Private Datasets Research Articles

A tree-based explainable AI model for early detection of Covid-19 using physiological data

With the outbreak of COVID-19 in 2020, countries worldwide faced significant concerns and challenges. Various studies have emerged utilizing Artificial Intelligence (AI) and Data Science techniques for disease detection. Although COVID-19 cases have declined, there are still cases and deaths around the world. Therefore, early detection of COVID-19 before the onset of symptoms has become crucial in reducing its extensive impact. Fortunately, wearable devices such as smartwatches have proven to be valuable sources of physiological data, including Heart Rate (HR) and sleep quality, enabling the detection of inflammatory diseases. In this study, we utilize an already-existing dataset that includes individual step counts and heart rate data to predict the probability of COVID-19 infection before the onset of symptoms. We train three main model architectures: the Gradient Boosting classifier (GB), CatBoost trees, and TabNet classifier to analyze the physiological data and compare their respective performances. We also add an interpretability layer to our best-performing model, which clarifies prediction results and allows a detailed assessment of effectiveness. Moreover, we created a private dataset by gathering physiological data from Fitbit devices to guarantee reliability and avoid bias.The identical set of models was then applied to this private dataset using the same pre-trained models, and the results were documented. Using the CatBoost tree-based method, our best-performing model outperformed previous studies with an accuracy rate of 85% on the publicly available dataset. Furthermore, this identical pre-trained CatBoost model produced an accuracy of 81% when applied to the private dataset. You will find the source code in the link: https://github.com/OpenUAE-LAB/Covid-19-detection-using-Wearable-data.git.

Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram.

Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application. The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician's careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research. The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician's assessment. The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.

Image2Flow: A proof-of-concept hybrid image and graph convolutional neural network for rapid patient-specific pulmonary artery segmentation and CFD flow field calculation from 3D cardiac MRI data.

Computational fluid dynamics (CFD) can be used for non-invasive evaluation of hemodynamics. However, its routine use is limited by labor-intensive manual segmentation, CFD mesh creation, and time-consuming simulation. This study aims to train a deep learning model to both generate patient-specific volume-meshes of the pulmonary artery from 3D cardiac MRI data and directly estimate CFD flow fields. This proof-of-concept study used 135 3D cardiac MRIs from both a public and private dataset. The pulmonary arteries in the MRIs were manually segmented and converted into volume-meshes. CFD simulations were performed on ground truth meshes and interpolated onto point-point correspondent meshes to create the ground truth dataset. The dataset was split 110/10/15 for training, validation, and testing. Image2Flow, a hybrid image and graph convolutional neural network, was trained to transform a pulmonary artery template to patient-specific anatomy and CFD values, taking a specific inlet velocity as an additional input. Image2Flow was evaluated in terms of segmentation, and the accuracy of predicted CFD was assessed using node-wise comparisons. In addition, the ability of Image2Flow to respond to increasing inlet velocities was also evaluated. Image2Flow achieved excellent segmentation accuracy with a median Dice score of 0.91 (IQR: 0.86-0.92). The median node-wise normalized absolute error for pressure and velocity magnitude was 11.75% (IQR: 9.60-15.30%) and 9.90% (IQR: 8.47-11.90), respectively. Image2Flow also showed an expected response to increased inlet velocities with increasing pressure and velocity values. This proof-of-concept study has shown that it is possible to simultaneously perform patient-specific volume-mesh based segmentation and pressure and flow field estimation using Image2Flow. Image2Flow completes segmentation and CFD in ~330ms, which is ~5000 times faster than manual methods, making it more feasible in a clinical environment.

AMFP-net: Adaptive multi-scale feature pyramid network for diagnosis of pneumoconiosis from chest X-ray images

Early detection of pneumoconiosis by routine health screening of workers in the mining industry is critical for preventing the progression of this incurable disease. Automated pneumoconiosis classification in chest X-ray images is challenging due to the low contrast of opacities, inter-class similarity, intra-class variation and the existence of artifacts. Compared to traditional methods, convolutional neural networks have shown significant improvement in pneumoconiosis classification tasks, however, accurate classification remains challenging due to mainly the inability to focus on semantically meaningful lesion opacities. Most existing networks focus on high level abstract information and ignore low level detailed object information. Different from natural images where an object occupies large space, the classification of pneumoconiosis depends on the density of small opacities inside the lung. To address this issue, we propose a novel two-stage adaptive multi-scale feature pyramid network called AMFP-Net for the diagnosis of pneumoconiosis from chest X-rays. The proposed model consists of 1) an adaptive multi-scale context block to extract rich contextual and discriminative information and 2) a weighted feature fusion module to effectively combine low level detailed and high level global semantic information. This two-stage network first segments the lungs to focus more on relevant regions by excluding irrelevant parts of the image, and then utilises the segmented lungs to classify pneumoconiosis into different categories. Extensive experiments on public and private datasets demonstrate that the proposed approach can outperform state-of-the-art methods for both segmentation and classification.

Physics-Based Practical Speckle Noise Modeling for Optical Coherence Tomography Image Denoising

Optical coherence tomography (OCT) has been extensively utilized in the field of biomedical imaging due to its non-invasive nature and its ability to provide high-resolution, in-depth imaging of biological tissues. However, the use of low-coherence light can lead to unintended interference phenomena within the sample, which inevitably introduces speckle noise into the imaging results. This type of noise often obscures key features in the image, thereby reducing the accuracy of medical diagnoses. Existing denoising algorithms, while removing noise, tend to also damage the structural details of the image, affecting the quality of diagnosis. To overcome this challenge, we have proposed a speckle noise (PSN) framework. The core of this framework is an innovative dual-module noise generator that can decompose the noise in OCT images into speckle noise and equipment noise, addressing each type independently. By integrating the physical properties of noise into the design of the noise generator and training it with unpaired data, we are able to synthesize realistic noise images that match clear images. These synthesized paired images are then used to train a denoiser to effectively denoise real OCT images. Our method has demonstrated its superiority in both private and public datasets, particularly in maintaining the integrity of the image structure. This study emphasizes the importance of considering the physical information of noise in denoising tasks, providing a new perspective and solution for enhancing OCT image denoising technology.

EPSViTs: A hybrid architecture for image classification based on parameter-shared multi-head self-attention

Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image. However, they still suffer from weak local feature extraction, easy loss of channel interaction information in one-dimensional multi-head self-attention modeling, and large number of parameters. This paper proposes a lightweight image classification hybrid architecture named EPSViTs (Efficient Parameter Shared Transformer, EPSViTs). Firstly, a new local feature extraction module is designed to effectively enhance the expression of local features. Secondly, using the parameter sharing approach, a lightweight multi-head self-attention module based on information interaction is designed, which can globally model the image from both spatial and channel dimensions, and mine the potential correlation of the image in space and channel. Extensive experiments are conducted on three public datasets, a subset of ImageNet, Cifar100 and APTOS2019, a private dataset Mushroom66, and the results show that the hybrid architecture EPSViTs proposed in this paper based on parameter sharing for multi-head self-attentive image classification has obvious advantages, especially on a subset of ImageNet to reach 89.18%, which is a 3.8% improvement compared to Edgevits_xxs, verifying the effectiveness of the model.

DiffRank: Enhancing efficiency in discontinuous frame rate analysis for urban surveillance systems

Urban public safety management relies heavily on video surveillance systems, which provide crucial visual data for resolving a wide range of incidents and controlling unlawful activities. Traditional methods for target detection predominantly employ a two-stage approach, focusing on precision in identifying objects such as pedestrians and vehicles. These objects, typically sparse in large-scale, lower-quality surveillance footage, induce considerable redundant computation during the initial processing stage. This redundancy constrains real-time detection capabilities and escalates processing costs. Furthermore, transmitting raw images and videos laden with superfluous information to centralized back-end systems significantly burdens network communications and fails to capitalize on the computational resources available at diverse surveillance nodes. This study introduces DiffRank, a novel preprocessing method for fixed-angle video imagery in urban surveillance. The method strategically generates candidate regions during preprocessing, thereby reducing redundant object detection and improving the efficiency of the detection algorithm. Drawing upon change detection principles, a background feature learning approach utilizing shallow features has been developed. This approach prioritizes learning the characteristics of fixed-area backgrounds over direct background identification. As a result, alterations in ROI are efficiently discerned using computationally efficient shallow features, markedly accelerating the generation of proposed Regions of Interest (ROIs) and diminishing the computational demands for subsequent object detection and classification. Comparative analysis on various public and private datasets illustrates that DiffRank, while maintaining high accuracy, substantially outperforms existing baselines in terms of speed, particularly with larger image sizes (e.g., an improvement exceeding 300 % at 1920×1080 resolution). Moreover, the method demonstrates enhanced robustness compared to baseline methods, efficiently disregarding static targets like mannequins in display windows. The advancements in candidate area preprocessing enable a balanced approach between detection accuracy and overall detection speed, making the algorithm highly applicable for real-time on-site analysis in edge computing scenarios and cloud-edge collaborative computing environments.

CoF-DResNet: Cancer Metastasis Recognition Network based on Dynamic Coordinated Metabolic Attention and Structural Attention.

Cancer metastasis usually means that cancer cells spread to other tissues or organs, and the condition worsens. Identifying whether cancer has metastasized can help doctors infer the progression of a patient's condition and is an essential prerequisite for devising treatment plans. Fluorine 18 fluorodeoxyglucose positron emission tomography/computed tomography ( 18F -FDG PET/CT) is an advanced cancer diagnostic imaging technique that provides both metabolic and structural information. In cancer metastasis recognition tasks, effectively integrating metabolic and structural information stands as a key technology to enhance feature representation and recognition performance. This paper proposes a cancer metastasis identification network based on dynamic coordinated metabolic attention and structural attention to address these challenges. Specifically, metabolic and structural features are extracted by incorporating a dynamic coordinated attention module (DCAM) into two branches of ResNet networks, thereby amalgamating high metabolic spatial information from PET images with texture structure information from CT images, and dynamically adjusting this process through iterations. Next, to improve the efficacy of feature expression, a multi-receptive field feature fusion module (MRFM) is included in order to execute multi-receptive field fusion of semantic features. To validate the effectiveness of our proposed model, experiments were conducted on both a private lung lymph nodes dataset and a public soft tissue sarcomas dataset. The accuracy of our method reached 76.0% and 75.1% for the two datasets, respectively, demonstrating an improvement of 6.8% and 5.6% compared to ResNet, thus affirming the efficacy of our method.

Simulating federated learning for steatosis detection using ultrasound images

We aimed to implement four data partitioning strategies evaluated with four federated learning (FL) algorithms and investigate the impact of data distribution on FL model performance in detecting steatosis using B-mode US images. A private dataset (153 patients; 1530 images) and a public dataset (55 patient; 550 images) were included in this retrospective study. The datasets contained patients with metabolic dysfunction-associated fatty liver disease (MAFLD) with biopsy-proven steatosis grades and control individuals without steatosis. We employed four data partitioning strategies to simulate FL scenarios and we assessed four FL algorithms. We investigated the impact of class imbalance and the mismatch between the global and local data distributions on the learning outcome. Classification performance was assessed with area under the receiver operating characteristic curve (AUC) on a separate test set. AUCs were 0.93 (95% CI 0.92, 0.94) for source-based partitioning scenario with FedAvg, 0.90 (95% CI 0.89, 0.91) for a centralized model, and 0.83 (95% CI 0.81, 0.85) for a model trained in a single-center scenario. When data was perfectly balanced on the global level and each site had an identical data distribution, the model yielded an AUC of 0.90 (95% CI 0.88, 0.92). When each site contained data exclusively from one single class, irrespective of the global data distribution, the AUC fell in the range of 0.34–0.70. FL applied to B-mode US images provide performance comparable to a centralized model and higher than single-center scenario. Global data imbalance and local data heterogeneity influenced the learning outcome.

Segmentation-based BI-RADS ensemble classification of breast tumours in ultrasound images

BackgroundThe development of computer-aided diagnosis systems in breast cancer imaging is exponential. Since 2016, 81 papers have described the automated segmentation of breast lesions in ultrasound images using artificial intelligence. However, only two papers have dealt with complex BI-RADS classifications. PurposeThis study addresses the automatic classification of breast lesions into binary classes (benign vs. malignant) and multiple BI-RADS classes based on a single ultrasonographic image. Achieving this task should reduce the subjectivity of an individual operator’s assessment. Materials and MethodsAutomatic image segmentation methods (PraNet, CaraNet and FCBFormer) adapted to the specific segmentation task were investigated using the U-Net model as a reference. A new classification method was developed using an ensemble of selected segmentation approaches. All experiments were performed on publicly available BUS B, OASBUD, BUSI and private datasets. ResultsFCBFormer achieved the best outcomes for the segmentation task with intersection over union metric values of 0.81, 0.80 and 0.73 and Dice values of 0.89, 0.87 and 0.82, respectively, for the BUS B, BUSI and OASBUD datasets. Through a series of experiments, we determined that adding an extra 30-pixel margin to the segmentation mask counteracts the potential errors introduced by the segmentation algorithm. An assembly of the full image classifier, bounding box classifier and masked image classifier was the most accurate for binary classification and had the best accuracy (ACC; 0.908), F1 (0.846) and area under the receiver operating characteristics curve (AUROC; 0.871) in the BUS B and ACC (0.982), F1 (0.984) and AUROC (0.998) in the UCC BUS datasets, outperforming each classifier used separately. It was also the most effective for BI-RADS classification, with ACC of 0.953, F1 of 0.920 and AUROC of 0.986 in UCC BUS. Hard voting was the most effective method for dichotomous classification. For the multi-class BI-RADS classification, the soft voting approach was employed. ConclusionsThe proposed new classification approach with an ensemble of segmentation and classification approaches proved more accurate than most published results for binary and multi-class BI-RADS classifications.

Hybrid CNN-Transformer Network With Circular Feature Interaction for Acute Ischemic Stroke Lesion Segmentation on Non-Contrast CT Scans.

Lesion segmentation is a fundamental step for the diagnosis of acute ischemic stroke (AIS). Non-contrast CT (NCCT) is still a mainstream imaging modality for AIS lesion measurement. However, AIS lesion segmentation on NCCT is challenging due to low contrast, noise and artifacts. To achieve accurate AIS lesion segmentation on NCCT, this study proposes a hybrid convolutional neural network (CNN) and Transformer network with circular feature interaction and bilateral difference learning. It consists of parallel CNN and Transformer encoders, a circular feature interaction module, and a shared CNN decoder with a bilateral difference learning module. A new Transformer block is particularly designed to solve the weak inductive bias problem of the traditional Transformer. To effectively combine features from CNN and Transformer encoders, we first design a multi-level feature aggregation module to combine multi-scale features in each encoder and then propose a novel feature interaction module containing circular CNN-to-Transformer and Transformer-to-CNN interaction blocks. Besides, a bilateral difference learning module is proposed at the bottom level of the decoder to learn the different information between the ischemic and contralateral sides of the brain. The proposed method is evaluated on three AIS datasets: the public AISD, a private dataset and an external dataset. Experimental results show that the proposed method achieves Dices of 61.39% and 46.74% on the AISD and the private dataset, respectively, outperforming 17 state-of-the-art segmentation methods. Besides, volumetric analysis on segmented lesions and external validation results imply that the proposed method is potential to provide support information for AIS diagnosis.

ScribFormer: Transformer Makes CNN Work Better for Scribble-Based Medical Image Segmentation.

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the convolutional layer with the local receptive field, which makes it difficult to learn global shape information from the limited information provided by scribble annotations. To address this issue, this paper proposes a new CNN-Transformer hybrid solution for scribble-supervised medical image segmentation called ScribFormer. The proposed ScribFormer model has a triple-branch structure, i.e., the hybrid of a CNN branch, a Transformer branch, and an attention-guided class activation map (ACAM) branch. Specifically, the CNN branch collaborates with the Transformer branch to fuse the local features learned from CNN with the global representations obtained from Transformer, which can effectively overcome limitations of existing scribble-supervised segmentation methods. Furthermore, the ACAM branch assists in unifying the shallow convolution features and the deep convolution features to improve model's performance further. Extensive experiments on two public datasets and one private dataset show that our ScribFormer has superior performance over the state-of-the-art scribble-supervised segmentation methods, and achieves even better results than the fully-supervised segmentation methods. The code is released at https://github.com/HUANGLIZI/ScribFormer.

Privacy-preserving intelligent fault diagnostics for wind turbine clusters using federated stacked capsule autoencoder

The emergence of Internet of Things (IoT) technologies in the field of health monitoring has introduced the paradigm of Industrial Internet of Things (IIoT) to the industry. IIoT systems provide enterprises with a substantial volume of monitoring data for industrial equipment health monitoring, facilitating the development of artificial intelligence fault diagnosis models. However, a singular industrial entity often encounters limitations in collecting sufficient training data in practical scenarios. Moreover, the sharing of confidential information among entities is strictly prohibited due to concerns regarding intellectual property and data security. This study proposes a fault diagnosis system that addresses this issue by incorporating a capsule-based fault feature expression into the federated learning (FL) framework. The system comprises clients distributed across multiple factories and a central server hosted in the cloud. The client models are trained on local private datasets, and then knowledge fusion is achieved by uploading intrinsic templates and pose matrices to the central server. The proposed method offers the advantage of reducing transmission burden and enhancing data security in comparison to existing FL approaches. Besides, a capsule knowledge alignment algorithm is proposed to update the capsule-based fault feature expression ona central server. To simulate real fault diagnosis application scenarios, two similar fault simulation platforms are built to acquire isolated fault diagnosis datasets. The effectiveness of the proposed method is verified using these datasets.

Framework to Create Inventory Dataset for Disaster Behavior Analysis Using Google Earth Engine: A Case Study in Peninsular Malaysia for Historical Forest Fire Behavior Analysis

This study developed a comprehensive framework using Google Earth Engine to efficiently generate a forest fire inventory dataset, which enhanced data accessibility without specialized knowledge or access to private datasets. The framework is applicable globally, and the datasets generated are freely accessible and shareable. By implementing the framework in Peninsular Malaysia, significant forest fire factors were successfully extracted, including the Keetch–Byram Drought Index (KBDI), soil moisture, temperature, windspeed, land surface temperature (LST), Palmer Drought Severity Index (PDSI), Normalized Vegetation Index (NDVI), landcover, and precipitation, among others. Additionally, this study also adopted large language models, specifically GPT-4 with the Noteable plugin, for preliminary data analysis to assess the dataset’s validity. Although the plugin effectively performed basic statistical analyses and visualizations, it demonstrated limitations, such as selectively dropping or choosing only relevant columns for tests and automatically modifying scales. These behaviors underscore the need for users to perform additional checks on the codes generated to ensure that they accurately reflect the intended analyses. The initial findings indicate that factors such as KBDI, LST, climate water deficit, and precipitation significantly impact forest fire occurrences in Peninsular Malaysia. Future research should explore extending the framework’s application to various regions and further refine it to accommodate a broader range of factors. Embracing and rigorously validating large language model technologies, alongside developing new tools and plugins, are essential for advancing the field of data analysis.

Multi-attentional causal intervention networks for medical image diagnosis

Medical image diagnosis has developed rapidly under the impetus of the deep network. Previous works mainly focus on improving the diagnostic accuracy of models, i.e., first use a backbone network to extract image global features and then feed it into the classifier for diagnosis. However, these methods do not fully explore the transparent and reasonable decision-making process of the final classification results, which is crucial for medical diagnosis. In this paper, we propose a framework called Causal Intervention-based Multi-head Attention network (CaIMA) to enhance the explainability of medical diagnosis from a causal inference perspective, by exploring the inherent causal relationship between multi-region attention and diagnosis results. Specifically, it consists of three key components: (1) The multi-region attention module enables the network to focus on the distinct discriminative lesion regions that hold causal relationships with the predicted outcome. (2) The attention-driven data augmentation module provides accurate localization of discriminative regions and enhances model explainability. (3) The causal intervention module aims to explore the intrinsic causal relationship between the attention map and the predicted outcome, encouraging the network to learn more useful attention maps for medical image diagnosis. Besides, to address the learning difficulty of this network, we further introduce a non-overlapping multiple attentional guidance loss that encourages the learned multiple attention maps to focus on specific lesion regions without overlapping. We compare the proposed CaIMA with state-of-the-art methods on multimedia medical datasets, including three public medical image datasets (Kvasir, ISIC2018, COVID-19) and one private dataset (CLC), and the experimental results substantiate the effectiveness of CaIMA in terms of diagnosis accuracy and explainability.

CMAN: Cascaded Multi-scale Spatial Channel Attention-guided Network for large 3D deformable registration of liver CT images

Deformable image registration is an essential component of medical image analysis and plays an irreplaceable role in clinical practice. In recent years, deep learning-based registration methods have demonstrated significant improvements in convenience, robustness and execution time compared to traditional algorithms. However, registering images with large displacements, such as those of the liver organ, remains underexplored and challenging. In this study, we present a novel convolutional neural network (CNN)-based unsupervised learning registration method, Cascaded Multi-scale Spatial-Channel Attention-guided Network (CMAN), which addresses the challenge of large deformation fields using a double coarse-to-fine registration approach. The main contributions of CMAN include: (i) local coarse-to-fine registration in the base network, which generates the displacement field for each resolution and progressively propagates these local deformations as auxiliary information for the final deformation field; (ii) global coarse-to-fine registration, which stacks multiple base networks for sequential warping, thereby incorporating richer multi-layer contextual details into the final deformation field; (iii) integration of the spatial-channel attention module in the decoder stage, which better highlights important features and improves the quality of feature maps. The proposed network was trained using two public datasets and evaluated on another public dataset as well as a private dataset across several experimental scenarios. We compared CMAN with four state-of-the-art CNN-based registration methods and two well-known traditional algorithms. The results show that the proposed double coarse-to-fine registration strategy outperforms other methods in most registration evaluation metrics. In conclusion, CMAN can effectively handle the large-deformation registration problem and show potential for application in clinical practice. The source code is made publicly available at https://github.com/LocPham263/CMAN.git.

Distillation of multi-class cervical lesion cell detection via synthesis-aided pre-training and patch-level feature alignment

Automated detection of cervical abnormal cells from Thin-prep cytologic test (TCT) images is crucial for efficient cervical abnormal screening using computer-aided diagnosis systems. However, the construction of the detection model is hindered by the preparation of the training images, which usually suffers from issues of class imbalance and incomplete annotations. Additionally, existing methods often overlook the visual feature correlations among cells, which are crucial in cervical lesion cell detection as pathologists commonly rely on surrounding cells for identification. In this paper, we propose a distillation framework that utilizes a patch-level pre-training network to guide the training of an image-level detection network, which can be applied to various detectors without changing their architectures during inference. The main contribution is three-fold: (1) We propose the Balanced Pre-training Model (BPM) as the patch-level cervical cell classification model, which employs an image synthesis model to construct a class-balanced patch dataset for pre-training. (2) We design the Score Correction Loss (SCL) to enable the detection network to distill knowledge from the BPM model, thereby mitigating the impact of incomplete annotations. (3) We design the Patch Correlation Consistency (PCC) strategy to exploit the correlation information of extracted cells, consistent with the behavior of cytopathologists. Experiments on public and private datasets demonstrate the superior performance of the proposed distillation method, as well as its adaptability to various detection architectures.

Magnetic Resonance Images Segmentation of Multifidus based on Dense-unet and Superpixel.

Lumbar disc herniation (LDH) is a common clinical condition causing lower back and leg pain. Accurate segmentation of the lumbar discs is crucial for assessing and diagnosing LDH. Magnetic resonance imaging (MRI) can reveal the condition of articular cartilage. However, manual segmentation of MRI images is burdensome for physicians and needs to be more efficient. In this study, we propose a method that combines UNet and superpixel segmentation to address the problem of loss of detailed information in the feature extraction phase, leading to poor segmentation results at object edges. The aim is to provide a reproducible solution for diagnosing patients with lumbar disc herniation. We suggest using the network structure of UNet. Firstly, dense blocks are inserted into the UNet network, and training is performed using the Swish activation function. The Dense-UNet model extracts semantic features from the images and obtains rough semantic segmentation results. Then, an adaptive-scale superpixel segmentation algorithm is applied to segment the input images into superpixel images. Finally, high-level abstract semantic features are fused with the detailed information of the superpixels to obtain edge-optimized semantic segmentation results. Evaluation of a private dataset of multifidus muscles in magnetic resonance images demonstrates that compared to other segmentation algorithms, this algorithm exhibits better semantic segmentation performance in detailed areas such as object edges. Compared to UNet, it achieves a 9.5% improvement in the Dice Similarity Coefficient (DSC) and an 11.3% improvement in the Jaccard Index (JAC). The experimental results indicate that this algorithm improves segmentation performance while reducing computational complexity.

Learning-Based Non-Intrusive Electric Load Monitoring for Smart Energy Management.

State-of-the-art smart cities have been calling for economic but efficient energy management over a large-scale network, especially for the electric power system. It is a critical issue to monitor, analyze, and control electric loads of all users in the system. In this study, a non-intrusive load monitoring method was designed for smart power management using computer vision techniques popular in artificial intelligence. First of all, one-dimensional current signals are mapped onto two-dimensional color feature images using signal transforms (including the wavelet transform and discrete Fourier transform) and Gramian Angular Field (GAF) methods. Second, a deep neural network with multi-scale feature extraction and attention mechanism is proposed to recognize all electrical loads from the color feature images. Third, a cloud-based approach was designed for the non-intrusive monitoring of all users, thereby saving energy costs during power system control. Experimental results on both public and private datasets demonstrate that the method achieves superior performances compared to its peers, and thus supports efficient energy management over a large-scale Internet of Things network.

Automated analysis of fetal heart rate baseline/acceleration/deceleration using MTU-Net3 + model.

In clinical practice, obstetricians use visual interpretation of fetal heart rate (FHR) to diagnose fetal conditions, but inconsistencies among interpretations can hinder accuracy. This study introduces MTU-Net3+, a deep learning model designed for automated, multi-task FHR analysis, aiming to improve diagnostic accuracy and efficiency. The proposed MTU-Net3 + was built upon the UNet3 + architecture, incorporating an encoder, a decoder, full-scale skip connections, and a deep supervision module, and further integrates a self-attention mechanism and bidirectional Long Short-Term Memory layers to enhance its performance. The MTU-Net3 + model accepts the preprocessed 20-minute FHR signals as input, outputting categorical probabilities and baseline values for each time point. The proposed MTU-Net3 + model was trained on a subset of a public database, and was tested on the remaining data of the public database and a private database. In the remaining public datasets, this model achieved F1 scores of 84.21% for deceleration (F1.Dec) and 61.33% for acceleration (F1.Acc), with a Root Mean Square Baseline Difference (RMSD.BL) of 3.46bpm, 0% of points with an absolute difference exceeding 15bpm(D15bpm), a Synthetic Inconsistency Coefficient (SI) of 44.82%, and a Morphological Analysis Discordance Index (MADI) of 7.00%. On the private dataset, the model recorded an RMSD.BL of 1.37bpm, 0% D15bpm, F1.Dec of 100%, F1.Acc of 87.50%, an SI of 12.20% and a MADI of 2.79%. The MTU-Net3 + model proposed in this study performed well in automated FHR analysis, demonstrating its potential as an effective tool in the field of fetal health assessment.