Transfer Learning in Brain Tumor Detection: from AlexNet to Hyb-DCNN-ResNet

Abstract

Detecting abnormalities in the human body with magnetic resonance imaging has long been a challenge in medical computer-aided diagnosis (CAD). This paper presents a comprehensive review of research focusing on transfer learning (TL) in brain tumor detection. Each work starts from collecting MR images and substantial strategies are applied when preprocessing data including data augmentation and image segmentation. Multiple pre-trained models from AlexNet to Hyb-DCNN-ResNet in the latest work are focused. And the results of binary and multiple class classification are compared chronologically. Three pre-trained models which are frequently used to attain a good performance in brain tumor detection are illustrated in detail. And these pre-trained models, GoogLeNet, VGG and ResNet, all are capable to help the proposed systems reach the accuracy of 99%. The challenges even after transferring apposite knowledge to the target domain still exist in pluralistic forms. But the essence of transfer learning can support interdisciplinary research to get better performance.