Existing computational models for salient object detection primarily rely on hand-crafted features, which are only able to capture low-level contrast information. In this paper, we learn the ...hierarchical contrast features by formulating salient object detection as a binary labeling problem using deep learning techniques. A novel superpixelwise convolutional neural network approach, called SuperCNN, is proposed to learn the internal representations of saliency in an efficient manner. In contrast to the classical convolutional networks, SuperCNN has four main properties. First, the proposed method is able to learn the hierarchical contrast features, as it is fed by two meaningful superpixel sequences, which is much more effective for detecting salient regions than feeding raw image pixels. Second, as SuperCNN recovers the contextual information among superpixels, it enables large context to be involved in the analysis efficiently. Third, benefiting from the superpixelwise mechanism, the required number of predictions for a densely labeled map is hugely reduced. Fourth, saliency can be detected independent of region size by utilizing a multiscale network structure. Experiments show that SuperCNN can robustly detect salient objects and outperforms the state-of-the-art methods on three benchmark datasets.
The SARS-CoV-2 Omicron variant has demonstrated enhanced transmissibility and escape of vaccine-derived immunity. Although first-generation vaccines remain effective against severe disease and death, ...robust evidence on vaccine effectiveness (VE) against all Omicron infections, irrespective of symptoms, remains sparse. We used a community-wide serosurvey with 5,310 subjects to estimate how vaccination histories modulated risk of infection in infection-naive Hong Kong during a large wave of Omicron BA.2 epidemic in January-July 2022. We estimated that Omicron infected 45% (41-48%) of the local population. Three and four doses of BNT162b2 or CoronaVac were effective against Omicron infection 7 days after vaccination (VE of 48% (95% credible interval 34-64%) and 69% (46-98%) for three and four doses of BNT162b2, respectively; VE of 30% (1-66%) and 56% (6-97%) for three and four doses of CoronaVac, respectively). At 100 days after immunization, VE waned to 26% (7-41%) and 35% (10-71%) for three and four doses of BNT162b2, and to 6% (0-29%) and 11% (0-54%) for three and four doses of CoronaVac. The rapid waning of VE against infection conferred by first-generation vaccines and an increasingly complex viral evolutionary landscape highlight the necessity for rapidly deploying updated vaccines followed by vigilant monitoring of VE.
Background Current practice of adding concurrent–adjuvant chemotherapy to radiotherapy (CRT) for treating advanced nasopharyngeal carcinoma is based on the Intergroup-0099 Study published in 1998. ...However, the outcome for the radiotherapy-alone (RT) group in that trial was substantially poorer than those in other trials, and there were no data on late toxicities. Verification of the long-term therapeutic index of this regimen is needed. Methods Patients with nonkeratinizing nasopharyngeal carcinoma staged T1-4N2-3M0 were randomly assigned to RT (176 patients) or to CRT (172 patients) using cisplatin (100 mg/m2) every 3 weeks for three cycles in concurrence with radiotherapy, followed by cisplatin (80 mg/m2) plus fluorouracil (1000 mg per m2 per day for 4 days) every 4 weeks for three cycles. Primary endpoints included overall failure-free rate (FFR) (the time to first failure at any site) and progression-free survival. Secondary endpoints included overall survival, locoregional FFR, distant FFR, and acute and late toxicity rates. All statistical tests were two-sided. Results The two treatment groups were well balanced in all patient characteristics, tumor factors, and radiotherapy parameters. Adding chemotherapy statistically significantly improved the 5-year FFR (CRT vs RT: 67% vs 55%; P = .014) and 5-year progression-free survival (CRT vs RT: 62% vs 53%; P = .035). Cumulative incidence of acute toxicity increased with chemotherapy by 30% (CRT vs RT: 83% vs 53%; P < .001), but the 5-year late toxicity rate did not increase statistically significantly (CRT vs RT: 30% vs 24%; P = .30). Deaths because of disease progression were reduced statistically significantly by 14% (CRT vs RT: 38% vs 24%; P = .008), but 5-year overall survival was similar (CRT vs RT: 68% vs 64%; P = .22; hazard ratio of CRT = 0.81, 95% confidence interval = 0.58 to 1.13) because deaths due to toxicity or incidental causes increased by 7% (CRT vs RT: 1.7% vs 0, and 8.1% vs 3.4%, respectively; P = .015). Conclusions Adding concurrent–adjuvant chemotherapy statistically significantly reduced failure and cancer-specific deaths when compared with radiotherapy alone. Although there was no statistically significant increase in major late toxicity, increase in noncancer deaths narrowed the resultant gain in overall survival.
Alzheimer's disease (AD), Parkinson's disease (PD), and amyotrophic lateral sclerosis with associated frontotemporal dementia (ALS/FTD) are major neurodegenerative diseases for which there are no ...cures. All are characterised by damage to several seemingly disparate cellular processes. The broad nature of this damage makes understanding pathogenic mechanisms and devising new treatments difficult. Can the different damaged functions be linked together in a common disease pathway and which damaged function should be targeted for therapy? Many functions damaged in neurodegenerative diseases are regulated by communications that mitochondria make with a specialised region of the endoplasmic reticulum (ER; mitochondria-associated ER membranes or ‘MAM’). Moreover, several recent studies have shown that disturbances to ER–mitochondria contacts occur in neurodegenerative diseases. Here, we review these findings.
Thioamides antithyroid‐drugs (ATDs) are important in hyperthyroid disease management. Identification of the susceptibility locus of ATD‐induced agranulocytosis is important for clinical management. ...We performed a genome‐wide association study (GWAS) involving 20 patients with ATD‐induced agranulocytosis and 775 healthy controls. The top finding was further replicated. A single‐nucleotide polymorphism (SNP), rs185386680, showed the strongest association with ATD‐induced agranulocytosis in GWAS (odds ratio (OR) = 36.4; 95% confidence interval (CI) = 12.8–103.7; P = 1.3 × 10‐24) and replication (OR = 37; 95% CI = 3.7–367.4; P = 9.6 × 10‐7). HLA‐B*38:02:01 was in complete linkage disequilibrium with rs185386680. High‐resolution HLA typing confirmed that HLA‐B*38:02:01 was associated with carbimazole (CMZ)/methimazole (MMI)‐induced agranulocytosis (OR = 265.5; 95% CI = 27.9–2528.0; P = 2.5 × 10‐14), but not associated with propylthiouracil (PTU). The positive and negative predictive values of HLA‐B*38:02:01 in predicting CMZ/MMI‐induced agranulocytosis were 0.07 and 0.999. Approximately 211 cases need to be screened to prevent one case. Screening for the risk allele will be useful in preventing agranulocytosis in populations in which the frequency of the risk allele is high.
Cordyceps sinensis, a well-known traditional Chinese medicine, possesses activities in anti-tumor, anti-oxidation and stimulating the immune response; however, the identity of active component(s) is ...not determined. A strain of Cordyceps sinensis, namely UST 2000, has been isolated. By using activity-guided purification, a novel polysaccharide of molecular weight ∼82kDa was isolated from the conditioned medium of cultured Cordyceps. The isolated exo-polysaccharide, namely cordysinocan, contains glucose, mannose, galactose in a ratio of 2.4:2:1. In cultured T-lymphocytes, application of cordysinocan induced the cell proliferation and the secretion of interleukin-2, interleukin-6 and interleukin-8. In addition, the phosphorylation of extracellular signal-regulated kinases (ERK) was induced transiently by the treatment of cordysinocan. Moreover, application of cordysinocan in cultured macrophages increased the phagocytosis activity and the enzymatic activity of acid phosphatase. These results therefore verify the important role of Cordyceps polysaccharide in triggering such immune responses.
Synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) exposures in dynamic scenes is challenging. There are two major problems caused by the large motions of foreground ...objects. One is the severe misalignment among the LDR images. The other is the missing content due to the over-/under-saturated regions caused by the moving objects, which may not be easily compensated for by the multiple LDR exposures. Thus, it requires the HDR generation model to be able to properly fuse the LDR images and restore the missing details without introducing artifacts. To address these two problems, we propose in this paper a novel GAN-based model, HDR-GAN , for synthesizing HDR images from multi-exposed LDR images. To our best knowledge, this work is the first GAN-based approach for fusing multi-exposed LDR images for HDR reconstruction. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content. In addition, we also propose a novel generator network, with a reference-based residual merging block for aligning large object motions in the feature domain, and a deep HDR supervision scheme for eliminating artifacts of the reconstructed HDR images. Experimental results demonstrate that our model achieves state-of-the-art reconstruction performance over the prior HDR methods on diverse scenes.
Image decolorization is a fundamental problem for many real-world applications, including monochrome printing and photograph rendering. In this paper, we propose a new color-to-gray conversion method ...that is based on a region-based saliency model. First, we construct a parametric color-to-gray mapping function based on global color information as well as local contrast. Second, we propose a region-based saliency model that computes visual contrast among pixel regions. Third, we minimize the salience difference between the original color image and the output grayscale image in order to preserve contrast discrimination. To evaluate the performance of the proposed method in preserving contrast in complex scenarios, we have constructed a new decolorization data set with 22 images, each of which contains abundant colors and patterns. Extensive experimental evaluations on the existing and the new data sets show that the proposed method outperforms the state-of-the-art methods quantitatively and qualitatively.
Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to the SID problem. Although weak ...supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, it is non-trivial to use only class labels to learn instance-aware saliency information, as salient instances with high semantic affinities may not be easily separated by the labels. As the subitizing information provides an instant judgement on the number of salient items, it is naturally related to detecting salient instances and may help separate instances of the same class while grouping different parts of the same instance. Inspired by this observation, we propose to use class and subitizing labels as weak supervision for the SID problem. We propose a novel weakly-supervised network with three branches: a Saliency Detection Branch leveraging class consistency information to locate candidate objects; a Boundary Detection Branch exploiting class discrepancy information to delineate object boundaries; and a Centroid Detection Branch using subitizing information to detect salient instance centroids. This complementary information is then fused to produce a salient instance map. To facilitate the learning process, we further propose a progressive training scheme to reduce label noise and the corresponding noise learned by the model, via reciprocating the model with progressive salient instance prediction and model refreshing. Our extensive evaluations show that the proposed method plays favorably against carefully designed baseline methods adapted from related tasks.
PDF
