Deep Learning Based Lightweight Model for Brain Tumor Classification and Segmentation

Andleeb, Ifrah; Hussain, B. Zahid; Ansari, Salik; Ansari, Mohammad Samar; Kanwal, Nadia; Aslam, Asra

Abstract

This paper presents two lightweight deep learning models for efficient detection and segmentation of brain tumors from MRI scans. A custom-made Convolutional Neural Network (CNN) is designed for identification of four different classes of brain tumors viz. Meningioma, Glioma, Pituitary brain tumor and normal (no tumor). Furthermore, another tailor-made lightweight model is presented for the segmentation of the tumor from the Magnetic Resonance Imaging (MRI) scans. The output of the segmentation model is the ‘mask’ depicting the tumor region. The overall performance in terms of detection accuracy, and segmentation accuracy, for the two models is found to be approximately 95% for both the cases individually. The proposed models are worthy additions to the existing literature on brain tumor classification and segmentation models due to their low-parameter count which make the models amenable for deployment on resource-constrained edge hardware.

Citation

Andleeb, I., Hussain, B. Z., Ansari, S., Ansari, M. S., Kanwal, N., & Aslam, A. (2024). Deep Learning Based Lightweight Model for Brain Tumor Classification and Segmentation. In Advances in Computational Intelligence Systems (491-503). Springer Nature [academic journals on nature.com]. https://doi.org/10.1007/978-3-031-47508-5_38

• Acceptance Date: Feb 1, 2024
• Online Publication Date: Feb 1, 2024
• Publication Date: 2024
• Deposit Date: Sep 13, 2024
• Publisher: Springer Nature [academic journals on nature.com]
• Pages: 491-503
• Series Title: Advances in Intelligent Systems and Computing
• Book Title: Advances in Computational Intelligence Systems
• ISBN: 9783031475078; 9783031475085
• DOI: https://doi.org/10.1007/978-3-031-47508-5_38
• Public URL: https://keele-repository.worktribe.com/output/920681
• Publisher URL: https://link.springer.com/chapter/10.1007/978-3-031-47508-5_38
• Additional Information: First Online: 1 February 2024; Conference Acronym: UKCI; Conference Name: UK Workshop on Computational Intelligence; Conference City: Birmingham; Conference Country: United Kingdom; Conference Year: 2023; Conference Start Date: 6 September 2023; Conference End Date: 8 September 2023; Conference ID: ukci2023; Conference URL: https://www.uk-ci.org/