Radiation exposure and the associated risk of cancer for patients in computed tomography (CT) scans have been major clinical concerns. The radiation exposure can be reduced effectively via lowering the x-ray tube current (mA). However, this strategy may lead to excessive noise and streak artifacts in the conventional filtered back-projection reconstructed images. To address this issue, some deep convolutional neural network (ConvNet) based approaches have been developed for low-dose CT imaging inspired by the recent development of machine learning. Nevertheless, some of the image textures reconstructed by the ConvNet could be corrupted by the severe streaks, especially in ultra-low-dose cases, which could be close to prostheses and hamper diagnosis. Therefore, in this work, we propose an iterative residual-artifact learning ConvNet (IRLNet) approach to improve the reconstruction performance over the ConvNet based approaches. Specifically, the proposed IRLNet estimates the high-frequency details within the noise and then removes them iteratively; after eliminating severe streaks in the low-dose CT images, the residual low-frequency details can be processed through the conventional network. Moreover, the proposed IRLNet scheme can be extended for robust handling of quantitative dual energy CT/cerebral perfusion CT imaging, and statistical iterative reconstruction. Real patient data are used to evaluate the proposed IRLNet, and the experimental results demonstrate that the proposed IRLNet approach outperforms the previous ConvNet based approaches in reducing the image noise and streak artifacts efficiently at the same time as preserving edge details well, suggesting that the proposed IRLNet approach can be used to improve the CT image quality, especially in ultra-low-dose cases.

Empirical studies on code require standardized datasets of significant size extracted from real-world programs in order to be reproducible and generalisable. We argue that there is a need for such data sets that are executable and can therefore be used for experiments using static and dynamic analysis. A harness for such a data set should have high coverage in order to facilitate the construction of comprehensive models of program execution.We present XCorpus, a set of 76 executable, real-world Java programs, including a subset of 70 programs from the Qualitas Corpus. XCorpus uses a harness that is a combination of built-in and generated test cases, resulting in a branch coverage that is significantly better than what is available from DaCapo.

No abstract

No abstract

No abstract