A Comparative Analysis of Convolutional Neural Network Architectures for Binary Image Classification: A Case Study in Skin Cancer Detection

Şerife Gül Korkut; Hatice Kocabaş; Rifat Kurban

Article Details

A Comparative Analysis of Convolutional Neural Network Architectures for Binary Image Classification: A Case Study in Skin Cancer Detection

Authors:

Şerife Gül Korkut | Hatice Kocabaş | Rifat Kurban

Publisher:

Giresun University

Main Topics:

Bilgisayar Yazılımı

Journal:

Karadeniz Fen Bilimleri Dergisi Vol.14 Issue 4, pp.2008-2022

Document Type:

Article

Publication Date:

12/2024

Document Language:

English

Document ID (Org No.):

2001333411

pISSN:

2564-7377

Keywords:

Abstract:

 In this study, a comprehensive comparative analysis of Convolutional Neural Network CNN architectures for binary image classification is presented with a particular focus on the benefits of transfer learning. The performance and accuracy of prominent CNN models, including MobileNetV3, VGG19, ResNet50, and EfficientNetB0, in classifying skin cancer from binary images are evaluated. Using a pre-trained approach, the impact of transfer learning on the effectiveness of these architectures and identify their strengths and weaknesses within the context of binary image classification are investigated. This paper aims to provide valuable insights for selecting the optimal CNN architecture and leveraging transfer learning to achieve superior performance in binary image classification applications, particularly those related to medical image analysis.

 In this study, a comprehensive comparative analysis of Convolutional Neural Network CNN architectures for binary image classification is presented with a particular focus on the benefits of transfer learning. The performance and accuracy of prominent CNN models, including MobileNetV3, VGG19, ResNet50, and EfficientNetB0, in classifying skin cancer from binary images are evaluated. Using a pre-trained approach, the impact of transfer learning on the effectiveness of these architectures and identify their strengths and weaknesses within the context of binary image classification are investigated. This paper aims to provide valuable insights for selecting the optimal CNN architecture and leveraging transfer learning to achieve superior performance in binary image classification applications, particularly those related to medical image analysis.

 In this study, a comprehensive comparative analysis of Convolutional Neural Network CNN architectures for binary image classification is presented with a particular focus on the benefits of transfer learning. The performance and accuracy of prominent CNN models, including MobileNetV3, VGG19, ResNet50, and EfficientNetB0, in classifying skin cancer from binary images are evaluated. Using a pre-trained approach, the impact of transfer learning on the effectiveness of these architectures and identify their strengths and weaknesses within the context of binary image classification are investigated. This paper aims to provide valuable insights for selecting the optimal CNN architecture and leveraging transfer learning to achieve superior performance in binary image classification applications, particularly those related to medical image analysis.

 Bu çalışmada, ikili görüntü sınıflandırması için Evrişimsel Sinir Ağı CNN mimarilerinin kapsamlı bir karşılaştırmalı analizi sunulmuş ve transfer öğreniminin faydalarına vurgu yapılmıştır. MobileNetV3, VGG19, ResNet50 ve EfficientNetB0 gibi önde gelen CNN modellerinin ikili görüntülerden cilt kanseri sınıflandırmadaki performans ve doğruluğu değerlendirilmiştir. Önceden eğitilmiş bir yaklaşım kullanılarak, transfer öğreniminin bu mimarilerin etkinliği üzerindeki etkisi araştırılmış ve ikili görüntü sınıflandırması bağlamında güçlü ve zayıf yönleri belirlenmiştir. Bu makale, optimal CNN mimarisinin seçimi ve transfer öğreniminden yararlanarak ikili görüntü sınıflandırma uygulamalarında, özellikle tıbbi görüntü analiziyle ilgili olanlarda, üstün performans elde etme konusunda değerli içgörüler sağlamayı amaçlamaktadır.

Article Details

A Comparative Analysis of Convolutional Neural Network Architectures for Binary Image Classification: A Case Study in Skin Cancer Detection

Authors:

Şerife Gül Korkut | Hatice Kocabaş | Rifat Kurban

Publisher:

Giresun University

Main Topics:

Bilgisayar Yazılımı

Journal:

Karadeniz Fen Bilimleri Dergisi Vol.14 Issue 4, pp.2008-2022

Document Type:

Article

Publication Date:

12/2024

Document Language:

English

Document ID (Org No.):

2001333411

pISSN:

2564-7377

Convolutional Neural Networks (CNNs)

Transfer Learning

Binary Image Classification

CNN Architecture Comparison

Skin Cancer DetectionEvrişimsel Sinir Ağları (CNN

Transfer Öğrenimi

İkili Görüntü Sınıflandırma

CNN Mimari Karşılaştırması

Cilt Kanseri Tespiti

Issues

Article Details

Authors: Şerife Gül Korkut | Hatice Kocabaş | Rifat Kurban

Publisher: Giresun University

Main Topics: Bilgisayar Yazılımı

Journal: Karadeniz Fen Bilimleri Dergisi Vol.14 Issue 4, pp.2008-2022

Document Type: Article

Publication Date: 12/2024

Document Language: English

Document ID (Org No.): 2001333411

pISSN: 2564-7377

Issues

Authors:

Şerife Gül Korkut | Hatice Kocabaş | Rifat Kurban

Publisher:

Giresun University

Main Topics:

Bilgisayar Yazılımı

Journal:

Karadeniz Fen Bilimleri Dergisi Vol.14 Issue 4, pp.2008-2022

Document Type:

Article

Publication Date:

12/2024

Document Language:

English

Document ID (Org No.):

2001333411

pISSN:

2564-7377