InceptionV3 infused Neural Network for Brain Tumor Detection

Automated identification and detection of brain tumors using Magnetic Resonance Imaging (MRI) is difficult, time-consuming and laborious because there exists many overlooked, misread, & deceptive lesions (similar to tumor) present in the brain tumor image scans. This paper evaluates the efficiency of the InceptionV3 infused convolutional neural network for brain tumor detection. Utilizing a comprehensive dataset Br35H with MRI brain tumor images, initially the model preprocessed and augmented the input to enhance training robustness. The novelty of our approach lies in the integration of advanced data augmentation techniques and a customized training pipeline. The proposed InceptionV3 infused neural network model achieved a validation accuracy of 98.50%, outperforming other models such as EfficientNetB4, VGG19, ResNet50, and MobileNetV2 in terms of key metrics. Our findings demonstrate that the proposed InceptionV3 infused neural network is highly effective and computationally efficient regarding brain tumor detection & classification, providing one reliable instrument for medical image analysis.