Deep learning has made great progress in medical diagnosis. However, due to data standardization and privacy restriction, the acquisition and sharing of medical image data have been hindered, leading to the unacceptable accuracy of some intelligent medical diagnosis models. Another concern is data quality. If insufficient quantity and low-quality data are used for training and testing medical diagnosis models, it may cause serious medical accidents. We always use data augmentation to deal with it, and one of the most representative ways is through mutation relation. However, although common mutation methods can increase the amount of medical data, the quality of the image cannot be guaranteed due to the particularity of medical image. Therefore, combined with the characteristics of medical images, we propose TauMed, which implements augmentation techniques based on a series of mutation rules and domain semantics on medical datasets to generate sufficient and high-quality images. Moreover, we chose the ResNet-50 model to experiment with the augmented dataset and compared the results with two main popular mutation tools. The experimental result indicates that TauMed can improve the classification accuracy of the model effectively, and the quality of augmented images is higher than the other two tools. Its video is at https://www.youtube.com/watch?v=O8W8I7U_eqk and TauMed can be used at http://121.196.124.158:9500/.

This paper investigates the performance on a class of DTCWTs based on the common factor technique. The common factor technique was first proposed in [6] by Selesnick, where two corresponding scaling lowpass filters are required to satisfy the half-sample delay condition, and then was modified to improve the analyticity [9] and frequency selectivity [8]. The analyticity of complex wavelet can be improved by minimizing the phase error in the approximation band of allpass filters with given flatness condition. The frequency selectivity of scaling lowpass filters can be improved by locating a specified number of zeros at z = -1 and applying the Remez exchange algorithm to minimize the magnitude response in the stopband. How to determine the approximation band and stopband will influence the performance of DTCWT. Therefore, this paper is dedicated to how to choose the approximation band and stopband properly.