No abstract

Recent state-of-the-art image segmentation algorithms are mostly based on deep neural networks, thanks to their high performance and fast computation time. However, these methods are usually trained in a supervised manner, which requires large number of high quality ground-truth segmentation masks. On the other hand, classical image segmentation approaches such as level-set methods are formulated in a selfsupervised manner by minimizing energy functions such as Mumford-Shah functional, so they are still useful to help generation of segmentation masks without labels. Unfortunately, these algorithms are usually computationally expensive and often have limitation in semantic segmentation. In this paper, we propose a novel loss function based on Mumford-Shah functional that can be used in deep-learning based image segmentation without or with small labeled data. This loss function is based on the observation that the softmax layer of deep neural networks has striking similarity to the characteristic function in the Mumford-Shah functional. We show that the new loss function enables semisupervised and unsupervised segmentation. In addition, our loss function can be also used as a regularized function to enhance supervised semantic segmentation algorithms. Experimental results on multiple datasets demonstrate the effectiveness of the proposed method.

No abstract

Introduction Internet gaming disorder (IGD) and alcohol dependence (AD) have been reported to share clinical characteristics including craving and over-engagement despite negative consequences. However, there are also clinical factors that differ between individuals with IGD and those with AD in terms of chemical intoxication, prevalence age, and visual and auditory stimulation. Methods We assessed brain functional connectivity within the prefrontal, striatum, and temporal lobe in 15 patients with IGD and in 16 patients with AD. Symptoms of depression, anxiety, and the attention deficit hyperactivity disorder were assessed in patients with IGD and in patients with AD. Results Both AD and IGD subjects have positive functional connectivity between the dorsolateral prefrontal cortex (DLPFC), cingulate, and cerebellum. In addition, both groups have negative functional connectivity between the DLPFC and the orbitofrontal cortex. However, the AD subjects have positive functional connectivity between the DLPFC, temporal lobe and striatal areas while IGD subjects have negative functional connectivity between the DLPFC, temporal lobe and striatal areas. Conclusions AD and IGD subjects may share deficits in executive function, including problems with self-control and adaptive responding. However, the negative connectivity between the DLPFC and the striatal areas in IGD subjects, different from the connectivity observed in AD subjects, may be due to the earlier prevalence age, different comorbid diseases as well as visual and auditory stimulation.

Medical image registration is one of the key processing steps for biomedical image analysis such as cancer diagnosis. Recently, deep learning based supervised and unsupervised image registration methods have been extensively studied due to its excellent performance in spite of ultra-fast computational time compared to the classical approaches. In this paper, we present a novel unsupervised medical image registration method that trains deep neural network for deformable registration of 3D volumes using a cycle-consistency. Thanks to the cycle consistency, the proposed deep neural networks can take diverse pair of image data with severe deformation for accurate registration. Experimental results using multiphase liver CT images demonstrate that our method provides very precise 3D image registration within a few seconds, resulting in more accurate cancer size estimation.