Brain tumor grade classification Using LSTM Neural Networks with Domain Pre-Transforms

The performance of image classification methods heavily relies on the high-quality annotations, which are not easily affordable, particularly for medical data. To alleviate this limitation, in this study, we propose a weakly supervised image classification method based on combination of hand-crafted features. We hypothesize that integration of these hand-crafted features alongside Long short-term memory (LSTM) classifier can reduce the adverse effects of weak labels in classification accuracy. Our proposed algorithm is based on selecting the appropriate domain representations of the data in Wavelet and Discrete Cosine Transform (DCT) domains. This information is then fed into LSTM network to account for the sequential nature of the data. The proposed efficient, low dimensional features exploit the power of shallow deep learning models to achieve higher performance with lower computational cost. In order to show efficacy of the proposed strategy, we have experimented classification of brain tumor grades and achieved the state of the art performance with the resolution of 256 × 256. We also conducted a comprehensive set of experiments to analyze the effect of each component on the performance.