Document Type
Honors Project - Open Access
Abstract
For the purpose of improving patient survival rates and facilitating efficient treatment planning, brain tumors need to be identified early and accurately classified. This research investigates the application of transfer learning and Convolutional Neural Networks (CNN) to create an automated, high-precision brain tumor segmentation and classification framework. Utilizing large-scale datasets, which comprise MRI images from open-accessible archives, the model exhibits the effectiveness of the method in various kinds of tumors and imaging scenarios. Our approach utilizes transfer learning techniques along with CNN architectures strengths to tackle the intrinsic difficulties of brain tumor diagnosis, namely significant tumor appearance variability and difficult segmentation tasks. The segmentation model, based on the U-Net architecture, excels in delineating tumor boundaries with remarkable precision, while the classification model, employing EfficientNet B3, achieves high accuracy in identifying tumor types. Our findings indicate a significant improvement in the speed and accuracy of brain tumor diagnosis, offering potential benefits for clinical practice and patient care.
Recommended Citation
Wang, Shengyuan, "The Future Of Brain Tumor Diagnosis: CNN And Transfer Learning Innovations" (2024). Mathematics, Statistics, and Computer Science Honors Projects. 87.
https://digitalcommons.macalester.edu/mathcs_honors/87
© Copyright is owned by author of this document
