For the application of reversible watermarking technology in three-Dimensional (3D) medical images, a 3D medical image reversible watermarking algorithm based on unidirectional prediction error expansion was proposed. Firstly, the intermediate pixels were predicted according to the 3D gradient changes between them and their neighborhood pixels to obtain the prediction errors. Then, considering the features of the 3D medical image generated by magnetic resonance imaging, the external information was embedded into the 3D medical image by combining unidirectional histogram shifting with prediction error expansion. Finally, the pixels were re-predicted to extract the external information and restore the original 3D image. Experimental results on MR-head and MR-chest data show that compared with two-dimensional (2D) gradient-based prediction, the mean absolute deviation of prediction error produced by 3D gradient-based prediction are reduced by 1.09 and 1.40, respectively; and the maximal embedding capacity of each pixel is increased by 0.0456 and 0.1291 bits, respectively. The proposed algorithm can predict the pixels more accurately and embed more external information, so it is applicable to 3D medical image tempering detection and privacy protection for patients.

Concerning the low training speed of mammography multi-classification, the Hypersphere Multi-Class Support Vector Data Description (HSMC-SVDD) algorithm was proposed. The Hypersphere One-Class SVDD (HSOC-SVDD) was extended to a HSMC-SVDD as a kind of immediate multi-classification. Through extracting gray-level co-occurrence matrix features of mammography, then Kernel Principle Component Analysis (KPCA) was used to reduce dimension, finally HSMC-SVDD was used for classification. As each category trained only one HSOC-SVDD, its training speed was higher than that of the present multi-class classifiers. The experimental results show that compared with the combined classifier, in which the average train time is 40.2 seconds, proposed by Wei (WEI L Y, YANG Y Y, NISHIKAWA R M,et al.A study on several machine-learning methods for classification of malignant and benign clustered micro-calcifications. IEEE Transactions on Medical Imaging, 2005, 24(3): 371-380), the training time of HSMC-SVDD classifier is 21.369 seconds, the accuracy is up to 76.6929% and it is suitable for solving classification problems of many categories.

This paper proposed a hardware task partitioning algorithm according to the problems of communication cost minimum in reconfigurable computing, called DFGSP (Depth First Greedy Search Partitioning). At first, the front task was taken from the ready queue, a Directed Acyclic Graph (DAG), which was transformed from a computing-intensive task, was scanned and partitioned by Depth First Search (DFS). Then, the number of outputting-edges (quantized to communication cost) of current partitioning module was computed when the task node did not meet the area constraints. Finally, the ready task node, which considered sufficiently partitioning module outputting-edges which were not increasing and made good use of reconfigurable resources hardware fragment as soon as possible, was scanned and partitioned, after skipping the task node which did not meet the area constraints. In comparison with the Cluster-Based Partitioning (CBP) algorithm and Level Sensitive Cluster-Based Partitioning (LSCBP) algorithm, the experimental results show that the proposed algorithm can obtain the least number of partitioning modules and the least average number of input-output edges crossing modules, and the practical results indicate the proposed algorithm gets a prominent improvement in hardware task partitioning performance over previous algorithms, while the run-time efficiency is preserved.