Purpose. Brain tumors have historically posed a significant risk to individuals, potentially leading to fatality. However, in contemporary times, they have emerged as one of the most dangerous health issues affecting both children and adults. The effects of this phenomenon result in the unregulated proliferation of brain cells. Therefore, early detection and precise classification of brain tumor is very necessary and important for saving lives and avoid future complications. Within the field of biological image processing, the utilisation of deep learning algorithms offers a distinct and unparalleled experience. The Convolutional Neural Network (CNN) is a pivotal component in brain tumor categorization applications. However, a notable limitation of CNNs is their extensive execution time, primarily attributed to the substantial number of trainable parameters involved. Also, the automatic detection and classification of brain tumor is still a challenging task due to its variability in shape, size and location. Methods. This study proposes a hybrid model for brain tumor classification that combines faster R-CNN and EfficientNet. The objective is to minimise the time required for classification without compromising accuracy. The data collection from Figshare was employed during the model’s development. Results and Conclusion. The hybrid model proposed in this study demonstrates a notable accuracy of 98.96% during the training phase and 99.2% during the testing phase, surpassing the performance of both the EfficientNet model and the Faster R-CNN model when employed individually. The aforementioned findings were derived through a comparative analysis of the Hybrid model, the EfficientNet model, and the Faster R-CNN model.
Read full abstract