Deep Learning and Transfer Learning for Brain Tumor Detection and Classification
bioRxiv – April 10, 2023
Source: medRxiv/bioRxiv/arXiv
Summary
Deep learning models can significantly enhance brain tumor detection using MRI scans. By employing advanced neural networks, particularly through a novel transfer learning technique inspired by animal camouflage detection, researchers improved classification accuracy. The models not only identified tumors but also considered surrounding tissue changes, mimicking expert radiologists' assessments.
Abstract
Convolutional neural networks (CNNs) are powerful tools that can be trained on image classification tasks and share many structural and functional similarities with biological visual systems and mechanisms of learning. In addition to serving as a model of biological systems, CNNs possess the convenient feature of transfer learning where a network trained on one task may be repurposed for training on another, potentially unrelated, task. In this retrospective study of public domain MRI data, we investigate the ability of neural network models to be trained on brain cancer imaging data while introducing a unique camouflage animal detection transfer learning step as a means of enhancing the network’s tumor detection ability. Training on glioma and normal brain MRI data, post-contrast T1-weighted and T2-weighted, we demonstrate the potential success of this training strategy for improving neural network classification accuracy. Qualitative metrics such as feature space and DeepDreamImage analysis of the internal states of trained models were also employed, which show improved generalization ability by the models following camouflage animal transfer learning. Image sensitivity functions further this investigation by allowing us to visualize the most salient image regions from a network’s perspective while learning. Such methods demonstrate that the networks not only ‘look’ at the tumor itself when deciding, but also at the impact on the surrounding tissue in terms of compressions and midline shifts. These results suggest an approach to brain tumor MRIs that is comparatively similar to that of trained radiologists while also exhibiting a high sensitivity to subtle structural changes resulting from the presence of a tumor. These findings present an opportunity for further research and potential use in a clinical setting.