Diagnosis of the Skin Cancer by Vision Transformers

Uğur Demiroğlu

Article Details

Diagnosis of the Skin Cancer by Vision Transformers

Authors:

Uğur Demiroğlu

Publisher:

Duzce University

Main Topics:

Derin Öğrenme | Yapay Görme

Journal:

Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 1, pp.588-598

Document Type:

Article

Publication Date:

1/2025

Document Language:

English

Document ID (Org No.):

2001339880

pISSN:

2148-2446

Keywords:

Abstract:

 Skin cancer, one of the most frequent cancers, requires early identification for efficient treatment and better survival. Early diagnosis relies on precise and quick skin lesion categorization into benign and malignant categories. This work uses Vision Transformers ViTs to classify skin cancer photos by modeling long-range relationships and capturing complicated visual patterns. ViTs, originally created for natural language processing, have showed great potential in picture classification tasks because to their self-attention processes, outperforming CNNs. A public collection of 270 skin lesion images240 malignant and 30 benignwas used in this study. Preprocessing included scaling and normalizing the dataset to 384x384x3 and splitting it into 80 training and 20 testing sets. Transfer learning optimised a pre-trained ViT model for this job. To improve accuracy and avoid overfitting, hyperparameters were carefully selected for network training. Parallel computing accelerated training to 30 minutes and 20 seconds. Vision Transformers classify medical images well, according to the study. The ViT model outperformed numerous other methods with 98.15 accuracy on the test set. A confusion matrix analysis showed great sensitivity in detecting malignant lesions and low misclassification of benign patients. These findings show that ViTs can capture detailed medical picture aspects, making them useful for dermatological diagnoses. This study shows that Vision Transformers can improve diagnosis accuracy and lays the groundwork for their use in other medical imaging fields. In the battle against skin cancer and other illnesses that need early diagnosis, ViTs scalability, efficiency, and precision are important. Future research might integrate ViTs with other deep learning architectures to improve robustness and flexibility. This study adds to the data supporting sophisticated AI in medical diagnostics and lays the groundwork for automated, reliable, and efficient healthcare solutions.

 Skin cancer, one of the most frequent cancers, requires early identification for efficient treatment and better survival. Early diagnosis relies on precise and quick skin lesion categorization into benign and malignant categories. This work uses Vision Transformers ViTs to classify skin cancer photos by modeling long-range relationships and capturing complicated visual patterns. ViTs, originally created for natural language processing, have showed great potential in picture classification tasks because to their self-attention processes, outperforming CNNs. A public collection of 270 skin lesion images240 malignant and 30 benignwas used in this study. Preprocessing included scaling and normalizing the dataset to 384x384x3 and splitting it into 80 training and 20 testing sets. Transfer learning optimised a pre-trained ViT model for this job. To improve accuracy and avoid overfitting, hyperparameters were carefully selected for network training. Parallel computing accelerated training to 30 minutes and 20 seconds. Vision Transformers classify medical images well, according to the study. The ViT model outperformed numerous other methods with 98.15 accuracy on the test set. A confusion matrix analysis showed great sensitivity in detecting malignant lesions and low misclassification of benign patients. These findings show that ViTs can capture detailed medical picture aspects, making them useful for dermatological diagnoses. This study shows that Vision Transformers can improve diagnosis accuracy and lays the groundwork for their use in other medical imaging fields. In the battle against skin cancer and other illnesses that need early diagnosis, ViTs scalability, efficiency, and precision are important. Future research might integrate ViTs with other deep learning architectures to improve robustness and flexibility. This study adds to the data supporting sophisticated AI in medical diagnostics and lays the groundwork for automated, reliable, and efficient healthcare solutions.

 Skin cancer, one of the most frequent cancers, requires early identification for efficient treatment and better survival. Early diagnosis relies on precise and quick skin lesion categorization into benign and malignant categories. This work uses Vision Transformers ViTs to classify skin cancer photos by modeling long-range relationships and capturing complicated visual patterns. ViTs, originally created for natural language processing, have showed great potential in picture classification tasks because to their self-attention processes, outperforming CNNs. A public collection of 270 skin lesion images240 malignant and 30 benignwas used in this study. Preprocessing included scaling and normalizing the dataset to 384x384x3 and splitting it into 80 training and 20 testing sets. Transfer learning optimised a pre-trained ViT model for this job. To improve accuracy and avoid overfitting, hyperparameters were carefully selected for network training. Parallel computing accelerated training to 30 minutes and 20 seconds. Vision Transformers classify medical images well, according to the study. The ViT model outperformed numerous other methods with 98.15 accuracy on the test set. A confusion matrix analysis showed great sensitivity in detecting malignant lesions and low misclassification of benign patients. These findings show that ViTs can capture detailed medical picture aspects, making them useful for dermatological diagnoses. This study shows that Vision Transformers can improve diagnosis accuracy and lays the groundwork for their use in other medical imaging fields. In the battle against skin cancer and other illnesses that need early diagnosis, ViTs scalability, efficiency, and precision are important. Future research might integrate ViTs with other deep learning architectures to improve robustness and flexibility. This study adds to the data supporting sophisticated AI in medical diagnostics and lays the groundwork for automated, reliable, and efficient healthcare solutions.

 En sık görülen kanserlerden biri olan cilt kanseri, etkili tedavi ve daha iyi sağ kalım için erken teşhis gerektirir. Erken teşhis, cilt lezyonlarının iyi huylu ve kötü huylu kategorilere hassas ve hızlı bir şekilde sınıflandırılmasına dayanır. Bu çalışma, uzun menzilli ilişkileri modelleyerek ve karmaşık görsel desenleri yakalayarak cilt kanseri fotoğraflarını sınıflandırmak için Görüntü Dönüştürücülerini ViTler kullanır. Başlangıçta doğal dil işleme için oluşturulan ViTler, kendi kendine dikkat süreçleri sayesinde CNNleri geride bırakarak resim sınıflandırma görevlerinde büyük potansiyel göstermiştir. Bu çalışmada 240 kötü huylu ve 30 iyi huylu olmak üzere 270 cilt lezyonu görüntüsünün genel koleksiyonu kullanılmıştır. Ön işleme, veri kümesinin 384x384x3e ölçeklenmesini ve normalleştirilmesini ve 80 eğitim ve 20 test kümelerine bölünmesini içeriyordu. Transfer öğrenme, bu iş için önceden eğitilmiş bir ViT modelini optimize etti. Doğruluğu artırmak ve aşırı uyumu önlemek için, ağ eğitimi için hiperparametreler dikkatlice seçildi. Paralel hesaplama, eğitimi 30 dakika 20 saniyeye hızlandırdı. Çalışmaya göre, Görüntü Dönüştürücüler tıbbi görüntüleri iyi sınıflandırıyor. ViT modeli, test setinde 98,15 doğrulukla diğer birçok yöntemi geride bıraktı. Bir karışıklık matrisi analizi, kötü huylu lezyonları tespit etmede büyük hassasiyet ve iyi huylu hastaların düşük yanlış sınıflandırılması gösterdi. Bu bulgular, ViTlerin ayrıntılı tıbbi resim yönlerini yakalayabildiğini ve bu sayede dermatolojik teşhisler için yararlı hale geldiğini gösteriyor. Bu çalışma, Görüntü Dönüştürücülerin teşhis doğruluğunu artırabileceğini ve diğer tıbbi görüntüleme alanlarında kullanımları için temel oluşturduğunu gösteriyor. Cilt kanseri ve erken teşhis gerektiren diğer hastalıklarla mücadelede, ViTlerin ölçeklenebilirliği, verimliliği ve hassasiyeti önemlidir. Gelecekteki araştırmalar, sağlamlığı ve esnekliği artırmak için ViTleri diğer derin öğrenme mimarileriyle entegre edebilir. Bu çalışma, tıbbi teşhislerde sofistike yapay zekayı destekleyen verilere katkıda bulunuyor ve otomatik, güvenilir ve verimli sağlık çözümleri için temel oluşturuyor.

Article Details

Diagnosis of the Skin Cancer by Vision Transformers

Authors:

Uğur Demiroğlu

Publisher:

Duzce University

Main Topics:

Derin Öğrenme | Yapay Görme

Journal:

Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 1, pp.588-598

Document Type:

Article

Publication Date:

1/2025

Document Language:

English

Document ID (Org No.):

2001339880

pISSN:

2148-2446

Skin cancer

Categorized images

Malignant and benign classes

Classification

Vision transformersCilt kanseri

Kategorize edilmiş görüntüler

Kötü huylu ve iyi huylu sınıflar

Sınıflandırma

Vision transformers

Issues

Article Details

Authors: Uğur Demiroğlu

Publisher: Duzce University

Main Topics: Derin Öğrenme | Yapay Görme

Journal: Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 1, pp.588-598

Document Type: Article

Publication Date: 1/2025

Document Language: English

Document ID (Org No.): 2001339880

pISSN: 2148-2446

Issues

Authors:

Uğur Demiroğlu

Publisher:

Duzce University

Main Topics:

Derin Öğrenme | Yapay Görme

Journal:

Düzce Üniversitesi Bilim ve Teknoloji Dergisi Vol.13 Issue 1, pp.588-598

Document Type:

Article

Publication Date:

1/2025

Document Language:

English

Document ID (Org No.):

2001339880

pISSN:

2148-2446