DEVELOPMENT OF WEB-BASED APPLICATION FOR TUMOR CLASSIFICATION USING PRE-TRAINED VGG19 MODELS

I Putu Rangga Indra Pramana

Authors

I Putu Rangga Indra Pramana Institut Bisnis dan Teknologi Indonesia (INSTIKI)

Keywords:

Tumor Classification, VGG19, Convolutional Neural Network, Flask, Web Application

Abstract

This paper discusses the development of a web-based application for brain tumor classification using a pre-trained VGG19 convolutional neural network (CNN) model. The application aims to assist in the early detection of brain tumors by automating the analysis of MRI images, thereby minimizing diagnostic errors. The dataset, sourced from Kaggle, consists of 253 brain MRI images, including 155 images of "Tumor" and 98 images of "No Tumor." The methodology involves transfer learning and fine-tuning of the VGG19 architecture to classify brain MRI images. The system is integrated into a user-friendly Flask-based web application, which allows healthcare professionals to access real-time predictions. Evaluation results show that the model achieves an accuracy of 82%, demonstrating its potential to assist doctors in making accurate diagnoses. This research addresses the critical need for reliable diagnostic tools, aiming to reduce misdiagnosis and improve patient outcomes. By leveraging deep learning and web-based platforms, the application offers a scalable solution for remote and automated brain tumor detection.

References

Khan, S., & Khan, S. (2020). Brain tumor classification using CNN-based deep learning architecture. Journal of Healthcare Engineering, 2020. https://doi.org/10.1155/2020/8123627

Sharma, P., & Singh, D. (2020). A review of CNN models for brain tumor classification. Journal of Biomedical Science and Engineering, 13(2), 25-40. https://www.scirp.org/journal/paperinformation.aspx?paperid=10003731

He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770-778. https://doi.org/10.1109/CVPR.2016.90

Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. https://arxiv.org/abs/1409.1556

Ozturk, T., & Guleryuz, M. (2019). CNN-based brain tumor classification using MRI images. International Journal of Computer Applications, 178(9), 27-35. https://doi.org/10.5120/ijca2019918663

Rajendra, P., & Pradhan, D. (2018). Convolutional neural network for brain tumor detection in MRI images. International Journal of Emerging Trends in Engineering and Development, 4(10), 28-35.

Ahmed, M., & Aslam, N. (2019). Transfer learning in brain tumor detection using CNNs: A systematic review and future directions. Proceedings of the International Conference on Computer Vision and Pattern Recognition. https://doi.org/10.1109/ICCVW.2019.00134

Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., ... & Rabinovich, A. (2015). Going deeper with convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1-9.

Karpathy, A., & Fei-Fei, L. (2015). Deep visual-semantic alignments for generating image descriptions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 3128-3137.

Zhou, Z.-H., & Jiang, Y.-G. (2021). Multi-class brain tumor classification based on convolutional neural networks with transfer learning and data augmentation techniques: A case study on MRI images from Kaggle dataset. MDPI Electronics, 11(7), 1146. https://doi.org/10.3390/electronics11071146.