Medical image classification via multiscale representation learning

Multiscale structure is an essential attribute of natural images. Similarly, there exist scaling phenomena in medical images, and therefore a wide range of observation scales would be useful for medical imaging measurements. The present work proposes a multiscale representation learning method via sparse autoencoder networks to capture the intrinsic scales in medical images for the classification task. We obtain the multiscale feature detectors by the sparse autoencoders with different receptive field sizes, and then generate the feature maps by the convolution operation. This strategy can better characterize various size structures in medical imaging than single-scale version. Subsequently, Fisher vector technique is used to encode the extracted features to implement a fixed-length image representation, which provides more abundant information of high-order statistics and enhances the descriptiveness and discriminative ability of feature representation. We carry out experiments on the IRMA-2009 medical collection and the mammographic patch dataset. The extensive experimental results demonstrate that the proposed method have superior performance.