Resnet -101 and Faster R-CNN Fusion Accurate Brain Tumor Detection and Categorization

Research into brain tumors can profoundly impact patients with long-term neurological and mental consequences. While some tumors manifest noticeable symptoms early, others remain undetected until they reach significant sizes. Despite advancements in deep learning, such as Convolutional Neural Networ...

Full description

Saved in:

Bibliographic Details
Published in:	2024 2nd International Conference on Artificial Intelligence and Machine Learning Applications Theme: Healthcare and Internet of Things (AIMLA) pp. 1 - 6
Main Authors:	K, Kavin Kumar, S, Srimathi, B, Suhashini, K, Vasanthan, N, Amirthavarshini, B, Arunkumar, B K, Dhanush, S, Sathesh
Format:	Conference Proceeding
Language:	English
Published:	IEEE 15-03-2024
Subjects:	Brain modeling Classification Computational modeling Convolutional neural network Convolutional neural networks Faster Region Feature extraction Medical services Real-time systems Resnet 101 Training
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Research into brain tumors can profoundly impact patients with long-term neurological and mental consequences. While some tumors manifest noticeable symptoms early, others remain undetected until they reach significant sizes. Despite advancements in deep learning, such as Convolutional Neural Networks (CNNs), improvements are still sought. Combining Residual Networks and Region-based CNNs offers a novel approach. Utilizing ResNet-101 as a feature extractor and Faster R-CNN for localization and classification, the model enhances accuracy and efficiency in diagnosis. This integration refines tumor detection by effectively capturing complex patterns from brain images. Training on a diverse dataset including various tumor types and anatomical variances, the model demonstrates improved accuracy and reduced false results. Its computational efficiency makes it viable for real-time clinical applications, addressing the critical need for swift diagnosis in medical contexts.
DOI:	10.1109/AIMLA59606.2024.10531315