To determine the prognostic value of cumulative calcification score of coronary artery calcification (CAC), thoracic aortic calcification (TAC) and aortic valve calcification (AVC) in acute ST ...segment elevation myocardial infarction (STEMI) patients.
This was a retrospective, single-center cohort study. A total of 332 STEMI patients who received primary percutaneous coronary intervention (PPCI) were enrolled in this study between January 2010 to October 2018. We assessed the calcification in the left anterior descending branch (LAD), left circumflex branch (LCX), right coronary artery (RCA), thoracic aorta, and aortic valve. Calcification of each part was counted as 1 point, and the cumulative calcification score was calculated as the sum of all points. The primary endpoint was all-cause mortality. Multivariate Cox proportional hazards models were used to determine association of cumulative calcification score with end points. The performance of the score was evaluated by receiver operating characteristic (ROC) curve analysis and absolute net reclassification improvement (NRI), compared with the Global Registry of Acute Coronary Events (GRACE) risk score.
The overall population's calcification score was 2.0 ± 1.6. During a mean follow-up time of 69.8 ± 29.3 months, the all-cause mortality rate was 12.1%. Kaplan-Meier curve showed that the score was significantly associated with mortality (log-rank p < 0.001). The multivariable Cox proportional hazard analyses showed that a calcification score of 4-5 was independently associated with all-cause death in STEMI patients hazard ratio (HR) = 2.32, 95% confidence interval (CI): 1.01-5.31, p = 0.046. The area under the ROC curve (AUC) of the calcification score was 0.67 (95% CI: 0.61-0.72), and the AUC of the GRACE score was 0.80 (95% CI: 0.75-0.84). There was no statistical difference in the predictive value between both scores for 3-year mortality in STEMI patients after PPCI (p = 0.06). Based on the NRI analysis, the calcification score showed better risk classification compared with the GRACE score (absolute NRI = 6.63%, P = 0.027).
The cumulative calcification score is independently associated with the long-term prognosis of STEMI patients after PPCI.
The golden cuttlefish (
) is an important cephalopod species with a lifespan of approximately one year. The species plays a crucial role in marine ecological support services and is commercially ...valuable in fisheries. In the seas around China, this species has emerged as the main target for cuttlefish fisheries, replacing
since the 1990s. Variations in oceanographic conditions associated with global warming could significantly impact the temporal-spatial distribution of the species. In this study, we performed bottom trawling surveys with four cruises during 2018-2019 in the East China Sea region to determine the current resource status and seasonal-spatial variations in
. We found that the average individual weight (AIW) values were 4.87 and 519.00 g/ind at stations located at 30.50° N, 124.00° E and 30.50° N, 124.50° E, respectively, with the aggregation of larvae and parent groups in spring. The species was not distributed north of 32.00° N in summer. The catch per unit effort by weight (CPUE
) value decreased in the order of 2772.50→2575.20→503.29→124.36 g/h, corresponding to latitudes of 34.50° N→34.00° N→33.50° N→32.50° N 121.50° E in autumn. The most suitable fishing areas were the south of the East China Sea region in spring; the south of the East China Sea region extending to the center and outer parts of the East China Sea region in summer; the south of the Yellow Sea close to the Haizhou Bay fishing ground and the forbidden fishing line region of the Lusi and Dasha fishing grounds in autumn; and the south and center of the East China Sea region in winter. The most suitable sea bottom temperature (SBT) values from spring to winter were 14.76-20.53 °C, 19.54-22.98 °C, 11.79-17.64 °C, and 16.94-20.36 °C, respectively. The most suitable sea bottom salinity (SBS) values were 31.53-34.80‱ in spring, 32.95-34.68‱ in summer, 31.51-34.77‱ in autumn, and 33.82-34.51‱ in winter. We concluded the following: (1) the southern and northern areas of the East China Sea region are spawning and nursery grounds, respectively, in spring; (2) the central distribution is located at a latitude of 28.00° N in autumn and winter; and (3) the southern area of the Yangtze River to the north is a spawning ground in spring, and the areas located at 29.00-34.50° N, 124.00-124.50° E, and 28.00-30.50° N, 125.50-126.50° E are nursery grounds. The results of this study provide useful guidance for appropriate fisheries management, thereby avoiding a collapse in the
population, which has been experienced in other species in this area.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Knowledge amalgamation (KA) is a novel deep model reusing task aiming to transfer knowledge from several well-trained teachers to a multi-talented and compact student. Currently, most of these ...approaches are tailored for convolutional neural networks (CNNs). However, there is a tendency that Transformers, with a completely different architecture, are starting to challenge the domination of CNNs in many computer vision tasks. Nevertheless, directly applying the previous KA methods to Transformers leads to severe performance degradation. In this work, we explore a more effective KA scheme for Transformer-based object detection models. Specifically, considering the architecture characteristics of Transformers, we propose to dissolve the KA into two aspects: sequence-level amalgamation (SA) and task-level amalgamation (TA). In particular, a hint is generated within the sequence-level amalgamation by concatenating teacher sequences instead of redundantly aggregating them to a fixed-size one as previous KA approaches. Besides, the student learns heterogeneous detection tasks through soft targets with efficiency in the task-level amalgamation. Extensive experiments on PASCAL VOC and COCO have unfolded that the sequence-level amalgamation significantly boosts the performance of students, while the previous methods impair the students. Moreover, the Transformer-based students excel in learning amalgamated knowledge, as they have mastered heterogeneous detection tasks rapidly and achieved superior or at least comparable performance to those of the teachers in their specializations.
In this study, the complete mitochondrial genome of the Taiwan tai Argyrops bleekeri was determined for the first time by next-generation sequencing. The circular mtDNA molecule was 16,646 bp in size ...and the overall base composition was A (27.77%), C (28.95%), G (16.60%), and T (26.68%), with a slight bias toward A + T. The complete mitogenome encoded 13 protein-coding genes (PCGs), 22 tRNA genes, two rRNA genes, and a control region. Phylogenetic analysis based on the 13 PCGs of the Sparidae family revealed that Argyrops appears to be most closely related to Pagrus and Parargyrops, but further research is needed.
Object detection is one of the core tasks in computer vision that serves as a crucial underpinning for numerous applications. In recent years, deep learning-based methods have achieved remarkable ...performance in object detection. However, the performance of small objects still remains unsatisfactory. Therefore, some specific architectures have been proposed to address this issue in certain areas, such as remote-sensing and UAV images. In this paper, we aim to design a pluggable and non-intrusive method, termed as PatchDetector, to improve the performance of small object detection, which can effectively avoid the time and resource overhead of retraining the entire network. To achieve that, we first analyze why the mainstream networks perform poorly on small objects and find out that the fundamental reason is that the features of small are superseded by the background, which leads to a significant semantic gap in multi-level layers. Then, significance analysis is conducted to find the essential features for improving the small object detection. Next, with the located significant features, we devise a pluggable patch network for extracting essential features for small objects, which is non-intrusive to the original network. Experiments on mainstream detectors, including YOLO series and Faster RCNN, show that the proposed PatchDetector achieves 0.4%∼2.0% mAP on small objects while not compromising the performance of medium and large objects.
•The first pluggable and non-intrusive patch for small object detection performance.•We analyze the small object poor performance and locate the essential features.•Experiments demonstrate that the PatchDetector achieves 0.4%∼2.0% mAP on small object.
Researchers of temporal networks (e.g., social networks and transaction networks) have been interested in mining dynamic patterns of nodes from their diverse interactions. Inspired by recently ...powerful graph mining methods like skip-gram models and graph neural networks (GNNs), existing approaches focus on generating temporal node embeddings sequentially with nodes' sequential interactions. However, the sequential modeling of previous approaches cannot handles the transition structure between nodes' neighbors with limited memorization capacity. In detail, an effective method for the transition structures is required to both model nodes' personalized patterns adaptively and capture node dynamics accordingly. In this article, we propose a method, namely t ransition p ropagation g raph n eural n etworks (TIP-GNN), to tackle the challenges of encoding nodes' transition structures. The proposed TIP-GNN focuses on the bilevel graph structure in temporal networks: besides the explicit interaction graph, a node's sequential interactions can also be constructed as a transition graph. Based on the bilevel graph, TIP-GNN further encodes transition structures by multistep transition propagation and distills information from neighborhoods by a bilevel graph convolution. Experimental results over various temporal networks reveal the efficiency of our TIP-GNN, with at most 7.2% improvements of accuracy on temporal link prediction. Extensive ablation studies further verify the effectiveness and limitations of the transition propagation module. Our code is available at https://github.com/doujiang-zheng/TIP-GNN .
Background
Microvascular invasion (MVI) is an independent prognostic factor that is associated with early recurrence and poor survival after resection of hepatocellular carcinoma (HCC). However, the ...traditional pathology approach is relatively subjective, time‐consuming, and heterogeneous in the diagnosis of MVI. The aim of this study was to develop a deep‐learning model that could significantly improve the efficiency and accuracy of MVI diagnosis.
Materials and Methods
We collected H&E‐stained slides from 753 patients with HCC at the First Affiliated Hospital of Zhejiang University. An external validation set with 358 patients was selected from The Cancer Genome Atlas database. The deep‐learning model was trained by simulating the method used by pathologists to diagnose MVI. Model performance was evaluated with accuracy, precision, recall, F1 score, and the area under the receiver operating characteristic curve.
Results
We successfully developed a MVI artificial intelligence diagnostic model (MVI‐AIDM) which achieved an accuracy of 94.25% in the independent external validation set. The MVI positive detection rate of MVI‐AIDM was significantly higher than the results of pathologists. Visualization results demonstrated the recognition of micro MVIs that were difficult to differentiate by the traditional pathology. Additionally, the model provided automatic quantification of the number of cancer cells and spatial information regarding MVI.
Conclusions
We developed a deep learning diagnostic model, which performed well and improved the efficiency and accuracy of MVI diagnosis. The model provided spatial information of MVI that was essential to accurately predict HCC recurrence after surgery.
Since the 1990s, the golden cuttlefish (Sepia esculenta) has become the dominant cuttlefish fisheries target in the seas around China. In this paper, we aim to determine the current resource status ...and spatio-seasonal variation in the population in the East China Sea region. We found more juveniles at latitudes of 27.50–28.00° N and 29.00° N and more subadult individuals at 28.50° N in autumn, exhibiting different growth rates and resource densities. In addition, we found the majority of the catches were composed of parent groups in spring, while in autumn, the majority of the catches were composed of juvenile groups. We concluded that the subadult groups might have dispersed widely for feeding and growth along the latitude of 30.00° N and to the south in summer, and the southern area of the Yangtze River extending north was the spawning ground in spring. The groups of S. esculenta preferred to stay in areas with a stable water temperature of ~20.00 °C, and many S. esculenta juveniles might have adapted to endure the negative influence of the low oxygen content in summer. The depth range of the S. esculenta population was 10.00–133.00 m from spring to autumn, but this shrank to 66.00–107.00 m in winter. The golden cuttlefish (Sepia esculenta) is an important cephalopod species with a lifespan of approximately one year. The species plays a crucial role in marine ecological support services and is commercially valuable in fisheries. In the seas around China, this species has emerged as the main target for cuttlefish fisheries, replacing Sepiella maindroni since the 1990s. Variations in oceanographic conditions associated with global warming could significantly impact the temporal-spatial distribution of the species. In this study, we performed bottom trawling surveys with four cruises during 2018–2019 in the East China Sea region to determine the current resource status and seasonal-spatial variations in S. esculenta. We found that the average individual weight (AIW) values were 4.87 and 519.00 g/ind at stations located at 30.50° N, 124.00° E and 30.50° N, 124.50° E, respectively, with the aggregation of larvae and parent groups in spring. The species was not distributed north of 32.00° N in summer. The catch per unit effort by weight (CPUEsub.w) value decreased in the order of 2772.50→2575.20→503.29→124.36 g/h, corresponding to latitudes of 34.50° N→34.00° N→33.50° N→32.50° N 121.50° E in autumn. The most suitable fishing areas were the south of the East China Sea region in spring; the south of the East China Sea region extending to the center and outer parts of the East China Sea region in summer; the south of the Yellow Sea close to the Haizhou Bay fishing ground and the forbidden fishing line region of the Lusi and Dasha fishing grounds in autumn; and the south and center of the East China Sea region in winter. The most suitable sea bottom temperature (SBT) values from spring to winter were 14.76–20.53 °C, 19.54–22.98 °C, 11.79–17.64 °C, and 16.94–20.36 °C, respectively. The most suitable sea bottom salinity (SBS) values were 31.53–34.80‰ in spring, 32.95–34.68‰ in summer, 31.51–34.77‰ in autumn, and 33.82–34.51‰ in winter. We concluded the following: (1) the southern and northern areas of the East China Sea region are spawning and nursery grounds, respectively, in spring; (2) the central distribution is located at a latitude of 28.00° N in autumn and winter; and (3) the southern area of the Yangtze River to the north is a spawning ground in spring, and the areas located at 29.00–34.50° N, 124.00–124.50° E, and 28.00–30.50° N, 125.50–126.50° E are nursery grounds. The results of this study provide useful guidance for appropriate fisheries management, thereby avoiding a collapse in the S. esculenta population, which has been experienced in other species in this area.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UILJ, UKNU, UL, UM, UPUK
Recently, many benchmark datasets have been found to contain noisy labels caused by unavoidable human mistakes. Many researchers propose new noise-aware loss functions to achieve robust ...classification performance. However, we discover that existing noise-aware loss functions cannot fully heal the damage caused by the noise. On the other hand, some methods filter out low confidence samples and train new models, whereas the filtered samples contain both noisy and hard samples that are critical for the robustness of models. Based on the above two discoveries, we devised the Noise-aware Network (NA-Net) for robust training with noisy labels. Each layer of NA-Net contains three groups of convolution kernels responsible for mix samples, clean samples, and noisy samples, termed as mix-kernels, clean-kernels, and noise-kernels, respectively. Mix-kernels are used for finding the clean samples with a newly devised noise-immune (NI) loss function; clean-kernels are targeted at learning better features without being misguided by noise; noise-kernels are trained by the remaining samples to rectify wrong labels for the next iteration. Meanwhile, for increasing the classification performance of mix-kernels, the extracted feature maps of clean-kernels without being poisoned are combined as the input of mix-kernels of the next layer. Also, the knowledge distillation strategy is adopted to distill the knowledge from clean-kernels to the noise-kernels. Extensive experiments demonstrate that the mutual promotion of three groups of kernels in NA-Net achieves state-of-the-art performance on both artificial noisy datasets and real-world datasets.
•The first to clarify the influence extent of noisy and hard samples for training.•Noise-aware Network with separate groups of kernels is proposed for handling noise.•A new loss function is proposed to make the training robust to the noise.
Understanding the connectivity in estuarine waters is important for sustainable fisheries management and safeguarding of estuarine ecological environments. Knowledge regarding the functional ...connectivity for some “estuarine opportunist” fish species between the Yangtze River estuary (YRE) and its adjacent coastal waters is still scarce. We investigated the connectivity for an exploited sciaenid, the small yellow croaker (
Larimichthys polyactis
), using otolith elemental composition. In 2020, 115 juveniles were collected in four putative habitat patches, and elemental fingerprints (strontium, barium, magnesium, manganese) of the otolith margin were used to determine spatial differentiation. The results indicated that multi-elemental fingerprints had limited efficacy in identifying habitat patches at a fine spatial scale. However, an elevated Ba/Ca ratio proved to be effective in identifying the presence of
L. polyactis
in the YRE, which was found to be 12.5 ± 0.7 µmol/mol. In 2021, 51 adult fish were collected from the Lvsi fishing grounds, and the core-to-edge Ba/Ca profiles of the adult fish were analyzed to evaluate the connectivity in the YRE and its adjacent waters. Among the specimens examined, 41% exhibited a life history associated with estuarine habitats. In addition, among the fish with estuarine life history, 72% of the estuarine life history occurred during the juvenile stage, and almost none at the larval stage. The functional connectivity of
L. polyactis
in estuarine habitats is conspicuous and closely linked to ontogeny. This study emphasizes the need to incorporate the concept of functional connectivity for a more comprehensive understanding of estuarine ecosystems. Furthermore, it highlights the significance of estuaries for “estuarine opportunist” fish, warranting increased attention and research.
