An Integrated AI-Based System For Early-Stage Of Brain Tumor Prediction

The current research proposed an integrated Artificial Intelligence (AI)-based system for the detection of brain tumor using the images from the MRI. Convolutional Neural Network is used as the feature extraction module, where automatic brain tumor images are classified into gliomas, meningiomas, pituitaries and non-tumors. In addition, a feature-based prediction module with patient-specific information, such as the age of the patient, genetic risk, medical history are also included, where combined features of images and other features enable increase the prediction accuracy and system credibility. From the obtained experiment results, the proposed CNN is capable of distinguishing and determining the type of tumor with high confidence, which is well suited for the analysis of medical images. Also, a Streamlit-based UI has been designed for interactive input of images by end-users. In order to present a clear understanding for the end-users, an explainable AI module with Gemini API has been designed to produce the informative and easy-to-use explanation for the prediction result of tumor type. The current system provides a reliable and efficient way for the early detection of the brain tumors.

  [1] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, 2015. [2] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016. [Online]. Available: https://www.deeplearningbook.org [3] G. Litjens et al., “A survey on deep learning in medical image analysis,” Medical Image Analysis, 2017. [4] A. Esteva et al., “A guide to deep learning in healthcare,” Nature Medicine, 2019. [5] N. Abiwinanda et al., “Brain tumor classification using CNN,” IEEE, 2019. [Online]. Available: https://ieeexplore.ieee.org/document/8903051 [6] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in IEEE CVPR, 2016. [7] O. Ronneberger, P. Fischer, and T. Brox, “U-Net: Convolutional networks for biomedical image segmentation,” in MICCAI, 2015. [Online]. Available: https://arxiv.org/abs/1505.04597 [8] S. Deepak and P. M. Ameer, “Brain tumor classification using deep CNN features,” Computers in Biology and Medicine, 2019. [9] M. Havaei et al., “Brain tumor segmentation with deep neural networks,” Medical Image Analysis, 2017. [10] T. T. Nguyen et al., “Deep learning for brain tumor detection: A review,” IEEE Access, 2020.