Diagnosis Tasks Research Articles

Fault Diagnosis Method of Box-Type Substation Based on Improved Conditional Tabular Generative Adversarial Network and AlexNet

To solve the problem of low diagnostic accuracy caused by the scarcity of fault samples and class imbalance in the fault diagnosis task of box-type substations, a fault diagnosis method based on self-attention improvement of conditional tabular generative adversarial network (CTGAN) and AlexNet was proposed. The self-attention mechanism is introduced into the generator of CTGAN to maintain the correlation between the indicators of the input data, and a large amounts of high-quality data are generated according to the small number of fault samples. The generated data are input into the AlexNet model for fault diagnosis. The experimental results demonstrate that compared with the SMOTE and CTGAN methods, the dataset generated by the self-attention-conditional tabular generative adversarial network (SA-CTGAN) model has better data relevance. The accuracy of fault diagnosis by the proposed method reaches 94.81%, which is improved by about 11% compared with the model trained on the original data.

Advanced digital twin-enabled fault diagnosis framework for unmanned vehicle systems

Abstract The control system of unmanned vehicles must demonstrate strong capability to promptly diagnose and address system faults. Such a capability can improve transportation efficiency, ensure the smooth execution of production tasks, and to a certain extent, mitigate the risk of human casualties. To ensure the upkeep of unmanned vehicles and address the diagnostic requirements of control systems, this study integrates traditional wheeled vehicle control systems with digital twin (DT) technology to establish a framework for control system fault diagnosis and maintenance, with the primary objective of fulfilling the fault diagnosis task. By this framework, a method for detecting faults in unmanned vehicle control systems based on DT technology has been developed. This method involves the design of a data-driven model using multiple sensors and the application of a DT-improved particle filter fault diagnosis algorithm, utilizing a multi-domain model approach. A case study of the proposed method and simulation results are presented to illustrate its feasibility.

Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading

Artificial intelligence (AI) holds significant promise in transforming medical imaging, enhancing diagnostics, and refining treatment strategies. However, the reliance on extensive multicenter datasets for training AI models poses challenges due to privacy concerns. Federated learning provides a solution by facilitating collaborative model training across multiple centers without sharing raw data. This study introduces a federated attention-consistent learning (FACL) framework to address challenges associated with large-scale pathological images and data heterogeneity. FACL enhances model generalization by maximizing attention consistency between local clients and the server model. To ensure privacy and validate robustness, we incorporated differential privacy by introducing noise during parameter transfer. We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19,461 whole-slide images of prostate cancer from multiple centers. In the diagnosis task, FACL achieved an area under the curve (AUC) of 0.9718, outperforming seven centers with an average AUC of 0.9499 when categories are relatively balanced. For the Gleason grading task, FACL attained a Kappa score of 0.8463, surpassing the average Kappa score of 0.7379 from six centers. In conclusion, FACL offers a robust, accurate, and cost-effective AI training model for prostate cancer pathology while maintaining effective data safeguards.

FedCAE: A New Federated Learning Framework for Edge-Cloud Collaboration Based Machine Fault Diagnosis

With the coming of the industrial big data era, data-driven fault diagnosis models emerge recently and show potential results in many studies. However, it is impractical to collect massive high-quality data in actual industrial applications, which strongly reduces the performance of fault diagnosis models. Therefore, multiple data owners are motivated to share their own data for training a brilliant model with the aggregated dataset. Notwithstanding, it is unrealistic to share data due to the potential conflict of interest. For addressing the issue of data island, a new federated framework namely FedCAE is proposed for fault diagnosis. In this framework, each client is equipped with a convolutional autoencoder (CAE) trained by its corresponding local data. Then, all CAEs are uploaded to a server and aggregated to a global CAE according to an adaptive weighted selection mechanism. Afterwards, the global CAE is downloaded to all clients for extracting low-level features from local datasets by its encoder and uploading these features to train a global fault diagnosis classifier in the server. At last, the classifier is downloaded to all clients for completing their own diagnosis tasks. Experiment results on two bearing datasets suggest FedCAE offers a promising solution on confidential decentralized learning.

SAH-NET: Structure-Aware Hierarchical Network for Clustered Microcalcification Classification in Digital Breast Tomosynthesis.

Benign and malignant classification of clustered microcalcifications (MCs) in digital breast tomosynthesis (DBT) is an essential task in computer-aided diagnosis. However, due to the anisotropic resolution of DBT, three-dimensional (3-D) convolutional neural network (CNN)-based methods cannot extract hierarchical features efficiently. Moreover, the sparse distribution of MC points in the cluster makes it difficult for the CNN to extract discriminative structural information for classification. To comprehensively address these challenges, we propose a novel structure-aware hierarchical network (SAH-Net) for benign and malignant classification of clustered MC in a DBT volume. Specifically, the two-dimensional (2-D) group convolution is used to extract intraslice features. The one-to-one correspondence between group convolutions and slices ensures the independence of hierarchical feature extraction. Then, a partial deformable Transformer-based 3-D structural feature learning module is proposed to capture the long-range dependency between MC points in the cluster. We evaluate the proposed method on an in-house dataset with 495 clustered MCs collected from 462 DBT images. Experimental results confirm the validity of our proposed modules. The results also show that the proposed SAH-Net outperforms several other representative methods on this topic, and achieves the best classification result, with an area under the receiver operation curve (AUC) of 86.87%. The implementation of the proposed model is available at https://github.com/sunhaotian130911/SAHNet.

Connectional-Style-Guided Contextual Representation Learning for Brain Disease Diagnosis

Structural magnetic resonance imaging (sMRI) has shown great clinical value and has been widely used in deep learning (DL) based computer-aided brain disease diagnosis. Previous DL-based approaches focused on local shapes and textures in brain sMRI that may be significant only within a particular domain. The learned representations are likely to contain spurious information and have poor generalization ability in other diseases and datasets. To facilitate capturing meaningful and robust features, it is necessary to first comprehensively understand the intrinsic pattern of the brain that is not restricted within a single data/task domain. Considering that the brain is a complex connectome of interlinked neurons, the connectional properties in the brain have strong biological significance, which is shared across multiple domains and covers most pathological information. In this work, we propose a connectional style contextual representation learning model (CS-CRL) to capture the intrinsic pattern of the brain, used for multiple brain disease diagnosis. Specifically, it has a vision transformer (ViT) encoder and leverages mask reconstruction as the proxy task and Gram matrices to guide the representation of connectional information. It facilitates the capture of global context and the aggregation of features with biological plausibility. The results indicate that CS-CRL achieves superior accuracy in multiple brain disease diagnosis tasks across six datasets and three diseases and outperforms state-of-the-art models. Furthermore, we demonstrate that CS-CRL captures more brain-network-like properties, and better aggregates features, is easier to optimize, and is more robust to noise, which explains its superiority in theory.

사립대학 재정진단의 쟁점과 과제

The sharp decline in the school-age population is deepening the financial crisis in private universities, along with a tuition freeze that has lasted for over 15 years. To overcome this, legislative support is very important to improve the quality of Korean university education through financial diagnosis of private universities and structural improvement. In this context, this paper attempted to discuss the current issues and tasks of financial diagnosis on private universities. Firstly, the issues of financial diagnosis on private universities, the structure and progress of financial diagnosis on private universities, and the efforts to enact the ｢Act on Support for Structural Improvement of Private Universities｣ were summarized, and the issues and tasks of financial diagnosis on private universities were discussed based on this discussion. The methods of this study are literature and data analysis. However, regarding the issues, the opinions of five experts in charge of financial diagnosis at private universities were collected. Issues and tasks were discussed by dividing them into macro, micro, and legal dimensions. The main conclusion is as follows. First, it should not stop at classifying it as a business crisis university through a financial diagnosis of private universities, and various support is required. Second, above all, legislative support for improving the university structure is very important. Third, it is necessary to clarify the procedure for confirming the approval of the financial diagnosis by the university so that the reliability and procedural justification of the financial diagnosis results can be secured. Fourth, the results of the financial diagnosis of private universities should be notified to all private universities. Fifth, it is necessary to continuously determine whether private universities fall under the financial crisis so that the final decision can be made.

FedDUS: Lung tumor segmentation on CT images through federated semi-supervised with dynamic update strategy

Background and ObjectiveLung tumor annotation is a key upstream task for further diagnosis and prognosis. Although deep learning techniques have promoted automation of lung tumor segmentation, there remain challenges impeding its application in clinical practice, such as a lack of prior annotation for model training and data-sharing among centers. MethodsIn this paper, we use data from six centers to design a novel federated semi-supervised learning (FSSL) framework with dynamic model aggregation and improve segmentation performance for lung tumors. To be specific, we propose a dynamically updated algorithm to deal with model parameter aggregation in FSSL, which takes advantage of both the quality and quantity of client data. Moreover, to increase the accessibility of data in the federated learning (FL) network, we explore the FAIR data principle while the previous federated methods never involve. ResultThe experimental results show that the segmentation performance of our model in six centers is 0.9348, 0.8436, 0.8328, 0.7776, 0.8870 and 0.8460 respectively, which is superior to traditional deep learning methods and recent federated semi-supervised learning methods. ConclusionThe experimental results demonstrate that our method is superior to the existing FSSL methods. In addition, our proposed dynamic update strategy effectively utilizes the quality and quantity information of client data and shows efficiency in lung tumor segmentation. The source code is released on (https://github.com/GDPHMediaLab/FedDUS).

Depression Detection via Capsule Networks with Contrastive Learning

Depression detection is a challenging and crucial task in psychological illness diagnosis. Utilizing online user posts to predict whether a user suffers from depression seems an effective and promising direction. However, existing methods suffer from either poor interpretability brought by the black-box models or underwhelming performance caused by the completely separate two-stage model structure. To alleviate these limitations, we propose a novel capsule network integrated with contrastive learning for depression detection (DeCapsNet). The highlights of DeCapsNet can be summarized as follows. First, it extracts symptom capsules from user posts by leveraging meticulously designed symptom descriptions, and then distills them into class-indicative depression capsules. The overall workflow is in an explicit hierarchical reasoning manner and can be well interpreted by the Patient Health Questionnaire-9 (PHQ9), which is one of the most widely adopted questionnaires for depression diagnosis. Second, it integrates with contrastive learning, which can facilitate the embeddings from the same class to be pulled closer, while simultaneously pushing the embeddings from different classes apart. In addition, by adopting the end-to-end training strategy, it does not necessitate additional data annotation, and mitigates the potential adverse effects from the upstream task to the downstream task. Extensive experiments on three widely-used datasets show that in both within-dataset and cross-dataset scenarios our proposed method outperforms other strong baselines significantly.

Combining graph neural networks and computer vision methods for cell nuclei classification in lung tissue

The detection of tumoural cells from whole slide images is an essential task in medical diagnosis and research. In this article, we propose and analyse a novel approach that combines computer vision-based models with graph neural networks to improve the accuracy of automated tumoural cell detection in lung tissue. Our proposal leverages the inherent structure and relationships between cells in the tissue. Experimental results on our own curated dataset show that modelling the problem with graphs gives the model a clear advantage over just working at pixel level. This change in perspective provides extra information that makes it possible to improve the performance. The reduction of dimensionality that comes from working with the graph also allows us to increase the field of view with low computational requirements. Code is available at https://github.com/Jerry-Master/lung-tumour-study, models are uploaded to https://huggingface.co/Jerry-Master/Hovernet-plus-Graphs, and the dataset is published on Zenodo https://zenodo.org/doi/10.5281/zenodo.8368122.

Spectral boundary detecting model: A promising tool for adaptive mode extraction and machinery fault diagnosis

Extraction of weak transients is vital for realizing the early machinery fault diagnosis. However, a significant challenge lies in an efficient determination of the spectral boundaries of expected modes for excluding interferential information. Through a new perspective exploration on the fundamental principle of variational mode decomposition, we find a relevance between the filtering structure of variational model and the shape of fault-induced features in spectral domain. Then, we propose a spectral boundary detecting model (SBDM) to identify fault-induced transients efficiently. SBDM comprises three steps. First, spectral structural features of analysis signal are quickly detected based on the found relevance. Second, spectral boundaries with expected modes are calculated based on the located spectral structural features. Third, a filter bank designed on the spectral boundaries is used to extract the expected modes. Furthermore, our SBDM is extended by two observed valuable phenomena to obtain a comprehensive result for downstream diagnosis tasks. Finally, an extended SBDM-based diagnosis procedure is presented for the machinery fault identification. Two experimental cases have validated that our SBDM outperforms eight advanced methods in the machinery fault diagnosis.

A recursive multi-head self-attention learning for acoustic-based gear fault diagnosis in real-industrial noise condition

Acoustic-based diagnosis (ABD) is a promising method for rotating machinery fault detection in real-industrial fields due to its advantage of non-contact measurement by air-couple. However, most ABD methods, which rely on single function module of denoising or anti-noise diagnosis, lacks sufficient ability against the strong and highly non-stationary background noise interference in practical industrial application. To deal with the obstacle, a novel two-stage ABD system, which performs denoising and anti-noise diagnosis in a step-by-step fashion, is proposed in this paper. In our method, the denoising sub-system can adaptively track and suppress real-industrial background noise from collected multi-channel signal by our designed recursive multi-head self-attention (RMHSA) mechanism, which take into account the global and long-range information of signal to recursively exclude noise component at each position in signal sequence for overcoming the limitation of traditional method in balancing denoising performance and computational complexity and discontinuity in diagnosis procedure. Subsequently, a novel anti-noise method is explored to automatically track the residual noise components after initial suppression and estimating the noise interference probability within time-frequency (T-F) unit of each signal sample by our designed spatial multi-head self-attention (SMHSA) mechanism in recursive manner. Simultaneously, the anti-noise protocol interacts with diagnosis model based on estimated probability in anti-noise diagnosis sub-system to further improve the diagnosis performance of ABD system under the interference of background noise. Experiment result in both real-industrial noise condition and simulated noise conditions with extremely worse SNRs indicate that the proposed two-stage ABD system is effective in dealing with gear fault diagnosis task under noise condition.

An Analysis of the WPT Function for Pattern Optimization to Detect Defects in Bearings

New trends in maintenance techniques are oriented to digitization and prognosis. The new electronic devices based on IoT (Internet of Things) technology among others that support the industry 4.0 paradigm let enhance the traditional condition monitoring techniques to better understand and predict the state of a machine in service. Related to maintenance applications, one of the important steps in condition monitoring tasks for fault diagnosis is the selection of the optimal pattern to provide accurate results (avoiding fault positives/negatives) with adequate computation time. When implementing this, the selection of optimal parameters and thresholds for setting alarms are important to detect problems in the machine before the failure occurs. Vibratory signals have been proved to be a good variable to determine their mechanical behavior. Nevertheless, parameters obtained from time domain measurements are not computationally efficient nor good patterns to compare different machine conditions. In this sense, tools that represent the frequency domain or time–frequency domain have been useful to detect defects in rotating elements such as bearings. In this work, defects in ball bearings are studied using wavelet packet transform. For this, a methodology will be developed for the optimal selection of the mother wavelet, incorporating intelligent classification systems, and using a medium Gaussian support vector machine model. In this way, it will be verified that the correct selection of this function influences both the results and the ease and reliability of detection. The results using the selected mother wavelet will be compared to those using Daubechies 6, since it is the mother wavelet that has been used in previous works and which was selected based on experience. For it, vibratory signals are obtained from a testbench with different bearing conditions: healthy bearings and defective bearings (inner and outer race).

Deep adaptive sparse residual networks: A lifelong learning framework for rotating machinery fault diagnosis with domain increments

Rotating machinery operates continuously for long periods of time under varying conditions in actual industrial environments. The number of fault samples increases with equipment operating time, whereas differences in data distribution are inevitable because of varying operating conditions. As a result, fault diagnosis of rotating machinery poses challenges related to the fault domain increments. In addition, the issue of catastrophic forgetting, where previously learned knowledge significantly affects the model's performance, remains a critical concern. Deep adaptive sparse residual network (DASRN), a new lifelong learning-based method, is proposed to overcome these challenges. The DASRN model is constructed based on an improved deep residual network. The model uses a task-aware dynamic masking strategy to adjust the retention and utilization of blank weights in the network, thereby balancing the model's memory and learning capabilities, mitigating catastrophic forgetting. Furthermore, throughout the entire training process of the model, a dynamic data removal strategy is applied to eliminate easily distinguishable samples. This approach adaptively allocates higher weights to more challenging samples, enhancing the model's learning efficiency while consolidating the sparsity within the model. Finally, the effectiveness of the proposed DASRN is validated on bearing datasets from the Chinese CRH380A high-speed train gearbox and integrated wheelset transmission test rig. Results demonstrate that DASRN provides an effective solution for catastrophic forgetting and domain incremental scenarios in rotating machinery fault diagnosis tasks.

Robust transfer subspace learning based on low-rank and sparse representation for bearing fault diagnosis

With the development of industrial intelligence, data-driven fault diagnosis plays an important role in prognostics and health management. However, there is usually a large amount of unlabeled data from different working conditions, making cross-domain fault diagnosis unstable and inflexible. To deal with this issue, we propose two novel transfer subspace learning methods based on the low-rank sparse representation (LRSR), called LRSR-G and LRSR-R. Specifically, LRSR-G integrates an additional matrix with LRSR to characterize the Gaussian noise for robustness, as well as capture global and local structures. Furthermore, LRSR-R adaptively learns the label matrix from samples instead of using the binary labeling matrix in LRSR-G, thus providing the possibility to improve the flexibility. In addition, we develop two efficient algorithms using the alternating direction method of multipliers to solve the proposed LRSR-G and LRSR-R. Extensive experiments are conducted on the Case Western Reserve University dataset and Jiangnan University (JNU) dataset. The results show that the proposed LRSR-G and LRSR-R perform better than the existing methods, while LRSR-R has more potential in cross-domain fault diagnosis tasks.

Breaking boundaries in radiology: redefining AI diagnostics via raw data ahead of reconstruction

Objective. In the realm of utilizing artificial intelligence (AI) for medical image analysis, the paradigm of ‘signal-image-knowledge’ has remained unchanged. However, the process of ‘signal to image’ inevitably introduces information distortion, ultimately leading to irrecoverable biases in the ‘image to knowledge’ process. Our goal is to skip reconstruction and build a diagnostic model directly from the raw data (signal). Approach. This study focuses on computed tomography (CT) and its raw data (sinogram) as the research subjects. We simulate the real-world process of ‘human-signal-image’ using the workflow ‘CT-simulated data- reconstructed CT,’ and we develop a novel AI predictive model directly targeting raw data (RCTM). This model comprises orientation, spatial, and global analysis modules, embodying the fusion of local to global information extraction from raw data. We selected 1994 patients with retrospective cases of solid lung nodules and modeled different types of data. Main results. We employed predefined radiomic features to assess the diagnostic feature differences caused by reconstruction. The results indicated that approximately 14% of the features had Spearman correlation coefficients below 0.8. These findings suggest that despite the increasing maturity of CT reconstruction algorithms, they still introduce perturbations to diagnostic features. Moreover, our proposed RCTM achieved an area under the curve (AUC) of 0.863 in the diagnosis task, showcasing a comprehensive superiority over models constructed from secondary reconstructed CTs (0.840, 0.822, and 0.825). Additionally, the performance of RCTM closely resembled that of models constructed from original CT scans (0.868, 0.878, and 0.866). Significance. The diagnostic and therapeutic approach directly based on CT raw data can enhance the precision of AI models and the concept of ‘signal-to-image’ can be extended to other types of imaging. AI diagnostic models tailored to raw data offer the potential to disrupt the traditional paradigm of ‘signal-image-knowledge’, opening up new avenues for more accurate medical diagnostics.

Investigating the efficacy and importance of mobile-based assessments for Parkinson's disease: uncovering the potential of novel digital tests

This study introduces PDMotion, a mobile application comprising 11 digital tests, including those adapted from the MDS-Unified Parkinson's Disease Rating Scale (MDS-UPDRS) Part III and novel assessments, for remote Parkinson's Disease (PD) motor symptoms evaluation. Employing machine learning techniques on data from 50 PD patients and 29 healthy controls, PDMotion achieves accuracies of 0.878 for PD status prediction and 0.715 for severity assessment. A post-hoc explanation model is employed to assess the importance of features and tasks in diagnosis and severity evaluation. Notably, novel tasks that are not adapted from MDS-UPDRS Part III like the circle drawing, coordination test, and alternative tapping test are found to be highly important, suggesting digital assessments for PD can go beyond digitizing existing tests. The alternative tapping test emerges as the most significant task. Using its features alone achieves prediction accuracies comparable to the full task set, underscoring its potential as an independent screening tool. This study addresses a notable research gap by digitalizing a wide array of tests, including novel ones, and conducting a comparative analysis of their feature and task importance. These insights provide guidance for task selection and future development in PD mobile assessments, a field previously lacking such comparative studies.

Deep Multi-Instance Conv-Transformer Frameworks for Landmark-Based Brain MRI Classification

For brain diseases, e.g., autism spectrum disorder (ASD), with unclear biological characteristics, the detection of imaging-based biomarkers is a critical task for diagnosis. Several landmark-based categorization approaches have been developed for the computer-aided diagnosis of brain diseases, such as Alzheimer’s disease (AD), utilizing structural magnetic resonance imaging (sMRI). With the automatic detection of the landmarks of brain disease, more detailed brain features were identified for clinical diagnosis. Multi-instance learning is an effective technique for classifying brain diseases based on landmarks. The multiple-instance learning approach relies on the assumption of independent distribution hypotheses and is mostly focused on local information, thus the correlation among different brain regions may be ignored. However, according to previous research on ASD and AD, the abnormal development of different brain regions is highly correlated. Vision Transformers, with self-attention modules to capture the relationship between embedded patches from a whole image, have recently demonstrated superior performances in many computer vision tasks. Nevertheless, the utilization of 3D brain MRIs imposes a substantial computational load, especially while training with Vision Transformer. To address the challenges mentioned above, in this research, we proposed a landmark-based multi-instance Conv-Transformer (LD-MILCT) framework as a solution to the aforementioned issues in brain disease diagnosis. In this network, a two-stage multi-instance learning strategy was proposed to explore both spatial and morphological information between different brain regions; the Vision Transformer utilizes a multi-instance learning head (MIL head) to fully utilize the features that are not involved in the ultimate classification. We assessed our proposed framework using T1-weighted MRI images from both AD and ASD databases. Our method outperformed existing deep learning and landmark-based methods in terms of brain MRI classification tasks.

Improved deep residual shrinkage network for a multi-cylinder heavy-duty engine fault detection with single channel surface vibration

The health monitoring and fault diagnosis of heavy-duty engines are increasingly important for energy storage ecosystem. During operation, vibration characters corresponding to the specific fault need to be extracted from the overall system vibration. Faulty characteristics emanating from one single cylinder are also mixed with those from other cylinders. Besides, the change of working condition brings strong nonlinearities in surface vibration. To solve these problems, an improved deep residual shrinkage network (IDRSN) is developed for detecting diverse engine faults at various degrees using single channel surface vibration signal. Within IDRSN, a wide convolution kernel is utilized in first convolution layer to capture the long-term fault-related impacts and eliminate the short-time random impact. The residual network module is adopted to enhance the focus the relevant components of vibration signals. Mini-batch training strategy is used to improve the model stability. Meanwhile, Gradient-weighted class activation map is adopted to assess the consistency between the learned knowledge and the fault-related information. The IDRSN is implemented to diagnosing a diesel engine under various faults, faulty degrees and operating speeds. Comparisons with existing models are analyzed in terms of hyper-parameters, training samples, noise resistance, and visualization. Results demonstrate the proposed IDRSN's superior performance on fault diagnosis accuracy, stability, anti-noise performance, and anti-interference performance. An average accuracy rate of 98.38 % was achieved by the proposed IDRSN, in comparison to 96.64 % and 93.56 % achieved by the DRSN and the wide-kernel deep convolutional neural network respectively. These results highlight the proposed IDRSN's superiority in diagnosing multiple faults under various working conditions, offering a low-cost, highly effective, and applicable approach for complex fault diagnosis tasks.

LGDNet: local feature coupling global representations network for pulmonary nodules detection.

Detection of suspicious pulmonary nodules from lung CT scans is a crucial task in computer-aided diagnosis (CAD) systems. In recent years, various deep learning-based approaches have been proposed and demonstrated significant potential for addressing this task. However, existing deep convolutional neural networks exhibit limited long-range dependency capabilities and neglect crucial contextual information, resulting in reduced performance on detecting small-size nodules in CT scans. In this work, we propose a novel end-to-end framework called LGDNet for the detection of suspicious pulmonary nodules in lung CT scans by fusing local features and global representations. To overcome the limited long-range dependency capabilities inherent in convolutional operations, a dual-branch module is designed to integrate the convolutional neural network (CNN) branch that extracts local features with the transformer branch that captures global representations. To further address the issue of misalignment between local features and global representations, an attention gate module is proposed in the up-sampling stage to selectively combine misaligned semantic data from both branches, resulting in more accurate detection of small-size nodules. Our experiments on the large-scale LIDC dataset demonstrate that the proposed LGDNet with the dual-branch module and attention gate module could significantly improve the nodule detection sensitivity by achieving a final competition performance metric (CPM) score of 89.49%, outperforming the state-of-the-art nodule detection methods, indicating its potential for clinical applications in the early diagnosis of lung diseases.