Automation of Brain Tumor Identification using EfficientNet on Magnetic Resonance Images
Sushreeta Tripathy, Rishabh Singh, Mousim Ray
Abstract
The general method for classification of brain tumors is through biopsy, but biopsy is performed only after a surgery where a small tissue is removed from the brain and examined under a microscope to determine if it is a tumor. Due to the advancement in technology especially in machine learning and artificial intelligence, it is possible for us to determine and classify a tumor without performing any surgery and feeding the present data of various MRI images to the machine for classification. Through our work, we put forward a technique for the detection of tumors by using EfficientNet, a pre-trained model using the approach of transfer learning. This paper focuses on three models from the family of models of EfficientNet namely EfficientNet-B2, EfficientNet-B3, and EfficientNet-B4. The proposed framework not only uses the pre-trained model to improve the performance of training a better model but also uses thresholding to improve the dataset for better accuracy and data augmentation for increasing the number of images in the dataset. Preliminary outcome shows that the family of models of EfficientNet performs better than previous CNN architectures because to scale all dimensions of depth, width, and resolution of an image with a constant ratio it uses the compound coefficient. The results also demonstrated that by scaling the baseline architecture the model is able to capture complicated features and thus the overall performance of the model is improved.