Deep Learning-based Classification of Breast Tumors using Raw Microwave Imaging Data

Mustafa Berkan Biçer; Uğur Eliiyi; Deniz Türsel Eliiyi

Makale detayları

Deep Learning-based Classification of Breast Tumors using Raw Microwave Imaging Data

Yazarlar:

Mustafa Berkan Biçer | Uğur Eliiyi | Deniz Türsel Eliiyi

Yayıncı:

Gazi University

Ana Başlıklar:

Mühendislik

Dergi:

Politeknik Dergisi Vol.27 Issue 4, pp.1327-1334

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001327671

pISSN:

2147-9429

Anahtar kelimeler:

Özet:

 Breast cancer is the leading type of malignant neoplasm disease among women worldwide. Breast screening makes extensive use of powerful techniques such as x-ray mammography, magnetic resonance imaging, and ultrasonography. While these technologies have numerous benefits, certain drawbacks such as the use of low-energy ionizing x-rays, a lack of specificity for malignant tissues, and cost, have motivated researchers to investigate novel imaging and detection modalities. Microwave imaging MWI has been extensively studied due to its low-cost structure and ability to perform measurements using non-ionizing electromagnetic waves. This study proposes a novel convolutional neural network CNN model for detecting and classifying tumor scatterers in MWI simulation data. To accomplish this, 10001 different numerical breast models with tumor scatterers of varying numbers and positions were developed, and the simulation results were derived using the synthetic aperture radar SAR technique. The presented CNN structure was trained using 8000 pieces of simulation data, and the remaining data were used for testing, achieving accuracy rates of 99.61 and 99.75, respectively. The proposed model is compared to three state-of-the-art models on the same dataset in terms of classification performance. The results demonstrate that the proposed model effectively performs effectively well in detecting and classifying tumor scatterers.

 Breast cancer is the leading type of malignant neoplasm disease among women worldwide. Breast screening makes extensive use of powerful techniques such as x-ray mammography, magnetic resonance imaging, and ultrasonography. While these technologies have numerous benefits, certain drawbacks such as the use of low-energy ionizing x-rays, a lack of specificity for malignant tissues, and cost, have motivated researchers to investigate novel imaging and detection modalities. Microwave imaging MWI has been extensively studied due to its low-cost structure and ability to perform measurements using non-ionizing electromagnetic waves. This study proposes a novel convolutional neural network CNN model for detecting and classifying tumor scatterers in MWI simulation data. To accomplish this, 10001 different numerical breast models with tumor scatterers of varying numbers and positions were developed, and the simulation results were derived using the synthetic aperture radar SAR technique. The presented CNN structure was trained using 8000 pieces of simulation data, and the remaining data were used for testing, achieving accuracy rates of 99.61 and 99.75, respectively. The proposed model is compared to three state-of-the-art models on the same dataset in terms of classification performance. The results demonstrate that the proposed model effectively performs effectively well in detecting and classifying tumor scatterers.

 Breast cancer is the leading type of malignant neoplasm disease among women worldwide. Breast screening makes extensive use of powerful techniques such as x-ray mammography, magnetic resonance imaging, and ultrasonography. While these technologies have numerous benefits, certain drawbacks such as the use of low-energy ionizing x-rays, a lack of specificity for malignant tissues, and cost, have motivated researchers to investigate novel imaging and detection modalities. Microwave imaging MWI has been extensively studied due to its low-cost structure and ability to perform measurements using non-ionizing electromagnetic waves. This study proposes a novel convolutional neural network CNN model for detecting and classifying tumor scatterers in MWI simulation data. To accomplish this, 10001 different numerical breast models with tumor scatterers of varying numbers and positions were developed, and the simulation results were derived using the synthetic aperture radar SAR technique. The presented CNN structure was trained using 8000 pieces of simulation data, and the remaining data were used for testing, achieving accuracy rates of 99.61 and 99.75, respectively. The proposed model is compared to three state-of-the-art models on the same dataset in terms of classification performance. The results demonstrate that the proposed model effectively performs effectively well in detecting and classifying tumor scatterers.

 Meme kanseri, dünya genelinde kadınlar arasında en yaygın türdeki kötü huylu tümör hastalığıdır. Meme taraması, x-ışını mamografisi, manyetik rezonans görüntüleme ve ultrasonografi gibi güçlü teknikleri yoğun bir şekilde kullanır. Bu teknolojilerin birçok faydası olsa da, düşük enerjili iyonlaştırıcı x-ışınlarının kullanımı, kötü huylu dokular için yetersizlik ve maliyet gibi bazı dezavantajlar, araştırmacıları yeni görüntüleme ve tespit yöntemlerini araştırmaya teşvik etmiştir. Mikrodalga görüntüleme MDG, düşük maliyetli yapısı ve iyonlaştırıcı olmayan elektromanyetik dalgalar kullanarak ölçümler yapabilme yeteneği nedeniyle yoğun bir şekilde araştırılmaktadır. Bu çalışma, MDG simülasyon verilerinde tümör saçaklarını tespit etmek ve sınıflandırmak için yeni bir ESA modeli önermektedir. Bunun için farklı sayı ve pozisyonlar tümör saçıcılarına sahip 10001 farklı sayısal meme modeli geliştirilmiştir ve sentetik açıklıklı radar SAR tekniği kullanılarak simülasyon sonuçları elde edilmiştir. Sunulan ESA yapısı, 8000 adet simülasyon verisi kullanılarak eğitilmiş ve kalan veriler test için kullanılarak sırasıyla 99.61 ve 99.75 doğruluk oranlarına ulaşılmıştır. Önerilen model, sınıflandırma performansı açısından aynı veri kümesi üzerinde üç farklı güncel modelle karşılaştırılmıştır. Sonuçlar, önerilen modelin tümör saçıcılarını tespit edip sınıflandırmada etkili bir şekilde çalıştığını göstermektedir.

Makale detayları

Deep Learning-based Classification of Breast Tumors using Raw Microwave Imaging Data

Yazarlar:

Mustafa Berkan Biçer | Uğur Eliiyi | Deniz Türsel Eliiyi

Yayıncı:

Gazi University

Ana Başlıklar:

Mühendislik

Dergi:

Politeknik Dergisi Vol.27 Issue 4, pp.1327-1334

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001327671

pISSN:

2147-9429

breast cancer

classification

convolutional neural networks

deep learning

microwave imagingmeme kanseri

sınıflandırma

evrişimsel sinir ağları

derin öğrenme

mikrodalga görüntüleme

Sayı

Makale detayları

Yazarlar: Mustafa Berkan Biçer | Uğur Eliiyi | Deniz Türsel Eliiyi

Yayıncı: Gazi University

Ana Başlıklar: Mühendislik

Dergi: Politeknik Dergisi Vol.27 Issue 4, pp.1327-1334

Belge Tipi: Makale

Yayın Tarihi: 9/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001327671

pISSN: 2147-9429

Sayı

Yazarlar:

Mustafa Berkan Biçer | Uğur Eliiyi | Deniz Türsel Eliiyi

Yayıncı:

Gazi University

Ana Başlıklar:

Mühendislik

Dergi:

Politeknik Dergisi Vol.27 Issue 4, pp.1327-1334

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001327671

pISSN:

2147-9429