Klasifikasi Tumor Otak menggunakan Convolutional Neural Network dan Transfer Learning

Muhammad Hasan Fadlun, Martanto Martanto, Umi Hayati


Brain tumor is an uncontrolled growth of cells in the form of a mass or tissue within the brain, capable of producing both cancerous and non-cancerous symptoms. Brain tumors are part of a group of tumors involving the nervous system, including tumors in the spinal cord and peripheral nerves. It is not a common disease, and prompt intervention is necessary to receive timely medical treatment or appropriate therapy. This research aims to apply Deep Learning techniques in the automatic classification of brain tumors. In this study, a dataset of brain MRI images covering various types of brain tumors was used. The dataset consisted of 3264 MRI images with four classes: glioma, meningioma, pituitary, and no tumor, obtained from Kaggle.com. The system utilized a pre-trained CNN architecture, EfficientNet-B0, trained on the ImageNet dataset. In the Transfer Learning phase, fine-tuning was performed on the last layers of the CNN to adapt it to the brain tumor image dataset. The Convolutional Neural Network model was trained using MRI images to identify important features related to brain tumors. Subsequently, with Transfer Learning, the knowledge acquired by the pre-existing model was adopted and applied to a new dataset to enhance model performance. The application of Deep Learning techniques in the automatic classification of brain tumors provides significant benefits in medical practice. With this system, doctors and radiologists can obtain more effective assistance in diagnosis and treatment planning. The ability to automatically recognize brain tumors with high accuracy also enables the adoption of this technology in various medical facilities, thereby improving the accessibility of testing and treatment needed by patients. The results of this research demonstrate that the CNN and TL methods successfully achieved high performance, including an epoch accuracy of 0.9981 or 99%, a loss of 0.0061, and an evaluation with values generated by the confusion matrix showing high precision of 0.98 or 98%, recall of 0.98 or 98%, and an F1-score of 0.98 or 98%. This study illustrates the significant potential of implementing Deep Learning techniques, particularly CNN and TL, in the automatic classification of brain tumors. Advances in this field can contribute significantly to improving the diagnosis, treatment, and prognosis of brain tumor patients, accelerating efforts to address this complex disease.


Deep Learning, Convolutional Neural Network, Transfer Learning, classification, Brain Tumor

Full Text:



Amalia, K., Magladena, R., & ... (2022). Klasifikasi Penyakit Tumor Otak Pada Citra Mri Menggunakan Metode CNN Dengan Arsitektur Alexnet. EProceedings …. https://openlibrarypublications.telkomuniversity.ac.id/index.php/engineering/article/view/18991

Andre, R., Wahyu, B., & Purbaningtyas, R. (2021). KLASIFIKASI TUMOR OTAK MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DENGAN ARSITEKTUR EFFICIENTNET-B3 (Vol. 11, Issue 3). https://jurnal.umj.ac.id/index.php/just-it/index

Badža, M. M., & Barjaktarović, M. C. (2020). Classification of brain tumors from mri images using a convolutional neural network. Applied Sciences (Switzerland), 10(6). https://doi.org/10.3390/app10061999

Baranwal, S. K., Jaiswal, K., Vaibhav, K., Kumar, A., & Srikantaswamy, R. (2020). Performance analysis of Brain Tumour Image Classification using CNN and SVM. 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA), 537–542. https://doi.org/10.1109/ICIRCA48905.2020.9183023

Hastomo, W., Hadiyanto, E., & Sutarno, D. (2021). KLASIFIKASI COVID-19 CHEST X-RAY DENGAN TIGA ARSITEKTUR CNN (RESNET-152, INCEPTIONRESNET-V2, MOBILENET-V2). In Seminar Nasional Teknologi Informasi dan Komunikasi STI&K (SeNTIK) (Vol. 5, Issue 1).

Hastomo, W., Sugiyanto, & Sudjiran. (2021). Convolution Neural Network Arsitektur Mobilenet-V2 Untuk Mendeteksi Tumor Otak. Prosiding Seminar SeNTIK. https://ejournal.jak-stik.ac.id/index.php/sentik/article/view/3355

Kristian, M., Andryana, S., & Gunaryati, A. (2021). DIAGNOSA PENYAKIT TUMOR OTAK MENGGUNAKAN METODE WATERFALL DAN ALGORITMA DEPTH FIRST SEARCH. In Universitas Nasional Jl. Sawo Manila (Issue 61). Pejaten Bar., Kec. Ps. Minggu.

Mehrotra, R., Ansari, M. A., Agrawal, R., & Anand, R. S. (2020). A Transfer Learning approach for AI-based classification of brain tumors. Machine Learning with Applications, 2, 100003. https://doi.org/https://doi.org/10.1016/j.mlwa.2020.100003

Orlando, O., & Rivan, M. E. Al. (2023). Klasifikasi Jenis kanker Kulit Manusia Menggunakan Convolution Neural Network. MDP Student Conference. https://jurnal.mdp.ac.id/index.php/msc/article/view/4335

Salah Bayoumi, E., Khaled Abd-Ellah, M., Khalaf, A. A. M., & Gharieb, R. R. (2022). Brain Tumor Automatic Detection from MRI Images Using Transfer Learning Model with Deep Convolutional Neural Network (Vol. 41, Issue 2). http://jaet.journals.ekb.eg

Umri, B. K., & Delica, V. (2021). Penerapan transfer learning pada convolutional neural networks dalam deteksi covid-19. JNANALOKA. http://lenteradua.net/jurnal/index.php/jnanaloka/article/view/38

Winnarto, M. N., Mailasari, M., & ... (2022). KLASIFIKASI JENIS TUMOR OTAK MENGGUNAKAN ARSITEKTURE MOBILENET V2. Simetris: Jurnal Teknik …. https://jurnal.umk.ac.id/index.php/simet/article/view/8821

DOI: http://dx.doi.org/10.36499/jinrpl.v6i1.10318


  • There are currently no refbacks.


Google Scholar GarudaCrossrefBASE Dimensions DOAJOne Search Scilit Sinta




Address : :

Fakultas Teknik Universitas Wahid Hasyim

JL. Menoreh Tengah X / 22, Sampangan, Gajahmungkur, Kota Semarang, Jawa Tengah 50232, Indonesia
Handphone: 0815-6529-309
Email: jinformatika@unwahas.ac.id
RJI JournalStories Main logo
View My Stats
ISSN : 2656-2855   E-ISSN : 2685-5518