Purpose: Due to the potential risk of inducing cancer, radiation exposure by X-ray CT devices should be reduced for routine patient scanning. However, in low-dose X-ray CT, severe artifacts typically occur due to photon starvation, beam hardening, and other causes, all of which decrease the reliability of the diagnosis. Thus, a high-quality reconstruction method from low-dose X-ray CT data has become a major research topic in the CT community. Conventional model-based de-noising approaches are, however, computationally very expensive, and image-domain de-noising approaches cannot readily remove CT-specific noise patterns. To tackle these problems, we want to develop a new low-dose X-ray CT algorithm based on a deep-learning approach. Method: We propose an algorithm which uses a deep convolutional neural network (CNN) which is applied to the wavelet transform coefficients of low-dose CT images. More specifically, using a directional wavelet transform to extract the directional component of artifacts and exploit the intra-and inter-band correlations, our deep network can effectively suppress CT-specific noise. In addition, our CNN is designed with a residual learning architecture for faster network training and better performance. Results: Experimental results confirm that the proposed algorithm effectively removes complex noise patterns from CT images derived from a reduced X-ray dose. In addition, we show that the wavelet-domain CNN is efficient when used to remove noise from low-dose CT compared to existing approaches. Our results were rigorously evaluated by several radiologists at the Mayo Clinic and won second place at the 2016 "Low-Dose CT Grand Challenge." Conclusions: To the best of our knowledge, this work is the first deep-learning architecture for lowdose CT reconstruction which has been rigorously evaluated and proven to be effective. In addition, the proposed algorithm, in contrast to existing model-based iterative reconstruction (MBIR) methods, has considerable potential to benefit from large data sets. Therefore, we believe that the proposed algorithm opens a new direction in the area of low-dose CT research.

Functional imaging studies have examined which brain regions respond to emotional stimuli, but they have not determined how stable personality traits moderate such brain activation. Two personality traits, extraversion and neuroticism, are strongly associated with emotional experience and may thus moderate brain reactivity to emotional stimuli. The present study used functional magnetic resonance imaging to directly test whether individual differences in brain reactivity to emotional stimuli are correlated with extraversion and neuroticism in healthy women. Extraversion was correlated with brain reactivity to positive stimuli in localized brain regions, and neuroticism was correlated with brain reactivity to negative stimuli in localized brain regions. This study provides direct evidence that personality is associated with brain reactivity to emotional stimuli and identifies both common and distinct brain regions where such modulation takes place.

Model-based iterative reconstruction algorithms for low-dose X-ray computed tomography (CT) are computationally expensive. To address this problem, we recently proposed a deep convolutional neural network (CNN) for low-dose X-ray CT and won the second place in 2016 AAPM Low-Dose CT Grand Challenge. However, some of the textures were not fully recovered. To address this problem, here we propose a novel framelet-based denoising algorithm using wavelet residual network which synergistically combines the expressive power of deep learning and the performance guarantee from the framelet-based denoising algorithms. The new algorithms were inspired by the recent interpretation of the deep CNN as a cascaded convolution framelet signal representation. Extensive experimental results confirm that the proposed networks have significantly improved performance and preserve the detail texture of the original images.

The functional status of central neural pathways, in particular their susceptibility to plasticity and functional reorganization, may influence speech performance of deaf cochlear implant users. In this paper, we sought to determine how brain metabolic activity measured before implantation relates to cochlear implantation outcome, that is, speech perception. In 22 prelingually deaf children between 1 and 11 years, we correlated preoperative glucose metabolism as measured by F-18 fluorodeoxyglucose positron emission tomography with individual speech perception performance assessed 3 years after implantation, while factoring out the confounding effect of age at implantation. Whereas age at implantation was positively correlated with increased activity in the right superior temporal gyrus, speech scores were selectively associated with enhanced metabolic activity in the left prefrontal cortex and decreased metabolic activity in right Heschl's gyrus and in the posterior superior temporal sulcus. These results reinforce the notion that implantation should be performed as early as possible to prevent cross-modal takeover of auditory regions and suggest that rehabilitation strategies may be more efficient if they capitalize on general cognitive functions instead of only targeting specialized circuits dedicated to auditory and audiovisual pattern recognition.