Our developed PneumoNet model has yielded the highest accuracy of 96.50 and 94.29 for private and public databases, respectively, in detecting pneumonia accurately from healthy subjects.

 Pneumonia is a dangerous disease that causes severe inflammation of the air sacs in the lungs. It is one of the infectious diseases with high morbidity and mortality in all age groups worldwide. Chest X-ray CXR is a diagnostic and imaging modality widely used in diagnosing pneumonia due to its low dose of ionizing radiation, low cost, and easy accessibility. Many deep learning methods have been proposed in various medical applications to assist clinicians in detecting and diagnosing pneumonia from CXR images. We have proposed a novel PneumoNet using a convolutional neural network CNN to detect pneumonia using CXR images accurately. Transformer-based deep learning methods, which have yielded high performance in natural language processing NLP problems, have recently attracted the attention of researchers. In this work, we have compared our results obtained using the CNN model with transformer-based architectures. These transformer architectures are vision transformer ViT, gated multilayer perceptron gMLP, MLP-mixer, and FNet. In this study, we have used the healthy and pneumonia CXR images from public and private databases to develop the model. Our developed PneumoNet model has yielded the highest accuracy of 96.50 and 94.29 for private and public databases, respectively, in detecting pneumonia accurately from healthy subjects.

 Pneumonia is a dangerous disease that causes severe inflammation of the air sacs in the lungs. It is one of the infectious diseases with high morbidity and mortality in all age groups worldwide. Chest X-ray CXR is a diagnostic and imaging modality widely used in diagnosing pneumonia due to its low dose of ionizing radiation, low cost, and easy accessibility. Many deep learning methods have been proposed in various medical applications to assist clinicians in detecting and diagnosing pneumonia from CXR images. We have proposed a novel PneumoNet using a convolutional neural network CNN to detect pneumonia using CXR images accurately. Transformer-based deep learning methods, which have yielded high performance in natural language processing NLP problems, have recently attracted the attention of researchers. In this work, we have compared our results obtained using the CNN model with transformer-based architectures. These transformer architectures are vision transformer ViT, gated multilayer perceptron gMLP, MLP-mixer, and FNet. In this study, we have used the healthy and pneumonia CXR images from public and private databases to develop the model. Our developed PneumoNet model has yielded the highest accuracy of 96.50 and 94.29 for private and public databases, respectively, in detecting pneumonia accurately from healthy subjects.

 Pnömoni, akciğerlerdeki hava keseciklerinin şiddetli iltihaplanmasına neden olan tehlikeli bir hastalıktır. Dünya genelinde tüm yaş gruplarında yüksek morbidite ve mortaliteye sahip bulaşıcı hastalıklardan biridir. Göğüs röntgeni CXR, düşük iyonize radyasyon dozu, düşük maliyeti ve kolay erişilebilirliği nedeniyle pnömoni teşhisinde yaygın olarak kullanılan bir teşhis ve görüntüleme yöntemidir. Çeşitli tıbbi uygulamalarda klinisyenlere CXR görüntülerinden pnömoni tespit ve teşhisinde yardımcı olmak için birçok derin öğrenme yöntemi önerilmiştir. CXR görüntülerini kullanarak pnömoniyi doğru bir şekilde tespit etmek için evrişimsel sinir ağı ESA kullanan yeni bir PneumoNet önerilmiştir. Doğal dil işleme NLP problemlerinde yüksek performans sağlayan dönüştürücü tabanlı derin öğrenme yöntemleri son zamanlarda araştırmacıların ilgisini çekmektedir. Bu çalışmada, CNN modelini kullanarak elde ettiğimiz sonuçlar dönüştürücü tabanlı mimarilerle karşılaştırılmıştır. Bu dönüştürücü mimariler görüntü dönüştürücü ViT, kapılı çok katmanlı algılayıcı gMLP, MLP-mikser ve FNettir. Bu çalışmada, modeli geliştirmek için kamu ve özel veri tabanlarından sağlıklı ve pnömoni CXR görüntüleri kullanılmıştır. Geliştirdiğimiz PneumoNet modeli, sağlıklı bireylerden pnömoniyi doğru bir şekilde tespit etmede özel ve kamu veri tabanları için sırasıyla 96,50 ve 94,29luk en yüksek doğruluğu sağlamıştır.

Makale detayları

PneumoNet: Automated Detection of Pneumonia using Deep Neural Networks from Chest X-Ray Images

Yazarlar:

Zehra Kadiroğlu | Erkan Deniz | Mazhar Kayaoğlu | Hanifi Güldemir | Abdurrahman Şenyiğit | Abdülkadir Şengür

Yayıncı:

Fırat University

Ana Başlıklar:

Computing Applications in Health

Dergi:

Turkish Journal of Science and Technology Vol.19 Issue 2, pp.325-338

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328533

pISSN:

1308-9080

Pneumonia detection

medical image classification

chest x-ray imaging

transformer

deep neural networksPnömoni tespiti

tıbbi görüntü sınıflandırma

göğüs röntgeni görüntüleme

transformatör

derin sinir ağları.

Sayı

Makale detayları

Yazarlar: Zehra Kadiroğlu | Erkan Deniz | Mazhar Kayaoğlu | Hanifi Güldemir | Abdurrahman Şenyiğit | Abdülkadir Şengür

Yayıncı: Fırat University

Ana Başlıklar: Computing Applications in Health

Dergi: Turkish Journal of Science and Technology Vol.19 Issue 2, pp.325-338

Belge Tipi: Makale

Yayın Tarihi: 9/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001328533

pISSN: 1308-9080

Sayı

Yazarlar:

Zehra Kadiroğlu | Erkan Deniz | Mazhar Kayaoğlu | Hanifi Güldemir | Abdurrahman Şenyiğit | Abdülkadir Şengür

Yayıncı:

Fırat University

Ana Başlıklar:

Computing Applications in Health

Dergi:

Turkish Journal of Science and Technology Vol.19 Issue 2, pp.325-338

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328533

pISSN:

1308-9080