MULTIPLE CLASSIFICATION OF BRAIN TUMORS FOR EARLY DETECTION USING A NOVEL CONVOLUTIONAL NEURAL NETWORK MODEL

Muhammed Çelik; Özkan İnik

Article Details

MULTIPLE CLASSIFICATION OF BRAIN TUMORS FOR EARLY DETECTION USING A NOVEL CONVOLUTIONAL NEURAL NETWORK MODEL

Authors:

Muhammed Çelik | Özkan İnik

Publisher:

Eskişehir Osmangazi University

Main Topics:

Bilgisayar Yazılımı

Journal:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.31 Issue 1, pp.491-500

Document Type:

Article

Publication Date:

4/2023

Document Language:

English

Document ID (Org No.):

2001288553

pISSN:

2630-5712

Keywords:

Abstract:

 Brain tumors can have very dangerous and fatal effects if not diagnosed early. These are diagnosed by specialized doctors using biopsy samples taken from the brain. This process is exhausting and wastes doctors time too much. Researchers have been working to develop a quick and accurate way for identifying and classifying brain tumors in order to overcome these drawbacks. Computer-assisted technologies are utilized to support doctors and specialists in making more efficient and accurate decisions. Deep learning-based methods are one of these technologies and have been used extensively in recent years. However, there is still a need to explore architectures with higher accuracy performance. For this purpose, in this paper proposed a novel convolutional neural network CNN which has twenty-four layers to multi-classify brain tumors from brain MRI images for early diagnosis. In order to demonstrate the effectiveness of the proposed model, various comparisons and tests were carried out. Three different state-of-the-art CNN models were used in the comparison: AlexNet, ShuffleNet and SqueezeNet. At the end of the training, proposed model is achieved highest accuracy of 92.82 and lowest loss of 0.2481. In addition, ShuflleNet determines the second highest accuracy at 90.17. AlexNet has the lowest accuracy at 80.5 with 0.4679 of loss. These results demonstrate that the proposed CNN model provides greater precision and accuracy than the state-of-art CNN models.

 Brain tumors can have very dangerous and fatal effects if not diagnosed early. These are diagnosed by specialized doctors using biopsy samples taken from the brain. This process is exhausting and wastes doctors time too much. Researchers have been working to develop a quick and accurate way for identifying and classifying brain tumors in order to overcome these drawbacks. Computer-assisted technologies are utilized to support doctors and specialists in making more efficient and accurate decisions. Deep learning-based methods are one of these technologies and have been used extensively in recent years. However, there is still a need to explore architectures with higher accuracy performance. For this purpose, in this paper proposed a novel convolutional neural network CNN which has twenty-four layers to multi-classify brain tumors from brain MRI images for early diagnosis. In order to demonstrate the effectiveness of the proposed model, various comparisons and tests were carried out. Three different state-of-the-art CNN models were used in the comparison: AlexNet, ShuffleNet and SqueezeNet. At the end of the training, proposed model is achieved highest accuracy of 92.82 and lowest loss of 0.2481. In addition, ShuflleNet determines the second highest accuracy at 90.17. AlexNet has the lowest accuracy at 80.5 with 0.4679 of loss. These results demonstrate that the proposed CNN model provides greater precision and accuracy than the state-of-art CNN models.

 Brain tumors can have very dangerous and fatal effects if not diagnosed early. These are diagnosed by specialized doctors using biopsy samples taken from the brain. This process is exhausting and wastes doctors time too much. Researchers have been working to develop a quick and accurate way for identifying and classifying brain tumors in order to overcome these drawbacks. Computer-assisted technologies are utilized to support doctors and specialists in making more efficient and accurate decisions. Deep learning-based methods are one of these technologies and have been used extensively in recent years. However, there is still a need to explore architectures with higher accuracy performance. For this purpose, in this paper proposed a novel convolutional neural network CNN which has twenty-four layers to multi-classify brain tumors from brain MRI images for early diagnosis. In order to demonstrate the effectiveness of the proposed model, various comparisons and tests were carried out. Three different state-of-the-art CNN models were used in the comparison: AlexNet, ShuffleNet and SqueezeNet. At the end of the training, proposed model is achieved highest accuracy of 92.82 and lowest loss of 0.2481. In addition, ShuflleNet determines the second highest accuracy at 90.17. AlexNet has the lowest accuracy at 80.5 with 0.4679 of loss. These results demonstrate that the proposed CNN model provides greater precision and accuracy than the state-of-art CNN models.

 Beyin tümörleri erken teşhis edilmezse çok tehlikeli ve ölümcül etkilere sahip olabilir. Beyin tümörleri, uzman doktorlar tarafından beyinden alınan biyopsi örnekleri kullanılarak teşhis edilir. Bu süreç yorucudur ve doktorların çok fazla zamanını harcar. Araştırmacılar, bu dezavantajların üstesinden gelmek amacıyla beyin tümörlerini tanımlamak ve sınıflandırmak için hızlı ve doğru bir yol geliştirmeye çalışmaktadırlar. Doktorların ve uzmanların daha verimli ve doğru kararlar vermelerini desteklemek için bilgisayar destekli teknolojiler kullanılmaktadır. Derin öğrenme tabanlı yöntemler de bu teknolojilerden biridir ve son yıllarda yoğun olarak kullanılmaya başlanmıştır. Bununla birlikte, daha yüksek doğruluk performansına sahip mimarileri keşfetmeye hala ihtiyaç vardır. Bu amaçla, bu çalışmada erken teşhis için beyin MR görüntülerinden beyin tümörlerini çoklu sınıflandırmak için yirmi dört katmana sahip yeni bir evrişimli sinir ağı ESA önerilmiştir. Önerilen modelin etkinliğini göstermek için çeşitli karşılaştırmalar ve testler yapılmıştır. Karşılaştırmada üç farklı son teknoloji CNN modeli kullanılmıştır: AlexNet, ShuffleNet ve SqueezeNet. Eğitim sonunda önerilen model 92,82 ile en yüksek doğruluk ve 0,2481 ile en düşük kayıp elde edilmiştir. Ek olarak, ShuflleNet 90,17 ile ikinci en yüksek doğruluk değerine ulaşmıştır. AlexNet, 0,4679 kayıpla 80,5 ile en düşük doğruluğa sahiptir. Bu Sonuçlar, önerilen CNN modelinin, son teknoloji CNN modellerinden daha fazla kesinlik ve doğruluk sağladığını göstermektedir.

Article Details

MULTIPLE CLASSIFICATION OF BRAIN TUMORS FOR EARLY DETECTION USING A NOVEL CONVOLUTIONAL NEURAL NETWORK MODEL

Authors:

Muhammed Çelik | Özkan İnik

Publisher:

Eskişehir Osmangazi University

Main Topics:

Bilgisayar Yazılımı

Journal:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.31 Issue 1, pp.491-500

Document Type:

Article

Publication Date:

4/2023

Document Language:

English

Document ID (Org No.):

2001288553

pISSN:

2630-5712

Deep learning

CNN models

pre-trained models

brain MRI images

classificationDerin öğrenme

ESA modelleri

önceden eğitilmiş modeller

Beyin MR görüntüleri

sınıflandırma

Issues

Article Details

Authors: Muhammed Çelik | Özkan İnik

Publisher: Eskişehir Osmangazi University

Main Topics: Bilgisayar Yazılımı

Journal: Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.31 Issue 1, pp.491-500

Document Type: Article

Publication Date: 4/2023

Document Language: English

Document ID (Org No.): 2001288553

pISSN: 2630-5712

Issues

Authors:

Muhammed Çelik | Özkan İnik

Publisher:

Eskişehir Osmangazi University

Main Topics:

Bilgisayar Yazılımı

Journal:

Eskişehir Osmangazi Üniversitesi Mühendislik ve Mimarlık Fakültesi Dergisi Vol.31 Issue 1, pp.491-500

Document Type:

Article

Publication Date:

4/2023

Document Language:

English

Document ID (Org No.):

2001288553

pISSN:

2630-5712