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

TL;DR

This study introduces a weakly supervised brain tumor grade classification method combining hand-crafted features with LSTM networks, leveraging domain transforms like Wavelet and DCT to improve accuracy and efficiency.

Contribution

The paper presents a novel approach integrating domain-specific transforms and hand-crafted features with LSTM for improved brain tumor classification under weak supervision.

Findings

Achieved state-of-the-art performance on brain tumor grade classification.

Demonstrated effectiveness of domain transforms in feature extraction.

Reduced computational cost with low-dimensional features.

Abstract

The performance of image classification methodsheavily relies on the high-quality annotations, which are noteasily affordable, particularly for medical data. To alleviate thislimitation, in this study, we propose a weakly supervised imageclassification method based on combination of hand-craftedfeatures. We hypothesize that integration of these hand-craftedfeatures alongside Long short-term memory (LSTM) classifiercan reduce the adverse effects of weak labels in classificationaccuracy. Our proposed algorithm is based on selecting theappropriate domain representations of the data in Wavelet andDiscrete Cosine Transform (DCT) domains. This informationis then fed into LSTM network to account for the sequentialnature of the data. The proposed efficient, low dimensionalfeatures exploit the power of shallow deep learning modelsto achieve higher performance with lower computational cost.In order to show efficacy of the proposed strategy, we haveexperimented classification of brain tumor grades and achievedthe state of the art performance with the resolution of 256 x 256. We also conducted a comprehensive set of experiments toanalyze the effect of each component on the performance.