Pretrained Models and the Role of Feature Selection: An Artificial Intelligence-Based Approach in the Diagnosis of Diabetic Retinopathy

Mehmet Kaan Kaya; Burak Tasci

Makale detayları

Pretrained Models and the Role of Feature Selection: An Artificial Intelligence-Based Approach in the Diagnosis of Diabetic Retinopathy

Yazarlar:

Mehmet Kaan Kaya | Burak Tasci

Yayıncı:

Fırat University

Ana Başlıklar:

Deep Learning | Computing Applications in Health

Dergi:

Turkish Journal of Science and Technology Vol.18 Issue 2, pp.511-517

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001290410

pISSN:

1308-9080

Anahtar kelimeler:

Özet:

 Diabetic retinopathy is a significant complication occurring in the retina of the eye as a result of prolonged diabetes. When not detected early, this condition can lead to vision loss. Advanced image processing techniques and artificial intelligence algorithms have enhanced the possibilities of early diagnosis and treatment. This article discusses current advancements in artificial intelligence-based diabetic retinopathy detection and explores future possibilities in this field. In the experimental studies of the article, the Kaggle Aptos 2019 dataset was utilized. This dataset comprises 5 classes and a total of 3662 images. The class distribution is as follows: No DR No Diabetic Retinopathy: 1805, Mild: 370, Moderate: 999, Severe: 193, Proliferative DR: 295. The study consists of four fundamental stages. These stages are 1 Feature extraction from VGG16 and VGG19 pretrained models, 2 Feature selection using NCA, Relieff, and Chi2, 3 Classification with Support Vector Machine classifier, 4 Iterative Majority Voting. Using the proposed method, a high accuracy of 99.18 is achieved. Furthermore, sensitivity of 100 for the No DR class, sensitivity of 100 for the Moderate class, sensitivity of 98.80 for the Severe class, and an F1-Score of 99.89 for the No DR class are obtained. This study demonstrates the effective utilization of machine learning methods in diabetic retinopathy diagnosis. The experimental results underscore the significant contributions of diabetic retinopathy patients diagnosis and treatment processes.

 Diabetic retinopathy is a significant complication occurring in the retina of the eye as a result of prolonged diabetes. When not detected early, this condition can lead to vision loss. Advanced image processing techniques and artificial intelligence algorithms have enhanced the possibilities of early diagnosis and treatment. This article discusses current advancements in artificial intelligence-based diabetic retinopathy detection and explores future possibilities in this field. In the experimental studies of the article, the Kaggle Aptos 2019 dataset was utilized. This dataset comprises 5 classes and a total of 3662 images. The class distribution is as follows: No DR No Diabetic Retinopathy: 1805, Mild: 370, Moderate: 999, Severe: 193, Proliferative DR: 295. The study consists of four fundamental stages. These stages are 1 Feature extraction from VGG16 and VGG19 pretrained models, 2 Feature selection using NCA, Relieff, and Chi2, 3 Classification with Support Vector Machine classifier, 4 Iterative Majority Voting. Using the proposed method, a high accuracy of 99.18 is achieved. Furthermore, sensitivity of 100 for the No DR class, sensitivity of 100 for the Moderate class, sensitivity of 98.80 for the Severe class, and an F1-Score of 99.89 for the No DR class are obtained. This study demonstrates the effective utilization of machine learning methods in diabetic retinopathy diagnosis. The experimental results underscore the significant contributions of diabetic retinopathy patients diagnosis and treatment processes.

 Diabetic retinopathy is a significant complication occurring in the retina of the eye as a result of prolonged diabetes. When not detected early, this condition can lead to vision loss. Advanced image processing techniques and artificial intelligence algorithms have enhanced the possibilities of early diagnosis and treatment. This article discusses current advancements in artificial intelligence-based diabetic retinopathy detection and explores future possibilities in this field. In the experimental studies of the article, the Kaggle Aptos 2019 dataset was utilized. This dataset comprises 5 classes and a total of 3662 images. The class distribution is as follows: No DR No Diabetic Retinopathy: 1805, Mild: 370, Moderate: 999, Severe: 193, Proliferative DR: 295. The study consists of four fundamental stages. These stages are 1 Feature extraction from VGG16 and VGG19 pretrained models, 2 Feature selection using NCA, Relieff, and Chi2, 3 Classification with Support Vector Machine classifier, 4 Iterative Majority Voting. Using the proposed method, a high accuracy of 99.18 is achieved. Furthermore, sensitivity of 100 for the No DR class, sensitivity of 100 for the Moderate class, sensitivity of 98.80 for the Severe class, and an F1-Score of 99.89 for the No DR class are obtained. This study demonstrates the effective utilization of machine learning methods in diabetic retinopathy diagnosis. The experimental results underscore the significant contributions of diabetic retinopathy patients diagnosis and treatment processes.

 Diyabetik retinopati, uzun süreli diyabet hastalığının bir sonucu olarak gözün retinasında meydana gelen ciddi bir komplikasyondur. Erken teşhis edilmediğinde görme kaybına neden olabilen bu durum, gelişmiş görüntü işleme teknikleri ve yapay zeka algoritmalarının kullanımıyla erken teşhis ve tedavi imkanlarını artırmıştır. Bu makalede, yapay zeka tabanlı diyabetik retinopati tespiti alanındaki güncel gelişmeler ve geleceğe yönelik ihtimaller ele alınmıştır. Makalemizin deneysel çalışmalarında, Kaggle Aptos 2019 veri seti kullanılmıştır. Bu verisetinde 5 sınıf bulunmaktadır ve toplamda 3662 görüntü içerir. Sınıf dağılımı şu şekildedir: DR Diyabet Retinopatisi yok: 1805, Hafif: 370, Orta: 999, Şiddetli: 193, Proliferatif DR: 295. Çalışma dört temel yapıdan oluşur. Bu aşamalar 1 VGG16 ve VGG19 ön eğitimli modellerinden özellik çıkarma, 2 Nca, relieff ve chi2 ile özellik seçimi,3 destek vektör makinesi sınıflandırıcı ile Sınıflandırma,4 yinelemeli çoğunluk oylamadır. Önerilen yöntem kullanılarak 99.18lik yüksek bir doğruluk elde edilmiştir. Ayrıca, Dr yok sınıfı için 100 hassasiyet, Orta sınıfı için 100 duyarlılık, Şiddetli sınıfı için 98.80 duyarlılık ve Dr yok sınıfı için 99.89 F1-Skoru elde edilmiştir. Bu çalışma, diyabetik retinopati tanısında makine öğrenimi yöntemlerinin kullanılmasının etkili bir yaklaşım olduğunu göstermektedir. Deney sonuçları, diyabetik retinopati hastalarının tanı ve tedavi süreçlerine önemli katkılar sağladığını ortaya koymaktadır.

Makale detayları

Pretrained Models and the Role of Feature Selection: An Artificial Intelligence-Based Approach in the Diagnosis of Diabetic Retinopathy

Yazarlar:

Mehmet Kaan Kaya | Burak Tasci

Yayıncı:

Fırat University

Ana Başlıklar:

Deep Learning | Computing Applications in Health

Dergi:

Turkish Journal of Science and Technology Vol.18 Issue 2, pp.511-517

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001290410

pISSN:

1308-9080

VGG16

VGG19

Neighborhood Component Analysis

Relieff

Chi2VGG16

VGG19

Komşuluk bileşenleri analizi

Relieff

Chi2

Sayı

Makale detayları

Yazarlar: Mehmet Kaan Kaya | Burak Tasci

Yayıncı: Fırat University

Ana Başlıklar: Deep Learning | Computing Applications in Health

Dergi: Turkish Journal of Science and Technology Vol.18 Issue 2, pp.511-517

Belge Tipi: Makale

Yayın Tarihi: 1/2023

Belge Dili: İngilizce

Document ID (Org No.): 2001290410

pISSN: 1308-9080

Sayı

Yazarlar:

Mehmet Kaan Kaya | Burak Tasci

Yayıncı:

Fırat University

Ana Başlıklar:

Deep Learning | Computing Applications in Health

Dergi:

Turkish Journal of Science and Technology Vol.18 Issue 2, pp.511-517

Belge Tipi:

Makale

Yayın Tarihi:

1/2023

Belge Dili:

İngilizce

Document ID (Org No.):

2001290410

pISSN:

1308-9080