The Design of Machine Learning-Based Computer-Aided System with LabVIEW For Abnormalities in Mammogram Images

Hasan Güler

Makale detayları

The Design of Machine Learning-Based Computer-Aided System with LabVIEW For Abnormalities in Mammogram Images

Yazarlar:

Hasan Güler

Yayıncı:

Fırat University

Ana Başlıklar:

Biomedical Imaging

Dergi:

Turkish Journal of Science and Technology Vol.19 Issue 2, pp.457-473

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328534

pISSN:

1308-9080

Anahtar kelimeler:

Özet:

 Mammogram is the best way of breast cancer detection nowadays, as breast cancer is the most common form of cancer in the female gender and this form of cancer usually causes death. Many scientists, doctors, and engineers are working together to deal with such serious issues in human life. This paper, it is aimed to develop a new computer-aided system with a graphical coded language to detect abnormalities in mammogram images by using machine learning technics such as ANN and SVM. The developed algorithm has a graphical user interface GUI and all results are shown in there. The algorithm was created using three different stages. These are image processing and mass segmentation, feature selection and extraction, and classification. To test the accuracy of the system as the sensitivity, specificity, and accuracy, mammogram images with forty benign and forty malignant masses were used. The obtained results for measuring the sensitivity, specificity, and accuracy are 95, 97.5, and 96.25 for ANN and 97.5, 97.5, and 97.5 for SVM, respectively. As can be said that the algorithm, user-friendly due to its user interface, can be preferred because it can detect many cancerous cells such as breast cancer with high accuracy.

 Mammogram is the best way of breast cancer detection nowadays, as breast cancer is the most common form of cancer in the female gender and this form of cancer usually causes death. Many scientists, doctors, and engineers are working together to deal with such serious issues in human life. This paper, it is aimed to develop a new computer-aided system with a graphical coded language to detect abnormalities in mammogram images by using machine learning technics such as ANN and SVM. The developed algorithm has a graphical user interface GUI and all results are shown in there. The algorithm was created using three different stages. These are image processing and mass segmentation, feature selection and extraction, and classification. To test the accuracy of the system as the sensitivity, specificity, and accuracy, mammogram images with forty benign and forty malignant masses were used. The obtained results for measuring the sensitivity, specificity, and accuracy are 95, 97.5, and 96.25 for ANN and 97.5, 97.5, and 97.5 for SVM, respectively. As can be said that the algorithm, user-friendly due to its user interface, can be preferred because it can detect many cancerous cells such as breast cancer with high accuracy.

 Mammogram is the best way of breast cancer detection nowadays, as breast cancer is the most common form of cancer in the female gender and this form of cancer usually causes death. Many scientists, doctors, and engineers are working together to deal with such serious issues in human life. This paper, it is aimed to develop a new computer-aided system with a graphical coded language to detect abnormalities in mammogram images by using machine learning technics such as ANN and SVM. The developed algorithm has a graphical user interface GUI and all results are shown in there. The algorithm was created using three different stages. These are image processing and mass segmentation, feature selection and extraction, and classification. To test the accuracy of the system as the sensitivity, specificity, and accuracy, mammogram images with forty benign and forty malignant masses were used. The obtained results for measuring the sensitivity, specificity, and accuracy are 95, 97.5, and 96.25 for ANN and 97.5, 97.5, and 97.5 for SVM, respectively. As can be said that the algorithm, user-friendly due to its user interface, can be preferred because it can detect many cancerous cells such as breast cancer with high accuracy.

 Meme kanseri kadınlarda en sık görülen kanser türü olduğundan ve bu kanser türü genellikle ölüme neden olduğundan, günümüzde meme kanserini tespit etmenin en iyi yolu mamografidir. Birçok bilim insanı, doktor ve mühendis insan hayatındaki bu tür ciddi sorunlarla başa çıkmak için birlikte çalışmaktadır. Bu makalede, YSA ve DVM gibi makine öğrenmesi teknikleri kullanılarak mamogram görüntülerindeki anormallikleri tespit etmek için grafik kodlu bir dile sahip yeni bir bilgisayar destekli sistem geliştirilmesi amaçlanmıştır. Geliştirilen algoritma grafiksel bir kullanıcı arayüzüne GUI sahiptir ve tüm sonuçlar burada gösterilmektedir. Algoritma üç farklı aşama kullanılarak oluşturulmuştur. Bunlar görüntü işleme ve kütle segmentasyonu, özellik seçimi ve çıkarımı ve sınıflandırmadır. Sistemin doğruluğunu duyarlılık, özgüllük ve doğruluk olarak test etmek için kırk iyi huylu ve kırk kötü huylu kitle içeren mamogram görüntüleri kullanılmıştır. Duyarlılık, özgüllük ve doğruluk ölçümleri için elde edilen sonuçlar sırasıyla YSA için 95, 97,5 ve 96,25; DVM için 97,5, 97,5 ve 97,5tir. Kullanıcı arayüzü sayesinde kullanıcı dostu olan algoritmanın, meme kanseri gibi birçok kanserli hücreyi yüksek doğrulukla tespit edebilmesi nedeniyle tercih edilebileceği söylenebilir.

Makale detayları

The Design of Machine Learning-Based Computer-Aided System with LabVIEW For Abnormalities in Mammogram Images

Yazarlar:

Hasan Güler

Yayıncı:

Fırat University

Ana Başlıklar:

Biomedical Imaging

Dergi:

Turkish Journal of Science and Technology Vol.19 Issue 2, pp.457-473

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328534

pISSN:

1308-9080

Mammography

breast cancer detection

machine learning

graphical user interfaceMamografi

meme kanseri tespiti

makine öğrenmesi

grafiksel kullanıcı arayüzü.

Sayı

Makale detayları

Yazarlar: Hasan Güler

Yayıncı: Fırat University

Ana Başlıklar: Biomedical Imaging

Dergi: Turkish Journal of Science and Technology Vol.19 Issue 2, pp.457-473

Belge Tipi: Makale

Yayın Tarihi: 9/2024

Belge Dili: İngilizce

Document ID (Org No.): 2001328534

pISSN: 1308-9080

Sayı

Yazarlar:

Hasan Güler

Yayıncı:

Fırat University

Ana Başlıklar:

Biomedical Imaging

Dergi:

Turkish Journal of Science and Technology Vol.19 Issue 2, pp.457-473

Belge Tipi:

Makale

Yayın Tarihi:

9/2024

Belge Dili:

İngilizce

Document ID (Org No.):

2001328534

pISSN:

1308-9080