Perbandingan Kinerja Model Transfer Learning VGG16 dan ResNet50 Dalam Klasifikasi Tumor Otak Pada Citra MRI
Abstract
Tingginya prevalensi tumor otak dan pentingnya deteksi dini mendorong pengembangan sistem diagnosis otomatis berbasis kecerdasan buatan. Penelitian ini bertujuan membandingkan kinerja dua arsitektur deep learning, yaitu VGG16 dan ResNet50, dalam mengklasifikasi empat jenis citra MRI tumor otak yakni glioma, meningioma, pituitary, dan no tumor. Pendekatan yang digunakan adalah transfer learning dengan dua skenario perbandingan yakni sebelum dan sesudah fine-tuning. Transfer learning memungkinkan pemanfaatan model yang telah dilatih sebelumnya, sedangkan fine-tuning dilakukan untuk menyesuaikan parameter model terhadap karakteristik data baru. Seluruh proses penelitian mengikuti tahapan Knowledge Discovery in Database (KDD), yang meliputi pengumpulan data, preprocessing, pelatihan model, dan evaluasi. Hasil evaluasi menunjukkan bahwa ResNet50 menghasilkan akurasi sebesar 94,80% sebelum fine-tuning dan meningkat menjadi 97,54% setelah fine-tuning. Sementara itu, VGG16 memperoleh akurasi sebesar 91,39% sebelum fine tuning dan meningkat signifikan menjadi 98,68% setelah fine tuning. Berdasarkan hasil tersebut, dapat disimpulkan bahwa model VGG16 dengan fine-tuning menunjukkan kinerja terbaik dalam klasifikasi tumor otak pada citra MRI. Temuan ini mengindikasikan bahwa pendekatan deep learning berbasis transfer learning berpotensi meningkatkan efektivitas dan efisiensi diagnosis tumor otak secara otomatis. Kata Kunci: fine-tuning, transfer learning, VGG16, ResNet50, klasifikasi tumor, citra MRI
Downloads
References
[1] C. Watson, M. Kirkcaldie, and G. Paxinos, The Brain: An Introduction to Functional Neuroanatomy. CiNii Books, Oct. 31, 2023. [Online]. Available: https://ci.nii.ac.jp/ncid/BB04049625 [Accessed: Oct. 30, 2024].
[2] N. Shettigar, C. L. Yang, K. C. Tu, and C. S. Suh, “On the Biophysical Complexity of Brain Dynamics: An Outlook,” Dynamics, vol. 2, no. 2, pp. 114–148, 2022.
[3] J. Ferlay et al., “Global Cancer Observatory: Cancer Today,” International Agency for Research on Cancer, Lyon, France, 2020. [Online]. Available: https://gco.iarc.fr/today [Accessed: Oct. 29, 2024].
[4] D. N. Louis et al., “The 2021 WHO Classification of Tumors of the Central Nervous System: A Summary,” Neuro-Oncology, vol. 23, no. 8, pp. 1231–1251, 2021.
[5] M. Matia et al., “Magnetic Resonance Image of Primary Adult Brain Tumors: State of the Art and Future Perspectives,” Biomedicines, vol. 11, no. 2, pp. 364, 2023.
[6] A. B. Abdusalomov, M. Mukhiddinov, and T. K. Whangbo, “Brain Tumor Detection Based on Deep Learning Approaches and Magnetic Resonance Imaging,” Cancers (Basel), vol. 15, no. 16, pp. 4172, 2023.
[7] A. Kascenas, N. Pugeault, and A. Q. O’Neil, “Denoising Autoencoders for Unsupervised Anomaly Detection in Brain MRI,” in Proc. Medical Imaging with Deep Learning, Edinburgh, Scotland, vol. 172, pp. 653–664, 2022.
[8] A. J. Rozaqi, A. Sunyoto, and M. R. Arief, “Implementasi Transfer Learning pada Algoritme Convolutional Neural Network untuk Identifikasi Penyakit Daun Kentang,” Procedia Engineering and Life Sciences, vol. 1, no. 1, 2021.
[9] K. R. Reddy and R. Dhuli, “A Novel Lightweight CNN Architecture for the Diagnosis of Brain Tumors Using MR Images,” Diagnostics, vol. 13, no. 2, pp. 312, 2023.
[10] American Association of Neurological Surgeons, “Brain Tumors.” [Online]. Available: https://www.aans.org/patients/conditions-treatments/brain-tumors/ [Accessed: Nov. 2, 2024].
[11] National Institute of Biomedical and Bioengineering, “Magnetic Resonance Imaging (MRI),” Apr. 2022. [Online]. Available: https://www.nibib.nih.gov/sites/default/files/2022-05/Fact-Sheet-Magnetic-Resonance-Imaging-MRI.pdf [Accessed: Nov. 2, 2024].
[12] D. Bhavani, A. Vasari, and P. T. Keshava, “Machine Learning: A Critical Review of Classification Techniques,” International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), vol. 3, no. 11, pp. 17–23, 2016.
[13] K. Sharifani and M. Amini, “Machine Learning and Deep Learning: A Review of Methods and Applications,” World Information Technology and Engineering Journal, vol. 10, no. 7, pp. 3897–3904, 2023.
[14] R. Geetha and T. Thilagam, “A Review on the Effectiveness of Machine Learning and Deep Learning Algorithms for Cyber Security,” Archives of Computational Methods in Engineering, vol. 28, no. 4, pp. 2861–2879, 2021.
[15] A. Hosna, E. Merry, J. Gyalmo, Z. Alom, Z. Aung, and M. Abdul Azim, “Transfer Learning: A Friendly Introduction,” Journal of Big Data, vol. 9, no. 1, pp. 102, 2022.
[16] Amanatulla, “Fine-Tuning the Model: What, Why, and How,” Medium, Sep. 21, 2023. [Online]. Available: https://medium.com/@amanatulla1606/fine-tuning-the-model-what-why-and-how-e7fa52bc8ddf [Accessed: May 30, 2025].
[17] A. Garg, “Image Classification Using ResNet-50 Deep Learning Model,” Data Science Blogathon, Sep. 20, 2022. [Online]. Available: https://www.analyticsvidhya.com/blog/2022/09/image-classification-in-stl-10-dataset-usingresnet-50-deep-learning-model/ [Accessed: Nov. 9, 2024].
[18] V. Kurama, “A Review of Popular Deep Learning Architectures: AlexNet, VGG16, and GoogleNet,” DigitalOcean, Sep. 25, 2024. [Online]. Available: https://www.digitalocean.com/community/tutorials/popular-deep-learning-architectures-alexnet-vgg-googlenet [Accessed: Nov. 9, 2024].
[19] H. Naviwala, “What is a Confusion Matrix? Understand the 4 Key Metric of its Interpretation,” Data Science Dojo, Sep. 23, 2024. [Online]. Available: https://datasciencedojo.com/blog/confusion-matrix/ [Accessed: Nov. 9, 2024].
[20] Deepanshi, “In-depth Understanding of Confusion Matrix,” Data Science Blogathon, Nov. 21, 2023. [Online]. Available: https://www.analyticsvidhya.com/blog/2021/05/in-depth-understanding-of-confusion-matrix/ [Accessed: Nov. 9, 2024].
[21] V. Brusic and J. Zeleznikow, “Knowledge Discovery and Data Mining in Biological Databases,” The Knowledge Engineering Review, vol. 14, no. 3, pp. 257–277, 1999.
