查看文章

Transfer learning strategies were used to develop a unique method in the field of medicine. Investigation in this study suggests an ensemble technique for early brain tumor detection utilizing tumor images. This investigation uses the BRATS dataset, which can be broken into two categories. A transfer learning strategy was used throughout initializing of the parameters and pre-training three neural networks named MobileNetV2, InceptionV3, and ResNet50. After these component models extracted characteristics from input photos, the Relu layer coupled to the Dense Layer was utilized as the classifier to train the models on the relevant dataset. The accuracy was verified using cross-validation of five, ten, and twenty folds. The final classifier was the Ensemble Deep Learning- Brain Tumor Classification (EDL-BTC), constructed by applying a weighted aggregate of the results of the component models. By obtaining 98.3 …