AlexNet‐NDTL: Classification of MRI brain tumor images using modified AlexNet with deep transfer learning and Lipschitz‐based data augmentation

Abstract

Deep learning is frequently used to classify medical images. Surgeons may know the type of tumor before doing surgery on a patient. Transfer learning was used to alleviate the overfitting issue of deep networks in classification since the training samples, such as a brain MRI dataset, were insufficient. To overcome this issue, We introduce a new deep‐learning methodology for the categorization of MRI brain tumor images. This method combines a unique data augmentation model with modified AlexNet and network‐based deep transfer learning. We used Lipschitz‐based data augmentation on a dataset, and the output of the augmentation model was fed into a modified AlexNet that uses network‐based deep transfer learning to extract features from a dataset. The proposed model is trained and tested using the BraTS 2020 and Figshare datasets. The proposed model's performance is assessed using sensitivity, specificity, accuracy, precision, F1‐score, and MCC. The proposed model yields superior results.

Maintaining Symmetry between Convolutional Neural Network Accuracy and Performance on an Edge TPU with a Focus on Transfer Learning Adjustments

“…SpinalXNet [13] adds a specialized fully connected layer to the end of the ResNet-101 model to identify COVID-19 in X-ray images. Other approaches use transfer learning with a modified ResNet architecture to detect emotion in crowds [14] and brain tumors [15,16]. A modified version of the VGG-16 model is used with transfer learning to detect solar flares [17].…”