Public Datasets Research Articles

Detection and severity assessment of obstructive sleep apnea according to deep learning of single-lead electrocardiogram signals.

Developing a convenient detection method is important for diagnosing and treating obstructive sleep apnea. Considering availability and medical reliability, we established a deep-learning model that uses single-lead electrocardiogram signals for obstructive sleep apnea detection and severity assessment. The detection model consisted of signal preprocessing, feature extraction, time-frequency domain information fusion, and classification segments. A total of 375 patients who underwent polysomnography were included. The single-lead electrocardiogram signals obtained by polysomnography were used to train, validate and test the model. Moreover, the proposed model performance on a public dataset was compared with the findings of previous studies. In the test set, the accuracy of per-segment and per-recording detection were 82.55% and 85.33%, respectively. The accuracy values for mild, moderate and severe obstructive sleep apnea were 69.33%, 74.67% and 85.33%, respectively. In the public dataset, the accuracy of per-segment detection was 91.66%. A Bland-Altman plot revealed the consistency of true apnea-hypopnea index and predicted apnea-hypopnea index. We confirmed the feasibility of single-lead electrocardiogram signals and deep-learning model for obstructive sleep apnea detection and severity evaluation in both hospital and public datasets. The detection performance is high for patients with obstructive sleep apnea, especially those with severe obstructive sleep apnea.

Neurostructural subgroup in 4291 individuals with schizophrenia identified using the subtype and stage inference algorithm

Machine learning can be used to define subtypes of psychiatric conditions based on shared biological foundations of mental disorders. Here we analyzed cross-sectional brain images from 4,222 individuals with schizophrenia and 7038 healthy subjects pooled across 41 international cohorts from the ENIGMA, non-ENIGMA cohorts and public datasets. Using the Subtype and Stage Inference (SuStaIn) algorithm, we identify two distinct neurostructural subgroups by mapping the spatial and temporal ‘trajectory’ of gray matter change in schizophrenia. Subgroup 1 was characterized by an early cortical-predominant loss with enlarged striatum, whereas subgroup 2 displayed an early subcortical-predominant loss in the hippocampus, striatum and other subcortical regions. We confirmed the reproducibility of the two neurostructural subtypes across various sample sites, including Europe, North America and East Asia. This imaging-based taxonomy holds the potential to identify individuals with shared neurobiological attributes, thereby suggesting the viability of redefining existing disorder constructs based on biological factors.

Combining unsupervised constraints on weakly supervised semantic segmentation of skin cancer.

Precise segmentation for skin cancer lesions at different stages is conducive to early detection and further treatment. Considering the huge cost of obtaining pixel-perfect annotations for this task, segmentation using less expensive image-level labels has become a research direction. Most image-level label weakly supervised segmentation uses class activation mapping (CAM) methods. A common consequence of this method is incomplete foreground segmentation, insufficient segmentation, or false negatives. At the same time, when performing weakly supervised segmentation of skin cancer lesions, ulcers, redness, and swelling may appear near the segmented areas of individual disease categories. This co-occurrence problem affects the model's accuracy in segmenting class-related tissue boundaries to a certain extent. The above two issues are determined by the loosely constrained nature of image-level labels that penalize the entire image space. Therefore, providing pixel-level constraints for weak supervision of image-level labels is the key to improving performance. To solve the above problems, this paper proposes a joint unsupervised constraint-assisted weakly supervised segmentation model(UCA-WSS). The weakly supervised part of the model adopts a dual-branch adversarial erasure mechanism to generate higher-quality CAM. The unsupervised part uses contrastive learning and clustering algorithms to generate foreground labels and fine boundary labels to assist segmentation and solve common co-occurrence problems in weakly supervised skin cancer lesion segmentation through unsupervised constraints. The model proposed in the article is evaluated comparatively with other related models on some public dermatology data sets. Experimental results show that our model performs better on the skin cancer segmentation task than other weakly supervised segmentation models, showing the potential of combining unsupervised constraint methods on weakly supervised segmentation.

Enhancing local representation learning through global–local integration with functional connectivity for EEG-based emotion recognition

Emotion recognition based on electroencephalogram (EEG) signals is crucial in understanding human affective states. Current research has limitations in extracting local features. The representation capabilities of local features are limited, making it difficult to comprehensively capture emotional information. In this study, a novel approach is proposed to enhance local representation learning through global–local integration with functional connectivity for EEG-based emotion recognition. By leveraging the functional connectivity of brain regions, EEG signals are divided into global embeddings that represent comprehensive brain connectivity patterns throughout the entire process and local embeddings that reflect dynamic interactions within specific brain functional networks at particular moments. Firstly, a convolutional feature extraction branch based on the residual network is designed to extract local features from the global embedding. To further improve the representation ability and accuracy of local features, a multidimensional collaborative attention (MCA) module is introduced. Secondly, the local features and patch embedded local embeddings are integrated into the feature coupling module (FCM), which utilizes hierarchical connections and enhanced cross-attention to couple region-level features, thereby enhancing local representation learning. Experimental results on three public datasets show that compared with other methods, this method improves accuracy by 4.92% on the DEAP, by 1.11% on the SEED, and by 7.76% on the SEED-IV, demonstrating its superior performance in emotion recognition tasks.

Detection and mitigation of DDoS attacks based on multi-dimensional characteristics in SDN

Due to the large computational overhead, underutilization of features, and high bandwidth consumption in traditional SDN environments for DDoS attack detection and mitigation methods, this paper proposes a two-stage detection and mitigation method for DDoS attacks in SDN based on multi-dimensional characteristics. Firstly, an analysis of the traffic statistics from the SDN switch ports is performed, which aids in conducting a coarse-grained detection of DDoS attacks within the network. Subsequently, a Multi-Dimensional Deep Convolutional Classifier (MDDCC) is constructed using wavelet decomposition and convolutional neural networks to extract multi-dimensional characteristics from the traffic data passing through suspicious switches. Based on these extracted multi-dimensional characteristics, a simple classifier can be employed to accurately detect attack samples. Finally, by integrating graph theory with restrictive strategies, the source of attacks in SDN networks can be effectively traced and isolated. The experimental results indicate that the proposed method, which utilizes a minimal amount of statistical information, can quickly and accurately detect attacks within the SDN network. It demonstrates superior accuracy and generalization capabilities compared to traditional detection methods, especially when tested on both simulated and public datasets. Furthermore, by isolating the affected nodes, the method effectively mitigates the impact of the attacks, ensuring the normal transmission of legitimate traffic during network attacks. This approach not only enhances the detection capabilities but also provides a robust mechanism for containing the spread of cyber threats, thereby safeguarding the integrity and performance of the network.

Physics-guided self-supervised learning for retrospective T1 and T2 mapping from conventional weighted brain MRI: Technical developments and initial validation in glioblastoma.

To develop a self-supervised learning method to retrospectively estimate T1 and T2 values from clinical weighted MRI. A self-supervised learning approach was constructed to estimate T1, T2, and proton density maps from conventional T1- and T2-weighted images. MR physics models were employed to regenerate the weighted images from the network outputs, and the network was optimized based on loss calculated between the synthesized and input weighted images, alongside additional constraints based on prior information. The method was evaluated on healthy volunteer data, with conventional mapping as references. The reproducibility was examined on two 3.0T scanners. Performance in tumor characterization was inspected by applying the method to a public glioblastoma dataset. For T1 and T2 estimation from three weighted images (T1 MPRAGE, T1 gradient echo sequences, and T2 turbo spin echo), the deep learning method achieved global voxel-wise error ≤9% in brain parenchyma and regional error ≤12.2% in six types of brain tissues. The regional measurements obtained from two scanners showed mean differences ≤2.4% and correlation coefficients >0.98, demonstrating excellent reproducibility. In the 50 glioblastoma patients, the retrospective quantification results were in line with literature reports from prospective methods, and the T2 values were found to be higher in tumor regions, with sensitivity of 0.90 and specificity of 0.92 in a voxel-wise classification task between normal and abnormal regions. The self-supervised learning method is promising for retrospective T1 and T2 quantification from clinical MR images, with the potential to improve the availability of quantitative MRI and facilitate brain tumor characterization.

RpTrack: Robust Pig Tracking with Irregular Movement Processing and Behavioral Statistics

Pig behavioral analysis based on multi-object tracking (MOT) technology of surveillance videos is vital for precision livestock farming. To address the challenges posed by uneven lighting scenes and irregular pig movements in the MOT task, we proposed a pig MOT method named RpTrack. Firstly, RpTrack addresses the issue of lost tracking caused by irregular pig movements by using an appropriate Kalman Filter and improved trajectory management. Then, RpTrack utilizes BIoU for the second matching strategy to alleviate the influence of missed detections on the tracking performance. Finally, the method utilizes post-processing on the tracking results to generate behavioral statistics and activity trajectories for each pig. The experimental results under conditions of uneven lighting and irregular pig movements show that RpTrack significantly outperforms four other state-of-the-art MOT methods, including SORT, OC-SORT, ByteTrack, and Bot-SORT, on both public and private datasets. The experimental results demonstrate that RpTrack not only has the best tracking performance but also has high-speed processing capabilities. In conclusion, RpTrack effectively addresses the challenges of uneven scene lighting and irregular pig movements, enabling accurate pig tracking and monitoring of different behaviors, such as eating, standing, and lying. This research supports the advancement and application of intelligent pig farming.

Statistical Analysis of Features for Detecting Leukemia

In this age of digital microscopy, image processing, statistical analysis, categorization, and systems for decision-making have become essential tools for medical diagnostics research. By visualizing and analyzing images, clinicians can identify anomalies in intracellular structure. Leukemia is a cancerous condition marked by an unregulated increase in aberrant white blood cells (WBCs). Recognizing acute leukemia tumor cells in blood smear images (BSI) is a challenging assignment. Image segmentation is regarded as the most significant step in the automated identification of this disease. The innovative concavity-based segmentation algorithm is employed in this study to segment WBC in sub-images from the ALLIDB2 database. The concave endpoints and elliptical features are used in the segmentation step of convex-shaped cell images. The procedure involves the extraction of contour evidence, which detects the visible section of each object, and contour estimation, which corresponds to the final object’s contours. Following the identification of the cells and their internal structure by concavity-based segmentation, the cells are categorized based on their morphological and statistical features. The method was evaluated using a public dataset meant to test classification and segmentation approaches. The statistical tool SPSS is used to independently check the significance of derived features. For classification, significant features are passed into machine learning techniques such as support vector machines (SVM), k-nearest neighbor (KNN), neural networks (NN), decision trees (DT), and Nave Bayes (NB). With an AUC of 98.9% and a total accuracy of 95%, the neural network model performed better. We advocate using the neural network model to identify acute leukemia cells based on its accuracy.

Identifying rice field weeds from unmanned aerial vehicle remote sensing imagery using deep learning

BackgroundRice field weed object detection can provide key information on weed species and locations for precise spraying, which is of great significance in actual agricultural production. However, facing the complex and changing real farm environments, traditional object detection methods still have difficulties in identifying small-sized, occluded and densely distributed weed instances. To address these problems, this paper proposes a multi-scale feature enhanced DETR network, named RMS-DETR. By adding multi-scale feature extraction branches on top of DETR, this model fully utilizes the information from different semantic feature layers to improve recognition capability for rice field weeds in real-world scenarios.MethodsIntroducing multi-scale feature layers on the basis of the DETR model, we conduct a differentiated design for different semantic feature layers. The high-level semantic feature layer adopts Transformer structure to extract contextual information between barnyard grass and rice plants. The low-level semantic feature layer uses CNN structure to extract local detail features of barnyard grass. Introducing multi-scale feature layers inevitably leads to increased model computation, thus lowering model inference speed. Therefore, we employ a new type of Pconv (Partial convolution) to replace traditional standard convolutions in the model.ResultsCompared to the original DETR model, our proposed RMS-DETR model achieved an average recognition accuracy improvement of 3.6% and 4.4% on our constructed rice field weeds dataset and the DOTA public dataset, respectively. The average recognition accuracies reached 0.792 and 0.851, respectively. The RMS-DETR model size is 40.8 M with inference time of 0.0081 s. Compared with three classical DETR models (Deformable DETR, Anchor DETR and DAB-DETR), the RMS-DETR model respectively improved average precision by 2.1%, 4.9% and 2.4%.DiscussionThis model is capable of accurately identifying rice field weeds in complex real-world scenarios, thus providing key technical support for precision spraying and management of variable-rate spraying systems.

Targeting SOX4/PCK2 signaling suppresses neuroendocrine trans-differentiation of castration-resistant prostate cancer

BackgroundNeuroendocrine prostate cancer (NEPC), a lethal subset of prostate cancer (PCa), is characterized by loss of AR signaling and resistance to AR-targeted therapy. While it is well reported that second-generation AR blockers induce neuroendocrine (NE) trans-differentiation of castration-resistant prostate cancer (CRPC) to promote the occurrence of NEPC, and pluripotent transcription factors might be potential regulators, the underlying molecular mechanisms remain unclear.MethodsWe analyzed the data from public databsets to screen candidate genes and then focused on SOX4, a regulator of NE trans-differentiation. The expression changes of SOX4 and its relationship with tumor progression were validated in clinical tumor tissues. We evaluated malignant characteristics related to NEPC in prostate cancer cell lines with stable overexpression or knockdown of SOX4 in vitro. Tumor xenografts were analyzed after inoculating the relevant cell lines into nude mice. RNA-seq, ATAC-seq, non-targeted metabolomics analysis, as well as molecular and biochemical assays were carried out to determine the mechanism.ResultsWe screened public datasets and identified that expression of SOX4 was significantly elevated in NEPC. Overexpressing SOX4 in C4-2B cells increased cell proliferation and migration, upregulated the expression of NE marker genes, and inhibited AR expression. Consistently, inhibition of SOX4 expression in DU-145 and PC-3 cells reduced the above malignant phenotypes and repressed the expression of NE marker genes. For the in vivo assay, we found that knockdown of SOX4 inhibited tumor growth of subcutaneous xenografts in castrated nude mice which were concomitantly treated with enzalutamide (ENZ). Mechanically, we identified that one of the key enzymes in gluconeogenesis, PCK2, was a novel target of SOX4. The activation of carbohydrate metabolism reprogramming by SOX4 could promote NE trans-differentiation via the SOX4/PCK2 pathway.ConclusionsOur findings reveal that SOX4 promotes NE trans-differentiation both in vitro and in vivo via directly enhancing PCK2 activity to activate carbohydrate metabolism reprogramming. The SOX4/PCK2 pathway and its downstream changes might be novel targets for blocking NE trans-differentiation.

From image-level to pixel-level labeling: A weakly-supervised learning method for identifying aquaculture ponds using iterative anti-adversarial attacks guided by aquaculture features

Aquaculture mapping is essential for monitoring and managing aquaculture resources. However, accurately geotargeting individual aquaculture ponds from medium-resolution remote sensing imagery remains challenging, and convolutional deep learning methods for identifying aquaculture ponds require labor-intensive pixel-level annotations. This paper presents a novel weakly-supervised learning method to derive pixel-level labels from image-level annotations for aquaculture ponds. Our approach uses iterative anti-adversarial attacks to refine localization results from multi-scale class activation maps (CAMs). The improved method integrates two regularization methods guided by aquaculture features to form a joint loss function for adversarial samples: discriminative water region suppression and non-aquaculture water class suppression. We also propose an aquaculture feature termed CFNDWI to constrain the localization results and generate high-quality pseudo-labels. As a result, the pseudo-labels are used to train semantic segmentation networks for accurately identifying aquaculture ponds. We evaluated the performance of our method using commonly-used backbones on 10 m Sentinel-2 imagery. Our method achieves Intersection over Union (IoU) values of 0.618–0.655 for pseudo-label generation, and IoU values of 0.664–0.708 for semantic segmentation, outperforming state-of-the-art weakly-supervised methods and public datasets. The effectiveness of each module of our method was also testified through ablation experiments. Our method leverages knowledge-driven aquaculture features to guide the data-driven adversarial learning process, addressing the lack of high-quality aquaculture datasets for model training. The code for implementing our method will be accessible at https://github.com/designer1024/WSLM-AQ.

Evaluating and Enhancing Artificial Intelligence Models for Predicting Student Learning Outcomes

Predicting student outcomes is an essential task and a central challenge among artificial intelligence-based personalised learning applications. Despite several studies exploring student performance prediction, there is a notable lack of comprehensive and comparative research that methodically evaluates and compares multiple machine learning models alongside deep learning architectures. In response, our research provides a comprehensive comparison to evaluate and improve ten different machine learning and deep learning models, either well-established or cutting-edge techniques, namely, random forest, decision tree, support vector machine, K-nearest neighbours classifier, logistic regression, linear regression, and state-of-the-art extreme gradient boosting (XGBoost), as well as a fully connected feed-forward neural network, a convolutional neural network, and a gradient-boosted neural network. We implemented and fine-tuned these models using Python 3.9.5. With a keen emphasis on prediction accuracy and model performance optimisation, we evaluate these methodologies across two benchmark public student datasets. We employ a dual evaluation approach, utilising both k-fold cross-validation and holdout methods, to comprehensively assess the models’ performance. Our research focuses primarily on predicting student outcomes in final examinations by determining their success or failure. Moreover, we explore the importance of feature selection using the ubiquitous Lasso for dimensionality reduction to improve model efficiency, prevent overfitting, and examine its impact on prediction accuracy for each model, both with and without Lasso. This study provides valuable guidance for selecting and deploying predictive models for tabular data classification like student outcome prediction, which seeks to utilise data-driven insights for personalised education.

A simple and effective deep neural network based QRS complex detection method on ECG signal

Introduction: The QRS complex is the most prominent waveform within the electrocardiograph (ECG) signal. The accurate detection of the QRS complex is an essential step in the ECG analysis algorithm, which can provide fundamental information for the monitoring and diagnosis of the cardiovascular diseases.Methods: Seven public ECG datasets were used in the experiments. A simple and effective QRS complex detection algorithm based on the deep neural network (DNN) was proposed. The DNN model was composed of two parts: a feature pyramid network (FPN) based backbone with dual input channels to generate the feature maps, and a location head to predict the probability of point belonging to the QRS complex. The depthwise convolution was applied to reduce the parameters of the DNN model. Furthermore, a novel training strategy was developed. The target of the DNN model was generated by using the points within 75 milliseconds and beyond 150 milliseconds from the closest annotated QRS complexes, and artificial simulated ECG segments with high heart rates were generated in the data augmentation. The number of parameters and floating point operations (FLOPs) of our model was 26976 and 9.90M, respectively.Results: The proposed method was evaluated through a cross-dataset test and compared with the sophisticated state-of-the-art methods. On the MITBIH NST, the proposed method demonstrated slightly better sensitivity (95.59% vs. 95.55%) and lower presicion (91.03% vs. 92.93%). On the CPSC 2019, the proposed method have similar sensitivity (95.15% vs.95.13%) and better precision (91.75% vs. 82.03%).Discussion: Experimental results show the proposed algorithm achieved a comparable performance with only a few parameters and FLOPs, which would be useful for the application of ECG analysis on the wearable device.

Deep learning for intracranial aneurysm segmentation using CT angiography.

This study aimed to employ a two-stage deep learning method to accurately detect small aneurysms (4-10 mm in size) in computed tomography angiography (CTA) images.
Methods: This study included 956 patients from 6 hospitals and a public dataset obtained with 6 CT scanners from different manufacturers. The proposed method consists of two components: a lightweight and fast head region selection (HRS) algorithm and an adaptive 3D nnU-Net network, which is used as the main architecture for segmenting aneurysms. Segments generated by the deep neural network were compared with expert-generated manual segmentation results and assessed using Dice scores.
Results: The area under the curve (AUC) exceeded 79% across all datasets. In particular, the precision and AUC reached 85.2% and 87.6%, respectively, on certain datasets. The experimental results demonstrated the promising performance of this approach, which reduced the inference time by more than 50% compared to direct inference without HRS.
Conclusion: Compared with a model without HRS, the deep learning approach we developed can accurately segment aneurysms by automatically localizing brain regions and can accelerate aneurysm inference by more than 50%.
Keywords: Deep Learning, CT Angiography, Aneurisms.

Deep-Sea Ophiuroids (Echinodermata; Ophiuroidea) from the Avilés Canyon System: Seven New Records for the Spanish North Atlantic Marine Subdivision

The Avilés Canyon System (ACS) is located in the southern Bay of Biscay (northern Spain, Cantabrian Sea). It has been declared a Site of Community Importance (SCI: C ESZZ12003) within the Natura 2000 Network and recognized as a Vulnerable Marine Ecosystem (VME). This area is included in the North Atlantic Marine Subdivision (NAMD). The present study reviews ophiuroid fauna collected during the INDEMARES–ACS project and compares the new findings with previous studies using the Official Spanish Checklist (“Inventario Español de Especies Marinas”) to update our knowledge on the diversity and distribution of these species. During the surveys carried out within the LIFE + INDEMARES–Avilés Canyon System project (2010–2012), a total of 7413 specimens belonging to 45 ophiuroid species were collected from 50 stations in a depth range between 266 and 2291 m. The most frequent species was Ophiactis abyssicola (M. Sars, 1861). Comparing the identified species with public datasets, seven species should be considered as new records for NAMD: Ophiocten centobi Paterson, Tyler & Gage, 1982, Amphiura borealis (G.O. Sars, 1872), Amphiura fragilis Verrill, 1885, Ophiochondrus armatus (Koehler, 1907), Ophiosabine parcita (Koehler, 1906), Ophiophrixus spinosus (Storm, 1881), Ophiotreta valenciennesi (Lyman, 1879). Furthermore, one species has expanded its bathymetric range: Ophiosabine parcita (Koehler, 1906).

Convolutional Block Attention Module–Multimodal Feature-Fusion Action Recognition: Enabling Miner Unsafe Action Recognition

The unsafe action of miners is one of the main causes of mine accidents. Research on underground miner unsafe action recognition based on computer vision enables relatively accurate real-time recognition of unsafe action among underground miners. A dataset called unsafe actions of underground miners (UAUM) was constructed and included ten categories of such actions. Underground images were enhanced using spatial- and frequency-domain enhancement algorithms. A combination of the YOLOX object detection algorithm and the Lite-HRNet human key-point detection algorithm was utilized to obtain skeleton modal data. The CBAM-PoseC3D model, a skeleton modal action-recognition model incorporating the CBAM attention module, was proposed and combined with the RGB modal feature-extraction model CBAM-SlowOnly. Ultimately, this formed the Convolutional Block Attention Module–Multimodal Feature-Fusion Action Recognition (CBAM-MFFAR) model for recognizing unsafe actions of underground miners. The improved CBAM-MFFAR model achieved a recognition accuracy of 95.8% on the NTU60 RGB+D public dataset under the X-Sub benchmark. Compared to the CBAM-PoseC3D, PoseC3D, 2S-AGCN, and ST-GCN models, the recognition accuracy was improved by 2%, 2.7%, 7.3%, and 14.3%, respectively. On the UAUM dataset, the CBAM-MFFAR model achieved a recognition accuracy of 94.6%, with improvements of 2.6%, 4%, 12%, and 17.3% compared to the CBAM-PoseC3D, PoseC3D, 2S-AGCN, and ST-GCN models, respectively. In field validation at mining sites, the CBAM-MFFAR model accurately recognized similar and multiple unsafe actions among underground miners.

Sensing the diversity of rumors: Rumor detection with hierarchical prototype contrastive learning

The proliferation of rumors on social networks poses a serious threat to cybersecurity, justice and public trust, increasing the urgent need for rumor detection. Existing detection methods typically treat all rumors as a single homogeneous category, neglecting the diverse semantic hierarchies within rumors. Rumors pervade various domains, each with its distinct characteristics. These methods tend to lag in expressiveness when confronted with real-world scenarios involving multiple semantic levels. Furthermore, the diversity of rumors also complicates the collection of datasets, and inevitably introduces noisy data, which hinders the correctness of the learned representations. To address these challenges, we propose a rumor detection framework with Hierarchical Prototype Contrastive Learning (HPCL). In this framework, we construct a set of dynamically updated hierarchical prototypes through contrastive learning to encourage capturing the hierarchical semantic structure within rumors. Additionally, we design a difficulty metric function based on the distance between instances and prototypes, and introduce curriculum learning to mitigate the adverse effects of noisy data. Experiments on four public datasets demonstrate that our approach achieves state-of-the-art performance. Our code is publicly released at https://github.com/Coder-HenryZa/HPCL.

State-of-the-art sleep arousal detection evaluated on a comprehensive clinical dataset

Aiming to apply automatic arousal detection to support sleep laboratories, we evaluated an optimized, state-of-the-art approach using data from daily work in our university hospital sleep laboratory. Therefore, a machine learning algorithm was trained and evaluated on 3423 polysomnograms of people with various sleep disorders. The model architecture is a U-net that accepts 50 Hz signals as input. We compared this algorithm with models trained on publicly available datasets, and evaluated these models using our clinical dataset, particularly with regard to the effects of different sleep disorders. In an effort to evaluate clinical relevance, we designed a metric based on the error of the predicted arousal index. Our models achieve an area under the precision recall curve (AUPRC) of up to 0.83 and F1 scores of up to 0.81. The model trained on our data showed no age or gender bias and no significant negative effect regarding sleep disorders on model performance compared to healthy sleep. In contrast, models trained on public datasets showed a small to moderate negative effect (calculated using Cohen's d) of sleep disorders on model performance. Therefore, we conclude that state-of-the-art arousal detection on our clinical data is possible with our model architecture. Thus, our results support the general recommendation to use a clinical dataset for training if the model is to be applied to clinical data.

Two-tier architecture-based grading for pancreatic cancer outperforms traditional grading.

A novel architecture-based grading system for pancreatic ductal adenocarcinoma (PDAC) is tested against traditional grading. A total of 103 PDAC resections were graded by College of American Pathologists/American Joint Committee on Cancer (CAP/AJCC) guidelines and by a system using an architectural pattern (dispersed larger duct = low grade vs dense smaller duct = high grade). Survival analyses and interobserver variability were assessed. In total, 114 cases from a public data set were used for validation. Median overall survivals were 15 and 36 months for architectural high-grade and low-grade cases, respectively (P<.001). Conversely, CAP/AJCC grading showed no survival difference between well-differentiated and moderately differentiated tumors (P=.545). Architecture-based grading remained prognostically significant for recurrence-free survival (P=.004), but CAP/AJCC grading was not (P=.226). Adjusted for stage and margin status, architectural high-grade PDACs showed a hazard ratio of 2.69 relative to low grade (P<.001) for survival. The validation cohort confirmed prognostic differences in overall (P<.001) and recurrence-free survival (P=.027) for the architecture-based system, outperforming CAP/AJCC grading. Architecture-based grading exhibited a Cohen's ĸ value of 0.710 (substantial agreement), superior to traditional grading (0.488, moderate agreement). Grading PDAC based on architectural pattern results in superior prognostication and reproducibility vs CAP/AJCC grading.

SiamDCFF: Dynamic Cascade Feature Fusion for Vision Tracking

Establishing an accurate and robust feature fusion mechanism is key to enhancing the tracking performance of single-object trackers based on a Siamese network. However, the output features of the depth-wise cross-correlation feature fusion module in fully convolutional trackers based on Siamese networks cannot establish global dependencies on the feature maps of a search area. This paper proposes a dynamic cascade feature fusion (DCFF) module by introducing a local feature guidance (LFG) module and dynamic attention modules (DAMs) after the depth-wise cross-correlation module to enhance the global dependency modeling capability during the feature fusion process. In this paper, a set of verification experiments is designed to investigate whether establishing global dependencies for the features output by the depth-wise cross-correlation operation can significantly improve the performance of fully convolutional trackers based on a Siamese network, providing experimental support for rational design of the structure of a dynamic cascade feature fusion module. Secondly, we integrate the dynamic cascade feature fusion module into the tracking framework based on a Siamese network, propose SiamDCFF, and evaluate it using public datasets. Compared with the baseline model, SiamDCFF demonstrated significant improvements.