Araştırma Makalesi
BibTex RIS Kaynak Göster

DERİN ÖĞRENME MİMARİLERİ KULLANILARAK MRI GÖRÜNTÜLERİ ÜZERİNDE BEYİN TÜMÖRÜ SINIFLANDIRMASI

Yıl 2023, Cilt: 26 Sayı: Özel Sayı - 9th Uluslararası IFS Çağdaş Matematik ve Mühendislik Konferansı (IFSCOM-E) Özel Sayısı, 1177 - 1186, 12.12.2023

Samaneh Sarfarazı , Önsen Toygar

https://doi.org/10.17780/ksujes.1339884

Öz

Beyin tümörü, beyindeki veya kafadaki hapishane hücresinin katı bir şekilde büyümesiyle üretilen tehlikeli bir nöral hastalıktır. Manyetik Rezonans Görüntüleme (MRI) görüntülerinden temiz olmayan tümör parçalarının segmentasyonu, analizi ve ayrılması kaygının ana kaynağıdır. Tümör içeren MRI görüntülerinin raporlanabilmesi için bilgisayar destekli yöntemlerin kullanılması gerekli hale gelmiştir. Bu makalede, MRI görüntülerinde beyin tümörlerini tanımlamak için Evrişimli Sinir Ağları (CNN) yaklaşımı kullanılmıştır. Bu çalışma için Kaggle Brain MRI veri kümesi ve Figshare Brain MRI veri kümesi olmak üzere iki veri kümesi kullanılmıştır. Derin öznitelikleri çıkarmak için VGG16, AlexNet ve ResNet'ten oluşan derin CNN modelleri kullanılmıştır. Söz konusu Derin Öğrenme (DL) modellerinin sınıflandırma doğrulukları, uygulanan sistemlerin verimliliklerini ölçmek için kullanılmıştır. Kaggle veri kümesi için AlexNet %98, VGG16 %97 ve ResNet %66 doğruluk elde etmiştir. Bu ağlar arasında AlexNet en yüksek düzeyde doğruluk sağlamıştır. Figshare veri kümesinde ise, AlexNet ve VGG16'nın her ikisi de %99, ResNet ise %96 doğruluk elde etmiştir. Doğruluk açısından AlexNet ve VGG16, ResNet'ten daha iyi performans göstermiştir. Bu performanslar, kanserlerin felç ve diğer komplikasyonlar gibi fiziksel zararlara yol açmadan önce erken teşhis edilmesine yardımcı olacaktır.

Anahtar Kelimeler

Beyin tümörü sınıflandırması Evrişimli Sinir Ağları derin öğrenme

Kaynakça

  • Amin, J., Sharif, M., Mussarat,Y., Fernandes, S.L. (2018). Big Data Analysis for Brain Tumor Detection: Deep Convolutiona Neural Networks. Future Gener. Comput. Syst., vol.87. 290–.297. https://doi.org/10.1016/j.future.2018.04.065.
  • Arshia, R., Saeeda, N., Muhammad, I.R., Faiza, A., Muhammad, I. (2020). A Deep Learning-based Framework for Automatic Brain Tumors Classification Using Transfer Learning, Circuits, Systems and Signal Processing. vol. 39, 757-775.https://doi.org/10.1007/s00034-019-01246-3.
  • Çınar, A. & Yıldırım, M. (2020). Detection of Tumors on Brain MRI Images Using the Hybrid Convolutional Neural Network Architecture, Med. Hypotheses, 139 (2020), 109684. https://doi.org/10.1016/j.mehy.2020.109684.
  • Deepak, R. & Ameer, P.M. (2019). Brain Tumor Classification Using Deep CNN Features via Transfer Learning, Computers in Biology and Medicine, 1-7. https://doi.org/10.1016/j.compbiomed.2019.103345.
  • Figshare Brain Tumor Dataset, https://doi.org/10.6084/m9.figshare.1512427.v5, Accessed: December 2018.
  • Gumaei, A., Hassan, M.M., Hassan, M.R., Alelaiwi, A. N., Fortino, G. A. (2019). Hybrid Feature Extraction Method with Regularized Extreme Learning Machinefor Brain Tumor Classification. 36266-36273.https://doi.org/ 10.1109/ACCESS.2019.2904145.
  • Hasan, A.M., Jalab, H.A., Meziane, F., Kahtan, H., Ahmad, A.S. (2019). Combining Deep and Handcrafted Image Features for MRI Brain Scan Classification. IEEE Access. 79959–79967. https://doi.org/10.1109/ACCESS.2019.2922691.
  • Hemanth, G., Janardhan, M., Sujihelen, L. (2019). Design and Implementing Brain Tumor Detection Using Machine Learning Approach . Third International Conference on Trends in Electronics and Informatics.1-6..https://doi.org/ 10.1109/ICOEI.2019.8862553.
  • Huafeng, W., Haixia, P., Huafeng,W., Yanxiang , Z., Yehe, C. (2015). Deep Learning for Image Retrieval: What Works and What Doesn't, Conference Paper .1-22.https://doi.org/10.1109/ICDMW.2015.121.
  • Kaggle Brain Tumor Classification (MRI) dataset, by Bhuvaji, S., Kadam, A., Bhumkar, P., Dedge, S., Kanchan, S., https://doi.org/10.34740/KAGGLE/DSV/1183165, Accessed: December 2020.
  • Kebir, S.T. & Mekaoui, S. (2018). An Efficient Methodology Of Brain Abnormalities Detection Using CNN Deep Learning Network. in Proc. Int. Conf.Appl. Smart Syst. (ICASS). https://doi.org/10.1109/ICASS.2018.8652054.2018.
  • Latif, G., Iskandar, D., Alghazo, N.F., Mohammad, J.M.N. (2018). Enhanced MR Image Classification Using Hybrid Statistical and Wavelets Features. IEEE Access .9634- 9644.https://doi.org/10.1109/ACCESS. 2018.2888488.
  • Manav, S., Pramanshu, S., Ritik, M., Kamakshi, G. (2021). Brain Tumour Detection Using Machine Learning . Journal of Electronics and Informatics, Volume 3, Issue 4. 298-308, 2021. https://doi.org/10.36548/jei.2021.4.005.
  • Minz, A. & Mahobiya, C. (2017). MR Image Classification Using Adaboost for Brain Tumor Type. IEEE 7th International Advance Computing Conference .1-5.https://doi.org/10.1109/IACC.2017.0146.
  • Mohsen, H., Sayed, E., Dahshan, E., Badeeh, A., Salem, M. (2018). Classification Using Deep learning Neural networks for Brain Tumors Future. Computing and Informatics Journal.68-73.https://doi.org/10.1109/ACCESS.2018.2888488.
  • Narayana, R.L. & Reddy, T.S. (2018). An Efficient Optimization Technique to Detect Brain Tumor from MRI Images. International Conference on Smart Systems and Inventive Technology.1-4.https://doi.org/10.1109/ICSSIT.2018.8748288.
  • Polat, Ö. & Güngen, C . (2021). Classification of Brain Tumors from MR Images Using Deep Transfer Learning. The Journal of Supercomputing ,volume 77. 7236–7252. https://doi.org/10.1007/s11227-020-03572-9.
  • Polly, E.P., Shil, S.K., Hossain, M.A., Ayman, A., Jang, Y.M. (2018). Detection and Classification of HGG and LGG BrainTumor Using Machine Learning. International conference on Information Networking. 813-817.https://doi.org/10.1109/ICOIN.2018.8343231.
  • Prabira, K.S. & Santi, K.B. (2021). A Data Constrained Approach for Brain Tumour Detection Using Fused Deep Features and SVM, Multimedia Tools and Applications, vol. 80, 28745-28760.https://doi.org/10.1007/s11042-021-11098-2.
  • Rehman, A., Khan, M.A., Saba, T.Z., Mehmood, T.U., Ayesha, N. (2021). Microscopic Brain Tumor Detection And Classification Using 3D CNN And Feature Selection Architecture. Microsc. Res. Techn, vol. 84, no. 1,133–149, 2021. https://doi.org/10.1002/jemt.23597.2021.
  • Rehman,A., Naz, S., Razzak,M.I., Akram ,F., Imran,M.Amin, J., Sharif, M., Yasmin, M., Fernandis, S.(2017). A Distinctive Approach in Brain Tumor Detection and Classification Using MRI. Pattern Recognition Letters.1- 10.https://doi.org/10.1016/j.patrec.2017.10.036.
  • Sethy, P.K. & Behera, S.K. (2021). A Data Constrained Approach for Brain Tumour Detection Using Fused Deep Features and SVM . Multimedia Tools and Applications (2021) 80.28745–28760.https://doi.org/10.1007/s11042-021-11098-2. Sert, E., Ozyurt, F., Doğantekin, A. (2019). A New Approach for Brain Tumor Diagnosis System: Single Image Superresolution Based Maximum Fuzzy Entropy Segmentation and Convolutional Neural Network. Medical Hypothesis.1-9.https://doi.org/10.1016/j.mehy.2019.109413.
  • Shankar, A.S., Asokan, A., Sivakumar, D. (2016). Brain Tumor Classification Using Gustafson–kessel (G-k) Fuzzy Clustering Algorithm. International Journal of Latest Engineering Research and Applications .68-72.
  • Simonyan, K. & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556.https://doi.org/10.1109/ACPR.2015.7486599.
  • Talo, M., Baloglu, U.B., Yıldırım, O., Acharya, U.R. (2019). Application Of Deep Transfer Learning For Automated Brain Abnormality Classification Using MRI Images.Cognitive Systems Research, 54(2019), 176–188.https://doi.org/10.1016/j.cogsys.2018.12.007.
  • Vinoth, R. & Venkatesh, C. (2018). Segmentation And Detection Of Tumor in MRI Images Using CNN And SVM Classification. in Proc. Conf. Emerg. Devices Smart Syst. (ICEDSS). 21–25. https://doi.org/10.1109/ICEDSS.2018.8544306.2018.
  • Wang, F.& Gong, M. (2020). Single Image Super-Resolution by Residual Recovery Based On an Independent Deep Convolutional Network.VOLUME 4.1–10.https://doi.org/10.1109/ACCESS.2020.2986365.
  • Wang, H., Pan, H., Zhang, Y., Cai,Y. (2015). Deep Learning for Image Retrieval: What Works and What Doesn't. Conference Paper ·1-22. https://doi.org/10.1109/ICDMW.2015.121. Zaw, H.T., Maneerat, N., Win, K.Y. (2019). Brain Tumor Detection Based On Naïve Bayes Classification. International Conference on Engineering, Applied Sciences and Technology.1-4. https://doi.org/10.1109/ICEAST.2019.8802562.

CLASSIFICATION OF BRAIN TUMORS ON MRI IMAGES USING DEEP LEARNING ARCHITECTURES

Yıl 2023, Cilt: 26 Sayı: Özel Sayı - 9th Uluslararası IFS Çağdaş Matematik ve Mühendislik Konferansı (IFSCOM-E) Özel Sayısı, 1177 - 1186, 12.12.2023

Samaneh Sarfarazı , Önsen Toygar

https://doi.org/10.17780/ksujes.1339884

Öz

A brain tumor is a dangerous neural illness produced by the strict growth of prison cells in the brain or head. The segmentation, analysis, and separation of unclean tumor parts from Magnetic Resonance Imaging (MRI) images are the main sources of anxiety. To report the segmented MRI images including tumor, the usage of computer-assisted methods is necessary. In this paper, a Convolutional Neural Network (CNN) approach is applied to identify brain cancers in MRI images. Two datasets are used in this study, namely Kaggle Brain MRI database and Figshare Brain MRI database. Models of deep CNN, consisting of VGG16, AlexNet, and ResNet, are utilized to extract deep features. The classification accuracies of the aforementioned Deep Learning (DL) networks are used to measure the efficiencies of the implemented systems. For the Kaggle database, AlexNet achieves 98% accuracy, VGG16 has 97% accuracy and ResNet has 66% accuracy. Among these networks, AlexNet has provided the highest level of accuracy. In the Figshare dataset, AlexNet and VGG16 both achieve 99% accuracy, and ResNet has 96% accuracy. In terms of accuracy, AlexNet and VGG16 outperform ResNet. These performances aid in the early detection of cancers before they cause physical harm such as paralysis and other complications.

Anahtar Kelimeler

Brain tumor classification Convolutional Neural Networks deep learning

Destekleyen Kurum

Not available.

Kaynakça

  • Amin, J., Sharif, M., Mussarat,Y., Fernandes, S.L. (2018). Big Data Analysis for Brain Tumor Detection: Deep Convolutiona Neural Networks. Future Gener. Comput. Syst., vol.87. 290–.297. https://doi.org/10.1016/j.future.2018.04.065.
  • Arshia, R., Saeeda, N., Muhammad, I.R., Faiza, A., Muhammad, I. (2020). A Deep Learning-based Framework for Automatic Brain Tumors Classification Using Transfer Learning, Circuits, Systems and Signal Processing. vol. 39, 757-775.https://doi.org/10.1007/s00034-019-01246-3.
  • Çınar, A. & Yıldırım, M. (2020). Detection of Tumors on Brain MRI Images Using the Hybrid Convolutional Neural Network Architecture, Med. Hypotheses, 139 (2020), 109684. https://doi.org/10.1016/j.mehy.2020.109684.
  • Deepak, R. & Ameer, P.M. (2019). Brain Tumor Classification Using Deep CNN Features via Transfer Learning, Computers in Biology and Medicine, 1-7. https://doi.org/10.1016/j.compbiomed.2019.103345.
  • Figshare Brain Tumor Dataset, https://doi.org/10.6084/m9.figshare.1512427.v5, Accessed: December 2018.
  • Gumaei, A., Hassan, M.M., Hassan, M.R., Alelaiwi, A. N., Fortino, G. A. (2019). Hybrid Feature Extraction Method with Regularized Extreme Learning Machinefor Brain Tumor Classification. 36266-36273.https://doi.org/ 10.1109/ACCESS.2019.2904145.
  • Hasan, A.M., Jalab, H.A., Meziane, F., Kahtan, H., Ahmad, A.S. (2019). Combining Deep and Handcrafted Image Features for MRI Brain Scan Classification. IEEE Access. 79959–79967. https://doi.org/10.1109/ACCESS.2019.2922691.
  • Hemanth, G., Janardhan, M., Sujihelen, L. (2019). Design and Implementing Brain Tumor Detection Using Machine Learning Approach . Third International Conference on Trends in Electronics and Informatics.1-6..https://doi.org/ 10.1109/ICOEI.2019.8862553.
  • Huafeng, W., Haixia, P., Huafeng,W., Yanxiang , Z., Yehe, C. (2015). Deep Learning for Image Retrieval: What Works and What Doesn't, Conference Paper .1-22.https://doi.org/10.1109/ICDMW.2015.121.
  • Kaggle Brain Tumor Classification (MRI) dataset, by Bhuvaji, S., Kadam, A., Bhumkar, P., Dedge, S., Kanchan, S., https://doi.org/10.34740/KAGGLE/DSV/1183165, Accessed: December 2020.
  • Kebir, S.T. & Mekaoui, S. (2018). An Efficient Methodology Of Brain Abnormalities Detection Using CNN Deep Learning Network. in Proc. Int. Conf.Appl. Smart Syst. (ICASS). https://doi.org/10.1109/ICASS.2018.8652054.2018.
  • Latif, G., Iskandar, D., Alghazo, N.F., Mohammad, J.M.N. (2018). Enhanced MR Image Classification Using Hybrid Statistical and Wavelets Features. IEEE Access .9634- 9644.https://doi.org/10.1109/ACCESS. 2018.2888488.
  • Manav, S., Pramanshu, S., Ritik, M., Kamakshi, G. (2021). Brain Tumour Detection Using Machine Learning . Journal of Electronics and Informatics, Volume 3, Issue 4. 298-308, 2021. https://doi.org/10.36548/jei.2021.4.005.
  • Minz, A. & Mahobiya, C. (2017). MR Image Classification Using Adaboost for Brain Tumor Type. IEEE 7th International Advance Computing Conference .1-5.https://doi.org/10.1109/IACC.2017.0146.
  • Mohsen, H., Sayed, E., Dahshan, E., Badeeh, A., Salem, M. (2018). Classification Using Deep learning Neural networks for Brain Tumors Future. Computing and Informatics Journal.68-73.https://doi.org/10.1109/ACCESS.2018.2888488.
  • Narayana, R.L. & Reddy, T.S. (2018). An Efficient Optimization Technique to Detect Brain Tumor from MRI Images. International Conference on Smart Systems and Inventive Technology.1-4.https://doi.org/10.1109/ICSSIT.2018.8748288.
  • Polat, Ö. & Güngen, C . (2021). Classification of Brain Tumors from MR Images Using Deep Transfer Learning. The Journal of Supercomputing ,volume 77. 7236–7252. https://doi.org/10.1007/s11227-020-03572-9.
  • Polly, E.P., Shil, S.K., Hossain, M.A., Ayman, A., Jang, Y.M. (2018). Detection and Classification of HGG and LGG BrainTumor Using Machine Learning. International conference on Information Networking. 813-817.https://doi.org/10.1109/ICOIN.2018.8343231.
  • Prabira, K.S. & Santi, K.B. (2021). A Data Constrained Approach for Brain Tumour Detection Using Fused Deep Features and SVM, Multimedia Tools and Applications, vol. 80, 28745-28760.https://doi.org/10.1007/s11042-021-11098-2.
  • Rehman, A., Khan, M.A., Saba, T.Z., Mehmood, T.U., Ayesha, N. (2021). Microscopic Brain Tumor Detection And Classification Using 3D CNN And Feature Selection Architecture. Microsc. Res. Techn, vol. 84, no. 1,133–149, 2021. https://doi.org/10.1002/jemt.23597.2021.
  • Rehman,A., Naz, S., Razzak,M.I., Akram ,F., Imran,M.Amin, J., Sharif, M., Yasmin, M., Fernandis, S.(2017). A Distinctive Approach in Brain Tumor Detection and Classification Using MRI. Pattern Recognition Letters.1- 10.https://doi.org/10.1016/j.patrec.2017.10.036.
  • Sethy, P.K. & Behera, S.K. (2021). A Data Constrained Approach for Brain Tumour Detection Using Fused Deep Features and SVM . Multimedia Tools and Applications (2021) 80.28745–28760.https://doi.org/10.1007/s11042-021-11098-2. Sert, E., Ozyurt, F., Doğantekin, A. (2019). A New Approach for Brain Tumor Diagnosis System: Single Image Superresolution Based Maximum Fuzzy Entropy Segmentation and Convolutional Neural Network. Medical Hypothesis.1-9.https://doi.org/10.1016/j.mehy.2019.109413.
  • Shankar, A.S., Asokan, A., Sivakumar, D. (2016). Brain Tumor Classification Using Gustafson–kessel (G-k) Fuzzy Clustering Algorithm. International Journal of Latest Engineering Research and Applications .68-72.
  • Simonyan, K. & Zisserman, A. (2014). Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556.https://doi.org/10.1109/ACPR.2015.7486599.
  • Talo, M., Baloglu, U.B., Yıldırım, O., Acharya, U.R. (2019). Application Of Deep Transfer Learning For Automated Brain Abnormality Classification Using MRI Images.Cognitive Systems Research, 54(2019), 176–188.https://doi.org/10.1016/j.cogsys.2018.12.007.
  • Vinoth, R. & Venkatesh, C. (2018). Segmentation And Detection Of Tumor in MRI Images Using CNN And SVM Classification. in Proc. Conf. Emerg. Devices Smart Syst. (ICEDSS). 21–25. https://doi.org/10.1109/ICEDSS.2018.8544306.2018.
  • Wang, F.& Gong, M. (2020). Single Image Super-Resolution by Residual Recovery Based On an Independent Deep Convolutional Network.VOLUME 4.1–10.https://doi.org/10.1109/ACCESS.2020.2986365.
  • Wang, H., Pan, H., Zhang, Y., Cai,Y. (2015). Deep Learning for Image Retrieval: What Works and What Doesn't. Conference Paper ·1-22. https://doi.org/10.1109/ICDMW.2015.121. Zaw, H.T., Maneerat, N., Win, K.Y. (2019). Brain Tumor Detection Based On Naïve Bayes Classification. International Conference on Engineering, Applied Sciences and Technology.1-4. https://doi.org/10.1109/ICEAST.2019.8802562.
Toplam 28 adet kaynakça vardır.

Ayrıntılar

Birincil Dil İngilizce
Konular Bilgisayar Görüşü, Örüntü Tanıma, Derin Öğrenme
Bölüm Bilgisayar Mühendisliği
Yazarlar

Samaneh Sarfarazı 0009-0007-5139-5662

Önsen Toygar 0000-0001-7402-9058

Yayımlanma Tarihi 12 Aralık 2023
Gönderilme Tarihi 9 Ağustos 2023
Yayımlandığı Sayı Yıl 2023Cilt: 26 Sayı: Özel Sayı - 9th Uluslararası IFS Çağdaş Matematik ve Mühendislik Konferansı (IFSCOM-E) Özel Sayısı

Kaynak Göster

APA Sarfarazı, S., & Toygar, Ö. (2023). CLASSIFICATION OF BRAIN TUMORS ON MRI IMAGES USING DEEP LEARNING ARCHITECTURES. Kahramanmaraş Sütçü İmam Üniversitesi Mühendislik Bilimleri Dergisi, 26(Özel Sayı), 1177-1186. https://doi.org/10.17780/ksujes.1339884
 Kapak Resmi İndir