Algoritma Convolutional Neural Network sebagai Alat Bantu Analisa Tingkat Keparahan Tumor Otak

IRMANIAR IRMANIAR; JOSUA TIMOTIUS MANIK; FREDDY HARYANTO

doi:10.26760/mindjournal.v9i1.1-12

Algoritma Convolutional Neural Network sebagai Alat Bantu Analisa Tingkat Keparahan Tumor Otak

IRMANIAR IRMANIAR, JOSUA TIMOTIUS MANIK, FREDDY HARYANTO

Sari

Abstrak

Kecerdasan buatan telah menjadi dasar dalam pengembangan computer-aided-diagnosed (CAD), yaitu alat tambahan yang digunakan untuk melakukan diagnosa penyakit, misalnya tumor otak. Pada penelitian ini dilakukan klasifikasi otomatis citra MRI otak ke dalam 4 kategori, yaitu tumor otak grade II, III, IV dan non-tumor menggunakan Convolutional Neural Network (CNN). Tiga jenis arsitektur yang digunakan, yaitu arsitektur 12 lapisan, Resnet-152 dan VGG-16. Peningkatan jumlah gambar dilakukan dengan melakukan 6 jenis teknik augmentasi. Hasilnya menunjukkan bahwa ketiga model dapat melakukan klasifikasi tumor dengan akurasi masing-masing sebesar 84%, 95% dan 84% pada data tanpa augmentasi dan 49%, 81% dan 72% untuk data yang mengalami augmentasi. Hasil tersebut menunjukkan bahwa arsitektur Resnet-152 memberikan performa terbaik dibandingkan dengan arsitektur lainnya.

Kata kunci: Tumor otak, Convolutional Neural Network (CNN), Resnet-152, VGG-16

Abstract

Artificial intelligence has become the basis for the development of computer-aided-diagnosed (CAD), an additional tool used to diagnose diseases, such as brain tumors. In this study, automatic classification of brain tumor was carried out into 4 categories, namely grade II, III, IV and non-tumor using the Convolutional Neural Network (CNN) algorithm. Three types of architecture are used, namely 12 layer architecture, Resnet-152 and VGG-16. The dataset comes from the REMBRANDT and IXI dataset. Increasing the number of images using 6 types of augmentation techniques is also done. The results show that the three models can classify tumors with an accuracy of 84%, 95% and 84% respectively for data without augmentation and 49%, 81% and 72% for data with augmentation. It can be concluded that the Resnet-152 architecture provides the best performance than the other architectures.

Keywords: Brain tumor, Convolutional Neural Network (CNN), Resnet-152, VGG-16

Teks Lengkap:

PDF

Referensi

Alqudah, A. M., Alquraan, H., Qasmich, I. A., Alqudah, A. & Al-Sharu, W. (2019). Brain tumor classification using deep learning technique - a comparison between cropped, uncropped, and segmented lesion images with different sizes, International Journal of Advanced Trends in Computer Science and Engineering, 8, 6

Chan, H., Hadjiiski, L. M., & Samala, R. K. (2020). Computerâ€aided diagnosis in the era of deep learning. Medical Physics, 47, 5

Deepak, S & Ameer, P. M. (2019). Brain tumor classification using deep CNN features via transfer learning, Computers in Biology and Medicine, 111, 103345

Edge, S. B. & Compton, C. C. (2010). The American joint committee on cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM, Annals of Surgical Oncology, 17, 1471â€“1474

Fitri, L A. (2020): Optimization of convolutional neural network parameters for urinary stones classification based on attenuation coefficient and dispersive X ray spectrum, Disertasi Program Doktor, Institut Teknologi Bandung, 18-24

Kumar, R. A., Gupta, H. S., Arora, G. N., Pandian & Raman, B. (2020). CGHF: A Computational Decision Support System for Glioma Classification Using Hybrid Radiomics- and Stationary Wavelet-Based Features, IEEE Access, 8, 79440-79458

Louis, D. N., Perry, A., Reifenberger, G., Deimling, A. V., Branger, D. F., Cavenee, W. K., Ohgaki, H., Wiestler, O. D., Kleihues, P. & Ellison, D. W. (2016). The 2016 world health organization classification of tumors of the central nervous system: a summary, Acta Neuropathol, 131(6), 803-20

Salamon, J. and Bello, J.P. (2017). Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification, IEEE Signal Processing Letters, 24, 3, 279-283

Shorten, C. & Khoshgoftaar, T.M. (2019). A survey on Image Data Augmentation for Deep Learning. J Big Data, 6, 60

Truhn, D., Schrading, S., Haarburger, C., Schneider, H., Merhof, D., Kuhl, S. (2019). Radiomic versus convolutional neural networks analysis for classification of contrast-enhancing lesions at multiparametric breast MRI, Radiology, 00

Xiao, M., Zhao, C., Zhu, Q., Zhang, J., Liu, H., Li, J. & Jiang, Y. (2019). An investigation of the classification accuracy of a deep learning framework-based computer-aided diagnosis system in different pathological types of breast lesions, Journal of Thoracic Disease, 12, 5023-5031

Yamashita, R., Nishio, M., Do, R.K.G., Togashi, K. (2018). Convolutional neural networks: an overview and application in radiology, Insights Imaging, 9(4), 611-629

Zukotynski, K., Gaudet, V., Kuo, P. H., Adamo, S., Goubran, M., Scott, C., Bocti, C., Borrie, M., Chertkow, H., Frayne, R., Hsiung, R., Laforce, R., Noseworthy, M. D., Prato, F. S., Sahlas, D. J., Smith, E. E., Sossi, V., Thiel, A., Soucy J. P., Tardif, J. C., & Black, S. E. (2019). The Use of Random Forests to Classify Amyloid Brain PET, Clinical Nuclear Medicine, 44, 10

DOI: https://doi.org/10.26760/mindjournal.v9i1.1-12