Brain tumor detection technique using deep learning for medical diagnosis

Setia Budi, Nur Anissya (2023) Brain tumor detection technique using deep learning for medical diagnosis. Project Report. Melaka, Malaysia, Universiti Teknikal Malaysia Melaka. (Submitted)

	Text (24 Pages) Brain tumor detection technique using deep laerning for medical diagnosis.pdf - Submitted Version Download (5MB)
	Text (Full Text) Brain tumor detection technique using deep laerning for medical diagnosis.pdf - Submitted Version Restricted to Registered users only Download (20MB)

Abstract

This final year report focuses on the development of deep learning-based brain tumour detection algorithms for medical diagnosis. The fundamental goal of this study is to overcome the difficulties in manually recognising and classifying brain tumours using MRI data. To do this, cutting-edge deep learning models such as VGG16, InceptionV3, ResNet50, and Xception are used to identify brain tumours and determine the best model for accurate detection. The project makes use of a dataset of 3000 MRI pictures separated into training, testing, and validation sets. The models are trained on the training data set, and their performance is measured using measures like accuracy, time, and loss. This enables for a thorough comparison and evaluation of the models performance in detecting brain tumours. This project findings contribute to the field of medical diagnostics by shedding light on the performance and applicability of deep learning algorithms for brain tumour identification. The test results will aid in determining the best effective model for reliably detecting brain tumours, allowing for early detection and timely action. Overall, the goal of this project is to increase the accuracy and efficiency of brain tumour diagnosis by utilising deep learning techniques. The findings of this study have the potential to have a substantial impact on medical diagnosis and lead to better patient care.

Actions (login required)

View Item