DETECTION AND CLASSIFICATION OF BRAIN CANCER USING DEEP LEARNING
Brain cancer is a serious medical condition that requires an accurate and timely diagnosis for effective treatment planning. In recent years, deep learning techniques have shown great potential in the field of medical image analysis. In this study, a brain cancer detection and classification system...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Year Project Report |
| Language: | English English |
| Published: |
Universiti Malaysia Sarawak, (UNIMAS)
2023
|
| Subjects: | |
| Online Access: | http://ir.unimas.my/id/eprint/43144/1/Asvin%20Kumar%20Moghan%2024pgs.pdf http://ir.unimas.my/id/eprint/43144/7/Asvin%20Kumar%20%20ft.pdf http://ir.unimas.my/id/eprint/43144/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Brain cancer is a serious medical condition that requires an accurate and timely diagnosis for effective treatment planning. In recent years, deep learning techniques have shown great potential in the field of medical image analysis. In this study, a brain cancer detection and classification system based on deep learning algorithms is proposed. The system utilises a convolutional neural network (CNN) architecture trained on a large dataset of brain MRI images. The images were preprocessed to enhance relevant features and remove noise. The CNN architecture chosen was GoogleNet. To validate the robustness of the system, a 5-fold cross-validation approach was employed, ensuring reliable and consistent results. The proposed system has the potential to assist medical professionals in the early detection and classification of brain tumours, aiding in accurate diagnosis and treatment decision-making. By automating the classification process, it reduces the burden of manual analysis, potentially saving time and improving the overall efficiency of the diagnostic process. The proposed model achieved an accuracy of 97.5522±0.2739%, a precision of 0.9498±0.0054, a recall of 0.9494±0.0057, a specificity 0.9839±0.0018 and an F1 Score of 0.9493±0.0057 across the 5-fold cross-validation iterations, demonstrating its effectiveness in accurately classifying brain MRI. |
|---|