Looking at Boundary: Siamese Densely Cooperative Fusion for Salient Object Detection.

Though deep learning-based saliency detection methods have achieved gratifying performance recently, the predicted saliency maps still suffer from the boundary challenge. From the perspective of foreground-background separation, this article attempts to extract the edge information of objects by exploiting the difference between different color channels in the RGB color space and establishes a novel multicolor contrast extraction (MCE) mechanism to improve the learning ability of exquisite boundary information of the network. To make full use of the MCE outputs and RGB colors, and well depict and capture the complementary information between them, we devise a novel Siamese densely cooperative fusion (DCF) network (SDFNet) for saliency detection, which consists of two effective components: boundary-directed feature learning (BDFL) and DCF. The BDFL provides joint learning for both MCE and RGB modalities through a Siamese network, while the DCF module is devised for complementary feature discovery, in order to effectively combine the features learned from two modalities. Experiments on five well-known benchmark datasets demonstrate that the proposed method outperforms the state-of-the-art approaches in terms of different evaluation metrics. We provide a detailed analysis of these results and indicate that our joint modeling of MCE and RGB colors helps to better capture the object details, especially in the object boundaries.

Complementarity-Aware Attention Network for Salient Object Detection.

In this article, we tackle the saliency detection task from an interesting perspective: we focus both on salient regions (or foreground) detection and nonsalient regions (or background) detection instead of only the foreground and propose a novel complementarity-aware attention network. It is a unified framework with two branches, namely, positive attention module (PAM) and negative attention module (NAM), for the foreground and background detection, respectively. More specifically, the PAM exploits a position self-attention mechanism to enhance the discriminant ability of feature representation, which can detect most of the salient object regions. Meanwhile, the NAM is designed to detect the background regions, aiming to pop out the missing object parts and details in the prediction map produced by the PAM. By fusing these two attention modules together, NAM can provide complementary cues to assist PAM for precise object detection. Furthermore, in order to capture more multiscale contextual information, we introduce a bidirectional structure with multisupervision to the proposed complementarity-aware attention module for performance improvement. Experiments on five benchmark datasets show that the proposed framework achieves comparable results compared with the state-of-the-art saliency detection methods.

Moxibustion for diarrhea in children: A protocol for systematic review and meta-analysis.

BACKGROUND: Infantile Diarrhea is a common and frequent digestive tract disease in children. The causes of this disease are relatively complex and the onset time is relatively long. At present, there is no specific treatment method in Western medicine. Moxibustion is a simple and painless external treatment. However, due to the lack of high-quality evidence to support the effectiveness and safety of moxibustion therapy for pediatric diarrhea. Therefore, the purpose of this study is to verify the effectiveness and safety of moxibustion in the treatment of pediatric diarrhea. METHODS: We will use PubMed, Cochrane Library, Wan Fang Database, Web of Science, China National Knowledge Infrastructure Database, Chinese Science Journal Database, China Biomedical Literature Database to carry out a progressive search of diseases. The study will be screened according to eligibility criteria, and quality of the study will be assessed by using the Cochrane Risk of Bias Tool. RESULTS: Through this study, we will systematically evaluate the effectiveness and safety of moxibustion in the treatment of pediatric diarrhea. CONCLUSION: The results of this study will provide reliable evidence of the safety and effectiveness of moxibustion in the treatment of infantile diarrhea, and provide a therapeutic basis for the future clinical application. ETHICS AND DISSEMINATION: Since this paper does not involve ethical issues, it does not need to pass the review of the ethics committee. It can only collect relevant literature and study. INPLASY REGISTRATION NUMBER: INPLASY202130091.

Efficacy and safety of moxibustion in the treatment of cancer-related fatigue: A protocol for systematic review and meta-analysis.

BACKGROUND: Cancer-related fatigue, a common symptom of cancer patients caused by the interaction of multiple factors, runs through the whole process of tumorigenesis, development, treatment, and prognosis. The main clinical manifestations are weakness, tiredness, exhaustion, fatigue, or slow movement, heavy limbs, low mood or irritability, sleep disturbance or lethargy, lack of attention, etc. CRF is different from the fatigue after daily body fatigue. It has no obvious relief or relief after rest or sleep, and exists for a long time in the relevant treatment and rehabilitation process. It seriously affects the physiological, psychological and social functions of patients, and reduces the quality of life of patients. Moxibustion therapy has shown strong advantages in the treatment of CRF, and the curative effect is accurate. Therefore, this paper will carry out a systematic evaluation and meta analysis of the efficacy and safety of moxibustion in the treatment of CRF. METHODS: we will searching 8 electronic databases, including PubMed, Embase, Web of Science, Cochrane Library, the China National Knowledge Infrastructure, Chinese Science and Technology Periodical Database, Wanfang Database, and Chinese Biomedical Literature Database. We will search above electronic databases from the beginning to January 2021, without any language restriction. Clinical efficacy, including total effective rate or cure rate, clinical symptom integral, and recurrence rate will be accepted as the primary outcomes. The fatigue scale score, quality of life improvement rate will be used as secondary outcomes. RevMan 5.3 software will be used for statistical analysis. The result about the curative effect and safety of moxibustion for cancer-related fatigue will be presented as risk ratio for dichotomous data and mean differences with a 95% confidence interval for continuous data. RESULTS: When this research program is completed, the relevant results can be obtained. CONCLUSIONS: The results of this study will provide reliable evidence for the efficacy and safety of moxibustion in the treatment of cancer-related fatigue. ETHICS AND DISSEMINATION: This article does not need to pass the ethics committee review, because this article does not involve the ethics question, only collates the related literature research. INPLASY REGISTRATION NUMBER: INPLASY202110072.