Patch Features Research Articles

A spatio-temporal evolution analysis framework based on sentiment recognition for temple murals

Murals are important resources for carrying cultural heritage, historical evidence and artistic memory. The sentiment of a mural is the transmission of its inner thoughts, closely related to the region and dynasty to which the mural belongs. To explore the sentiment evolution patterns of temple murals, we construct a spatio-temporal evolution analysis framework based on sentiment recognition. This framework mainly includes feature extraction, sentiment recognition and sentiment evolution analysis. First, we extract the colour features, local features, global semantic features, patch features and structure relations to represent the visual features of temple murals. Second, the semantics of spatio-temporal attributes and titles of murals are extracted through the fine-tuned BERT (Bidirectional Encoder Representations from Transformers) to enhance the feature discrimination for sentiment recognition. Third, we introduce the SMOTE (Synthetic Minority Oversampling Technique) to reduce the influence of imbalanced data and select RF (random forest) as the optimal classifier. The F1 score of the fine-grained sentiment recognition model is up to 81.37%. Finally, we collect the temple murals and reveal the characteristics and patterns of sentiment evolution from the spatial, temporal and spatio-temporal perspectives.

Research on Fault Diagnosis of Rotating Parts Based on Transformer Deep Learning Model

The rotating parts of large and complex equipment are key components that ensure the normal operation of the equipment. Accurate fault diagnosis is crucial for the safe operation of these systems. To simultaneously extract both local and global valuable fault feature information from key components of complex equipment, this study proposes a fault diagnosis network model, named MultiDilatedFormer, which is based on the fusion of transformer and multi-head dilated convolution. The newly designed multi-head dilated convolution module is sequentially integrated into the transformer-encoder architecture, constructing a feature extraction module where the complementary advantages of both components enhance overall performance. Firstly, the sample is expanded into a two-dimensional feature map and then input into the newly designed feature extraction module. Finally, the diagnostic output is performed by the designed patch feature fusion module and classifier module. Additionally, interpretability research is conducted on the proposed model, aiming to understand the decision-making mechanism of the model through visual analysis of the entire decision process. The experimental results on three different datasets indicate that the proposed model achieved high accuracy in fault diagnosis with relatively short data windows. The highest accuracy reached 97.95%, which was up to 10.97% higher than other models. Furthermore, the feasibility of the model is also verified in the actual dataset of the rotating parts of the injection molding machine. The excellent performance of the model on different datasets demonstrates its effectiveness in extracting comprehensive fault feature information and also proves its great potential in practical industrial applications.

Facile minocycline deployment in gingiva using a dissolvable microneedle patch for the adjunctive treatment of periodontal disease

AbstractMinocycline is a commonly used drug for adjunctive therapy in periodontal disease. However, the current mainstream local medications primarily rely on intra‐pocket administration, which, while avoiding the side effects of traditional systemic drugs, presents challenges such as inconvenience, discomfort, and the need for professional assistance, thus affecting patient compliance. Herein, we introduce a minocycline‐loaded dissolvable microneedle (Mino‐DMN) patch that allows for local and efficient delivery of minocycline to gingiva for the treatment of periodontitis. A two‐step casting micro‐molding process involving vacuum drying and freeze drying is employed to concentrate minocycline in the microneedle part and limit its diffusion into the patch backing. The resulting Mino‐DMN patch features an array of minocycline‐enriched gelatin MNs with a porous HA patch backing. The microneedles can penetrate into gingiva with enough mechanical strength and quickly release minocycline into the gingival tissue, ensuring prolonged local residence of the drug and minimizing its loss to saliva. In vivo experiments show Mino‐DMN inhibits pro‐inflammatory factors, promotes anti‐inflammatory factors, and stimulates bone formation, surpassing topical application and comparable to the inconvenient and discomfort administration of Periocline®. This proposed Mino‐DMN offers a simple, efficient, user‐friendly strategy for the adjunctive treatment of periodontal disease.

Intelligent microneedle patch based on functionalized alginate and chitosan for long-term self-regulated insulin delivery

Severely diabetic patients need insulin input to maintain the body's glycemic balance. However, traditional injection methods are often associated with poor adherence and an increased risk of hypoglycemia. Microneedle technology offers a promising solution by minimizing pain and trauma during insulin administration. Nonetheless, achieving prolonged glycemic control by microneedle with high insulin loading remains a significant challenge. Herein, we introduce an innovative microneedle patch that draws inspiration from the elegant light-induced blooming of water lily petals. The patch features a glucose-responsive hydrogel network crafted from two modified polysaccharide polymers, which enables the delivery of long-acting insulin without depending on glucose oxidase. By incorporating phenylboronic acid-modified sodium alginate, quaternary ammonium chitosan, and polyvinyl alcohol into a hydrogel matrix, we have created a microneedle system that harbors dynamic borate ester linkages and electrostatic attractions, resulting in heightened sensitivity to blood glucose levels. The electrostatic interaction acts as a relatively stable crosslinking point, balancing the dynamic reproducibility response based on the borate ester bond. This self-adaptive hydrogel can regulate insulin-controlled release by responding to changes in glucose concentration. Herein, we achieved massive insulin loading (20 IU) with long lasting glycaemic control (48 h) in a single treatment of diabetic SD rats.

Pathologist-level diagnosis of ulcerative colitis inflammatory activity level using an automated histological grading method

Background and AimsInflammatory bowel disease (IBD) is a global disease that is evolving with increasing incidence. However, there are few works on computationally assisted diagnosis of IBD based on pathological images. Therefore, based on the UK and Chinese IBD diagnostic guidelines, our study established an artificial intelligence-assisted diagnostic system for histologic grading of inflammatory activity in ulcerative colitis (UC). MethodsWe proposed an efficient deep-learning (DL) method for grading inflammatory activity in whole-slide images (WSIs) of UC pathology. Our model was constructed using 603 UC WSIs from Nanjing Drum Tower Hospital for model train set and internal test set. We collected 212 UC WSIs from Zhujiang Hospital as an external test set. Initially, the pre-trained ResNet50 model on the ImageNet dataset was employed to extract image patch features from UC patients. Subsequently, a multi-instance learning (MIL) approach with embedded self-attention was utilized to aggregate tissue image patch features, representing the entire WSI. Finally, the model was trained based on the aggregated features and WSI annotations provided by senior gastrointestinal pathologists to predict the level of inflammatory activity in UC WSIs. ResultsIn the task of distinguishing the presence or absence of inflammatory activity, the Area Under Curve (AUC) value in the internal test set is 0.863 (95% confidence interval [CI] 0.829, 0.898), with a sensitivity of 0.913 (95% [CI] 0.866, 0.961), and specificity of 0.816 (95% [CI] 0.771, 0.861). The AUC in the external test set is 0.947 (95% confidence interval [CI] 0.939, 0.955), with a sensitivity of 0.889 (905% [CI] 0.837, 0.940), and specificity of 0.858 (95% [CI] 0.777, 0.939). For distinguishing different levels of inflammatory activity in UC, the average Macro-AUC in the internal test set and the external test set are 0.827 (95% [CI] 0.803, 0.850) and 0.908 (95% [CI] 0.882, 0.935). the average Micro-AUC in the internal test set and the external test set are 0.816 (95% [CI] 0.792, 0.840) and 0.898 (95% [CI] 0.869, 0.926). ConclusionsComparative analysis with diagnoses made by pathologists at different expertise levels revealed that the algorithm reached a proficiency comparable to the pathologist with 5 years of experience. Furthermore, our algorithm performed superior to other MIL algorithms.

Transformer based on multi-scale local feature for colon cancer histopathological image classification

Colon cancer histopathological image recognition is an important method in the early screening of colon cancer. At present, most whole slide images (WSIs) classification models only consider the features of a single patch, and do not consider the features of the WSIs region. To expand the receptive field of the patches and obtain its surrounding pathological information, this paper proposes a transformer based on multi-scale local feature for colon cancer histopathological image classification model. The model samples patches based on farthest point sampling (FPS). A multi-scale grouping scheme is also proposed to capture WSI local regions. Then the classification labels, feature information and local area information of sampled patches are embedded into the transformer encoder. In addition, the focal loss function is adopted to solve the problem of unbalanced categories of colon cancer histopathological images. Experimental results demonstrate that our model surpasses competing methods in performance on both hospital colon cancer datasets and The Cancer Genome Atlas(TCGA) colon cancer datasets.

A time patch dynamic attention transformer for enhanced well production forecasting in complex oilfield operations

In the field of oil production, accurately predicting well production is of great significance for optimizing production processes and enhancing economic benefits. However, oil production data generally exhibit characteristics such as high noise, complex distribution, and severe temporal fluctuations, which pose significant challenges to traditional prediction models, thereby limiting their accuracy. To address this issue, this study proposes an innovative Time Patch Dynamic Attention Transformer (TPDAT) model. This model segments the time series data into multiple time patches, extracts local features, and integrates a dynamically fused causal temporal attention mechanism to enhance the recognition of transient events and short-term fluctuations. The TPDAT model comprises the Temporal Patch Feature Extraction (TPF) module and the Dynamic Fusion Causal Temporal Attention (DFCTA) mechanism, effectively capturing multi-scale temporal features and enhancing the modeling of causal relationships during oilfield production. Experiments on the North Sea Volve oilfield dataset show that the TPDAT model significantly outperforms traditional deep learning models in well production prediction, achieves the best performance in model evaluation metrics, and demonstrates strong adaptability to complex data. The results confirm that the TPDAT model improves the accuracy and stability of well production prediction in complex oilfield environments, providing reliable support for oilfield production optimization.

Self-Supervised Representation Distribution Learning for Reliable Data Augmentation in Histopathology WSI Classification.

Multiple instance learning (MIL) based whole slide image (WSI) classification is often carried out on the representations of patches extracted from WSI with a pre-trained patch encoder. The performance of classification relies on both patch-level representation learning and MIL classifier training. Most MIL methods utilize a frozen model pre-trained on ImageNet or a model trained with self-supervised learning on histopathology image dataset to extract patch image representations and then fix these representations in the training of the MIL classifiers for efficiency consideration. However, the invariance of representations cannot meet the diversity requirement for training a robust MIL classifier, which has significantly limited the performance of the WSI classification. In this paper, we propose a Self-Supervised Representation Distribution Learning framework (SSRDL) for patch-level representation learning with an online representation sampling strategy (ORS) for both patch feature extraction and WSI-level data augmentation. The proposed method was evaluated on three datasets under three MIL frameworks. The experimental results have demonstrated that the proposed method achieves the best performance in histopathology image representation learning and data augmentation and outperforms state-of-the-art methods under different WSI classification frameworks. The code is available at https://github.com/lazytkm/SSRDL.

Few-shot anomaly detection using positive unlabeled learning with cycle consistency and co-occurrence features

In industrial manufacturing sites, defect detection is crucial to improve reliability and lower inspection costs. Though prior anomaly detectors have shown success, they rely on large amounts of labeled data. Now, we aim to answer “how to cost-effectively utilize limited data for defect detection?”. Inspired by positive and unlabeled learning and few-shot learning, we propose a Positive Unlabeled learning based Few-shot Anomaly Detection model (PUFAD) that builds a representative memory bank of patch features using the large unlabeled set and few normal samples. Frequently co-occurring patch features in the unlabeled set, and cycle-consistent features between normal and unlabeled samples are regarded as pseudo normal features used for classifier training, including memory bank updates. Given test samples during inference, abnormal samples are detected by comparing the features in the memory bank via density estimation. Our method achieves state-of-the-art performance compared to existing few-shot anomaly detection methods on two benchmarks. This work addresses the real-world challenges of collecting large datasets for visual anomaly detection by proposing a practical solution that requires only a few normal samples and unlabeled data.

Efficient Representation Learning for Generalized Category Discovery

Generalized Category Discovery (GCD) aims to discover and cluster data from previously unseen classes. Numerous studies have delved into GCD; however, they either overlooked the significance of representation learning or naively adapt the contrastive loss from self-supervised learning without further refinements. Therefore, in this paper, we propose a simple yet effective method to address this task. Our first contribution is to design a robust Divide-and-Combine strategy with an improved contrastive loss to generate informative features. Subsequently, in light of the scarce supervised signals, we propose a Neighborhood-based Sampling module based on the analysis of cluster-level alignment and uniformity to better discover novel categories. Ultimately, to boost the model’s ability to learn from unlabeled data, we adopt a fusion training approach utilizing combinational patch features and the deterministic threshold to selectively identify high-confidence samples. We unify these learning processes within a single framework and jointly optimize. Extensive experiments across three general datasets and four fine-grained benchmark datasets show the compelling evidence for the superiority of our proposed method—Efficient Representation Learning for Generalized Category Discovery (ERL4GCD).

Global-local combined features to detect pain intensity from facial expression images with attention mechanism

The estimation of pain intensity is critical for medical diagnosis and treatment of patients. With the development of image monitoring technology and artificial intelligence, automatic pain assessment based on facial expression and behavioral analysis shows a potential value in clinical applications. This paper reports a framework of convolutional neural network with global and local attention mechanism (GLA-CNN) for the effective detection of pain intensity at four-level thresholds using facial expression images. GLA-CNN includes two modules, namely global attention network (GANet) and local attention network (LANet). LANet is responsible for extracting representative local patch features of faces, while GANet extracts whole facial features to compensate for the ignored correlative features between patches. In the end, the global correlational and local subtle features are fused for the final estimation of pain intensity. Experiments under the UNBC-McMaster Shoulder Pain database demonstrate that GLA-CNN outperforms other state-of-the-art methods. Additionally, a visualization analysis is conducted to present the feature map of GLA-CNN, intuitively showing that it can extract not only local pain features but also global correlative facial ones. Our study demonstrates that pain assessment based on facial expression is a non-invasive and feasible method, and can be employed as an auxiliary pain assessment tool in clinical practice.

A Prototype-Based Neural Network for Image Anomaly Detection and Localization

Image anomaly detection and localization perform not only image-level anomaly classification but also locate pixel-level anomaly regions. Recently, it has received much research attention due to its wide application in various fields. This paper proposes ProtoAD, a prototype-based neural network for image anomaly detection and localization. First, the patch features of normal images are extracted by a deep network pre-trained on nature images. Then, the prototypes of the normal patch features are learned by non-parametric clustering. Finally, we construct an image anomaly localization network (ProtoAD) by appending the feature extraction network with L2 feature normalization, a 1×1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1\ imes 1$$\\end{document} convolutional layer, a channel max-pooling, and a subtraction operation. We use the prototypes as the kernels of the 1×1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$1\ imes 1$$\\end{document} convolutional layer; therefore, our neural network does not need a training phase and can conduct anomaly detection and localization in an end-to-end manner. Extensive experiments on two challenging industrial anomaly detection datasets, MVTec AD and BTAD, demonstrate that ProtoAD achieves competitive performance compared to the state-of-the-art methods with a higher inference speed. The code and pre-trained models are publicly available at https://github.com/98chao/ProtoAD.

Hyaluronic acid dissolving microneedle patch loaded with tranexamic acid for melasma treatment

Melasma is an acquired hypermelanotic condition characterized by the presence of irregular light-to-dark brown macules that primarily manifest on the sun-exposed areas of the skin, particularly the face. The management of melasma poses significant challenges, as it is often recalcitrant to treatment and tends to recur despite successful treatment. In this study, we explored a safe, easy, and effective melasma treatment strategy. A hyaluronic acid (HA)-based microneedle (MN) patch loaded with tranexamic acid (TXA) was designed to deliver the necessary medication for melasma treatment. The MN patch features uniform needles with adequate mechanical strength and effective penetration and solubility in the skin without cytotoxicity. Remarkably, these MNs substantially reduce the thickness of the epidermis of melasma mice, curtail melanin production, and diminish dopachrome tautomerase (DCT) expression.

Multi-model feature aggregation for classification of laser welding images with vision transformer

The laser welding technique is quite common in various manufacturing lines, including those for lithium-ion power batteries, due to its remarkable productivity, effectiveness, and flexibility. However, it has been observed that the consistency of the welding quality is not always optimal. This study investigates the adoption of laser welding in the manufacturing of lithium-ion batteries, such as their anode, cathode and safety vent, where consistent weld quality is crucial for battery performance and safety. Therefore, evaluating the laser-welding product is indispensable for industrial production and the public domain. Several techniques have been utilized for laser welding evaluation, both destructive and non-destructive. However, these methods are ineffective and too cumbersome to be adopted in mass manufacturing. In contrast, a machine vision strategy has recently been adopted to distinguish between successful and unsuccessful laser welding items. This opened new perspectives for evaluating the quality of the laser welding product using digital image techniques. However, these methods cannot deliver outstanding performance across multiple laser-welding products and achieve optimal classification accuracy. Deep learning has evolved remarkably in recent years and gained popularity in detecting welding defects. This paper presents the observation of a Hybrid Vision Transformer (HViT) to classify the laser welding images corresponding to their feature patch images based on multi-model feature aggregation. The VGG-16 and MobileNet, which were pre-trained on ImageNet, were utilized as the core models to extract the rich features of the laser welding image. To integrate these features, the squeeze excitation module (SE) was utilized, and a multi-layer perception (MLP) approach with a label smoothing optimizer was used for classification. To determine the effectiveness of the proposed strategy, a comparative analysis was conducted with a multitude of alternative machine learning and deep learning approaches. The results indicate that the proposed strategy surpasses all other methods in terms of classification accuracy and evaluation metrics on the test dataset.

Patch-based tendency camera multi-constraint learning for unsupervised person re-identification

Unsupervised person re-identification (ReID) is a task that aims to retrieve pedestrians across different cameras from unlabeled data. Existing methods rely on clustering to generate pseudo-labels, but they are inevitably noisy. Although pseudo-label refinement approaches have been presented, the essentiality of patch contours is ignored. The tendency analysis of retrieval between global and patch features has not been well investigated. In this paper, we propose a Patch-based Tendency Camera Multi-Constraint Learning (PTCML) model for unsupervised person ReID. First, to explore the tendentious retrieval of global and patch features, we design a Ranking Tendency Similarity (RTS) score by gauging the distribution discrepancy of distance changes. Second, based on RTS score, we propose a Tendency-based Mutual Complementation (TMC) loss to improve the quality of global and patch pseudo-labels. Third, to resist camera variations, we propose an Adaptive Camera Multi-Constraint (ACM) loss to optimize recognition results with camera distribution constraint and instance constraint simultaneously. Finally, numerous experiments on Market-1501 and MSMT17 demonstrate that our method can significantly surpass the state-of-the-art performance.

Convolutional neural network with parallel convolution scale attention module and ResCBAM for breast histology image classification

Breast cancer is the most common cause of female morbidity and death worldwide. Compared with other cancers, early detection of breast cancer is more helpful to improve the prognosis of patients. In order to achieve early diagnosis and treatment, clinical treatment requires rapid and accurate diagnosis. Therefore, the development of an automatic detection system for breast cancer suitable for patient imaging is of great significance for assisting clinical treatment. Accurate classification of pathological images plays a key role in computer-aided medical diagnosis and prognosis. However, in the automatic recognition and classification methods of breast cancer pathological images, the scale information, the loss of image information caused by insufficient feature fusion, and the enormous structure of the model may lead to inaccurate or inefficient classification. To minimize the impact, we proposed a lightweight PCSAM-ResCBAM model based on two-stage convolutional neural network. The model included a Parallel Convolution Scale Attention Module network (PCSAM-Net) and a Residual Convolutional Block Attention Module network (ResCBAM-Net). The first-level convolutional network was built through a 4-layer PCSAM module to achieve prediction and classification of patches extracted from images. To optimize the network's ability to represent global features of images, we proposed a tiled feature fusion method to fuse patch features from the same image, and proposed a residual convolutional attention module. Based on the above, the second-level convolutional network was constructed to achieve predictive classification of images. We evaluated the performance of our proposed model on the ICIAR2018 dataset and the BreakHis dataset, respectively. Furthermore, through model ablation studies, we found that scale attention and dilated convolution play an important role in improving model performance. Our proposed model outperforms the existing state-of-the-art models on 200 × and 400 × magnification datasets with a maximum accuracy of 98.74 %.

Evaluation of strength and stiffness degradation of RC shear walls: An integrated image processing and deep learning approach

AbstractIn the aftermath of an earthquake, damage detection and performance evaluation of structural components are imperative for assessing the residual seismic capacity of a building. In this study, an integrated image processing and deep learning approach was developed to evaluate the degradation in strength and stiffness (i.e., strength reduction and stiffness reduction) of reinforced concrete (RC) shear walls. The approach comprised two main tasks: detecting and localizing visible seismic damage from photographs and evaluating strength and stiffness degradation based on this information. The semantic segmentation network, Damage‐Net, was used for damage detection and localization. A novel crack morphological processing layer and a patch feature extraction layer were developed for damage feature extraction and compression. A lightweight deep convolutional neural network named DegradeEval‐Net_v2, featuring the upgraded dilated and separable convolution block and multi‐layer perception, was developed to link the damage feature with strength and stiffness degradation. A database comprising test data and photographs of 14 RC shear wall specimens with a flexural‐dominated behavior mode and high to intermediate ductility was constructed to train and test the DegradeEval‐Net_v2 network. The results indicate that DegradeEval‐Net_v2 substantially improved the performance assessment accuracy of damaged RC shear walls, with a 35% smaller root mean square error (RMSE) for stiffness degradation evaluation and 75% smaller RMSE for strength degradation evaluation, compared with the provisions specified in JBDPA and FEMA guidelines. Moreover, evaluation results on test sets demonstrate that introducing the damage feature extraction and compression layers effectively preserved local crack information and improved the accuracy with which stiffness reduction was evaluated. In addition, DegradeEval‐Net_v2 outperformed ResNet18 and MobileNet V3 in terms of balanced efficiency and accuracy. Interpretability analysis demonstrates that the model learned the distinct contribution patterns of various visible damage indexes to stiffness and strength degradation across different loading levels.

Measuring canopy morphology of saltmarsh plant patches using UAV-based LiDAR data

Plant patches play a crucial role in understanding the biogeomorphology of saltmarshes. Although two-dimensional optical remote sensing has long been applied to the study of saltmarsh plant patches, studies focusing on the canopy features at a patch-scale remain limited. Therefore, a simple and efficient method is needed to capture three-dimensional patch features and their relationship to habitat. This study utilized UAV-based LiDAR to obtain three-dimensional patch features of the native species S. mariqueter and the invasive species S. alterniflora in Andong Shoal, Hangzhou Bay, and examine the relationship between patch distribution and geomorphological characteristics. A workflow was established to overcome the inability of low-cost LiDAR sensor to penetrate dense vegetation, resulting in no ground return. Results showed that S. alterniflora patches were smaller in size but taller in canopy height than S. mariqueter patches. Regarding morphological patterns of patch canopy, S. alterniflora exhibited single-arch patterns (29%) and double-arch patterns (16%), whereas S. mariqueter exhibited only single-arch patterns (83%). The presence of double-arch patches suggested the development of fairy circles, indicating that the invasive S. alterniflora exhibits greater ecological resilience compared to the native S. mariqueter. Furthermore, this study explored the ecological niches of the two species in the pioneer zone of Andong Shoal. The ecological niches for S. alterniflora were 2.00-2.25 m, whereas that for S. mariqueter were 1.85-2.00 m and 2.25-2.40 m. Distance from the tidal creeks significantly moderated the number and area of patches for both species. This study demonstrated that UAV-based LiDAR technology can provide high-quality three-dimensional information about the pioneer zone of saltmarsh, thus helping to understand biogeomorphological processes in this region.

Classification of Chest CT Lung Nodules Using Collaborative Deep Learning Model.

Early detection of lung cancer through accurate diagnosis of malignant lung nodules using chest CT scans offers patients the highest chance of successful treatment and survival. Despite advancements in computer vision through deep learning algorithms, the detection of malignant nodules faces significant challenges due to insufficient training datasets. This study introduces a model based on collaborative deep learning (CDL) to differentiate between cancerous and non-cancerous nodules in chest CT scans with limited available data. The model dissects a nodule into its constituent parts using six characteristics, allowing it to learn detailed features of lung nodules. It utilizes a CDL submodel that incorporates six types of feature patches to fine-tune a network previously trained with ResNet-50. An adaptive weighting method learned through error backpropagation enhances the process of identifying lung nodules, incorporating these CDL submodels for improved accuracy. The CDL model demonstrated a high level of performance in classifying lung nodules, achieving an accuracy of 93.24%. This represents a significant improvement over current state-of-the-art methods, indicating the effectiveness of the proposed approach. The findings suggest that the CDL model, with its unique structure and adaptive weighting method, offers a promising solution to the challenge of accurately detecting malignant lung nodules with limited data. This approach not only improves diagnostic accuracy but also contributes to the early detection and treatment of lung cancer, potentially saving lives.

MGRR-Net: Multi-level Graph Relational Reasoning Network for Facial Action Unit Detection

The Facial Action Coding System (FACS) encodes the action units (AUs) in facial images, which has attracted extensive research attention due to its wide use in facial expression analysis. Many methods that perform well on automatic facial action unit (AU) detection primarily focus on modeling various AU relations between corresponding local muscle areas or mining global attention–aware facial features; however, they neglect the dynamic interactions among local-global features. We argue that encoding AU features just from one perspective may not capture the rich contextual information between regional and global face features, as well as the detailed variability across AUs, because of the diversity in expression and individual characteristics. In this article, we propose a novel Multi-level Graph Relational Reasoning Network (termed MGRR-Net ) for facial AU detection. Each layer of MGRR-Net performs a multi-level (i.e., region-level, pixel-wise, and channel-wise level) feature learning. On the one hand, the region-level feature learning from the local face patch features via graph neural network can encode the correlation across different AUs. On the other hand, pixel-wise and channel-wise feature learning via graph attention networks (GAT) enhance the discrimination ability of AU features by adaptively recalibrating feature responses of pixels and channels from global face features. The hierarchical fusion strategy combines features from the three levels with gated fusion cells to improve AU discriminative ability. Extensive experiments on DISFA and BP4D AU datasets show that the proposed approach achieves superior performance than the state-of-the-art methods.