Combination Of Convolutional Neural Network Research Articles

Development of a CNN-LSTM Approach with Images as Time-Series Data Representation for Predicting Gold Prices

Predicting gold prices is not easy due to its non-linear, unpredictable, volatile, and uncontrollable price movements. In this research, a combination of convolutional neural network (CNN) and long short-term memory (LSTM) is used to predict gold prices. By combining these two methods, the prediction model can leverage the strengths of CNN and LSTM to improve accuracy and learning performance. In addition, this CNN-LSTM model is enriched with input in the form of images that represent the timeseries data, where the gramian angular field (GAF) technique is used in timeseries data to images transformation. Experimental results showed that the proposed approach performs significantly better compared to the benchmark model.

Prototype Learning Guided Hybrid Network for Breast Tumor Segmentation in DCE-MRI.

Automated breast tumor segmentation on the basis of dynamic contrast-enhancement magnetic resonance imaging (DCE-MRI) has shown great promise in clinical practice, particularly for identifying the presence of breast disease. However, accurate segmentation of breast tumor is a challenging task, often necessitating the development of complex networks. To strike an optimal tradeoff between computational costs and segmentation performance, we propose a hybrid network via the combination of convolution neural network (CNN) and transformer layers. Specifically, the hybrid network consists of a encoder-decoder architecture by stacking convolution and deconvolution layers. Effective 3D transformer layers are then implemented after the encoder subnetworks, to capture global dependencies between the bottleneck features. To improve the efficiency of hybrid network, two parallel encoder sub-networks are designed for the decoder and the transformer layers, respectively. To further enhance the discriminative capability of hybrid network, a prototype learning guided prediction module is proposed, where the category-specified prototypical features are calculated through online clustering. All learned prototypical features are finally combined with the features from decoder for tumor mask prediction. The experimental results on private and public DCE-MRI datasets demonstrate that the proposed hybrid network achieves superior performance than the state-of-the-art (SOTA) methods, while maintaining balance between segmentation accuracy and computation cost. Moreover, we demonstrate that automatically generated tumor masks can be effectively applied to identify HER2-positive subtype from HER2-negative subtype with the similar accuracy to the analysis based on manual tumor segmentation. The source code is available at https://github.com/ZhouL-lab/ PLHN.

Enhancing Diagnostic Accuracy with Ensemble Techniques: Detecting COVID-19 and Pneumonia on Chest X-Ray Images

Lung diseases such as COVID-19 and pneumonia can lead to breathing difficulties, decreased lung function, and respiratory failure, leading to death if not treated immediately. Chest X-ray imaging techniques are quick, effective, and inexpensive in controlling many of these diseases. Artificial intelligence has shown promising results in detecting many diseases, including lung diseases, as it can analyze large sets of data in a short time, which leads to causes reducing the spread of these diseases. Artificial intelligence with the help of deep learning and machine learning is a milestone in modern biomedical research, offering major advances in various medical research disciplines. In this research paper, we introduced various advanced ensemble techniques as bagging, boosting, stacking, and blending with different algorithms, to enhance the performance of our classification models in detecting coronavirus and pneumonia. We specifically focused on combining convolutional neural network (CNN) and vision transformer (ViT) models to create powerful ensemble models. Our objective was to determine the most accurate ensemble technique for diagnosing lung diseases. We assessed their ability to correctly classify chest X-ray images as either COVID-19, pneumonia, or normal. The CatBoost algorithm achieved the highest accuracy of 99.753% using the COVID-19 Radiography dataset and the bagging ensemble model achieved the highest accuracy of 95.08% using 5 different publicly available data (COVIDx CXR-4). The results indicate that the advanced ensemble techniques can significantly improve the performance of machine learning models.

Hybrid model of convolutional neural network and long short term memory for heart disease prediction

<span>Data mining is a process that assists in uncovering meaningful data from large, disorganized datasets. This research is being conducted to predict heart disorders by using available data to make predictions for the future. The approach is carried out in several stages, such as pre-processing the data, extracting relevant features, and classifying the data. all of these steps are essential for predicting heart disease. The deep learning models is already proposed by the researches for the heart disease prediction. This work introduces a hybrid deep learning model that combines convolutional neural network (CNN) and long short-term memory (LSTM) to predict heart disease. The proposed model has been implemented in python, and its accuracy, precision, and recall have been evaluated.</span>

Pclf: Parallel cnn-lstm fusion model for sms spam filtering

Short Message Service (SMS) is widely used for its accessibility, simplicity, and cost-effectiveness in communication, bank notifications, and identity confirmation. The increase in spam text messages presents significant challenges, including time waste, potential financial scams, and annoyance for users and carriers. This paper proposes a novel deep learning model based on parallel structure in the feature extraction step to address this challenge, unlike the traditional models that only enhance the classifier. This parallel model fuses local and temporal features to enhance feature representation by combining convolutional neural networks (CNN) and long short-term memory networks (LSTM). The performance of this model has been evaluated on the UCI SMS Collection V.1 dataset, which comprises both spam and ham messages. The model achieves an accuracy of 99.28% on this dataset. Also, the model demonstrates good precision, recall, and F1 score. This paper aims to provide the best protection from unwanted messages for mobile phone users.

A Novel Approach for Arabic SMS Spam Detection Using Hybrid Deep Learning Techniques

Spam detection in SMS communication is a crucial task for maintaining the quality of messaging services and protecting users from unwanted and potentially harmful messages. Arabic SMS spam detection poses unique challenges due to the rich morphology and complex structure of the Arabic language, which can significantly impact the performance of traditional text classification methods. To address these challenges, this paper presents a novel approach for Arabic SMS spam detection using a hybrid deep learning model that combines Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. The proposed model leverages the strengths of CNNs in capturing local features and patterns in the text and the capability of Bi-LSTM networks to understand long-term dependencies and contextual information. This hybrid architecture is designed to effectively handle the complexities of the Arabic language and improve the accuracy of spam detection. The model was evaluated on a dataset of Arabic SMS messages, consisting of both ham (non-spam) and spam messages. The dataset underwent preprocessing steps, including text cleaning, tokenization, and padding, to prepare it for training the deep learning model. The hybrid model was trained using the Adam optimizer and evaluated using accuracy, precision, recall, and F1 score metrics. Early stopping was implemented to prevent overfitting during the training process. The results demonstrate that the hybrid model achieved high performance, with an accuracy of 0.9699, precision of 0.9739, recall of 0.9675, and an F1 score of 0.9707. These metrics indicate the model's effectiveness in accurately detecting spam in Arabic SMS messages. Additionally, the paper provides visualizations of the confusion matrix, ROC curve, and training-validation loss graph to illustrate the model's performance. The implications of this research are significant for the field of Arabic text classification and spam detection. The proposed hybrid model offers a robust solution for accurately classifying Arabic SMS messages, which can be integrated into messaging platforms to enhance spam detection capabilities and improve user experience. Future work could explore data augmentation techniques, transfer learning, and advanced hybrid architectures to further enhance the model's performance and applicability.

MFEM-CIN: A Lightweight Architecture Combining CNN and Transformer for the Classification of Pre-Cancerous Lesions of the Cervix.

Goal: Cervical cancer is one of the most common cancers in women worldwide, ranking among the top four. Unfortunately, it is also the fourth leading cause of cancer-related deaths among women, particularly in developing countries where incidence and mortality rates are higher compared to developed nations. Colposcopy can aid in the early detection of cervical lesions, but its effectiveness is limited in areas with limited medical resources and a lack of specialized physicians. Consequently, many cases are diagnosed at later stages, putting patients at significant risk. Methods: This paper proposes an automated colposcopic image analysis framework to address these challenges. The framework aims to reduce the labor costs associated with cervical precancer screening in undeserved regions and assist doctors in diagnosing patients. The core of the framework is the MFEM-CIN hybrid model, which combines Convolutional Neural Networks (CNN) and Transformer to aggregate the correlation between local and global features. This combined analysis of local and global information is scientifically useful in clinical diagnosis. In the model, MSFE and MSFF are utilized to extract and fuse multi-scale semantics. This preserves important shallow feature information and allows it to interact with the deep feature, enriching the semantics to some extent. Conclusions: The experimental results demonstrate an accuracy rate of 89.2% in identifying cervical intraepithelial neoplasia while maintaining a lightweight model. This performance exceeds the average accuracy achieved by professional physicians, indicating promising potential for practical application. Utilizing automated colposcopic image analysis and the MFEM-CIN model, this research offers a practical solution to reduce the burden on healthcare providers and improve the efficiency and accuracy of cervical cancer diagnosis in resource-constrained areas.

The multi-strategy hybrid forecasting base on SSA-VMD-WST for complex system.

In view of the strong randomness and non-stationarity of complex system, this study suggests a hybrid multi-strategy prediction technique based on optimized hybrid denoising and deep learning. Firstly, the Sparrow search algorithm (SSA) is used to optimize Variational mode decomposition (VMD) which can decompose the original signal into several Intrinsic mode functions (IMF). Secondly, calculating the Pearson correlation coefficient (PCC) between each IMF component and the original signal, the subsequences with low correlation are eliminated, and the remaining subsequence are denoised by Wavelet soft threshold (WST) method to obtain effective signals. Thirdly, on the basis of the above data noise reduction and reconstruction, our proposal combines Convolutional neural network (CNN) and Bidirectional short-term memory (BiLSTM) model, which is used to analyze the evolution trend of real time sequence data. Finally, we applied the CNN-BiLSTM-SSA-VMD-WST to predict the real time sequence data together with the other methods in order to prove it's effectiveness. The results show that SNR and CC of the SSA-VMD-WST are the largest (the values are 20.2383 and 0.9342). The performance of the CNN-BiLSTM-SSA-VMD-WST are the best, MAE and RMSE are the smallest (which are 0.150 and 0.188), the goodness of fit R2 is the highest(its value is 0.9364). In contrast with other methods, CNN-BiLSTM-SSA-VMD-WST method is more suitable for denoising and prediction of real time series data than the traditional and singular deep learning methods. The proposed method may provide a reliable way for related prediction in various industries.

Prediction of Bitcoin Prices Based on Blockchain Information: A Deep Reinforcement Learning Approach

Bitcoin, the first decentralized cryptocurrency, has attracted significant attention from investors and researchers alike due to its volatile and unpredictable price movements. However, predicting the price of Bitcoin remains a challenging task. This paper presents a detailed literature review on previous studies that have attempted to predict the price of Bitcoin. It discusses the main drivers of Bitcoin prices, including its attractiveness, macroeconomic and financial factors with a particular focus on the use of Blockchain information. We apply time series to daily data for the period from 28/04/2013 to 28/01/2023. We used Python and TensorFlow library version 2.11.0 and propose a deep multimodal reinforcement learning policy combining Convolutional Neural Network (CNN) and Long ShortTerm Memory (LSTM) neural network for cryptocurrencies’ prices prediction. Also, this study attempts to predict the price of Bitcoin using a special type of deep neural networks, a Deep Autoencoders. Two results are worth noting: Autoencoders turns out to be the best method of predicting Bitcoin prices, and Bitcoin-specific Blockchain information is the most important variable in predicting Bitcoin prices. This study highlights the potential utility of incorporating Blockchain factors in price prediction models. Also, our findings show that sentiment indicator, Ethereum, XRP and Doge Coin prices, global currency ratio, macroeconomic factors, and Blockchain information of Ethereum did not contribute significantly toward predicting Bitcoin prices. These conclusions provide decision support for investors and a reference for the governments to design better regulatory policies.

Lung Cancer Prognosis Through Standardized Pre-Processing And Multifaceted Data Enhancement: A Deep Learning Approach

With high rates of morbidity and mortality, lung cancer continues to be a major problem for world health. A precise prognosis is essential for clinical judgment and patient care. This study provides a unique deep learning method for enhancing the prognosis of lung cancer through multimodal data enhancement and standardized pre-processing. The proposed methodology begins with the comprehensive pre-processing of diverse patient data sources, including medical images, clinical records, and genomic information. Standardization techniques are applied to ensure data consistency and reliability, reducing noise and enhancing the quality of the input data. Furthermore, feature selection and extraction methods are employed to identify the most informative variables for prognostic prediction. To harness the full potential of the integrated data, a deep learning architecture is developed. This architecture combines convolutional neural networks (CNNs) for image analysis, recurrent neural networks (RNNs) for sequential clinical data, and fully connected layers for genomic information. By fusing these diverse data modalities, the model captures intricate patterns and relationships, enabling more accurate prognosis. This research paper introduces a cutting-edge deep learning approach for lung cancer prognosis that leverages standardized pre-processing and multifaceted data enhancement. By integrating medical images, clinical records, and genomic information, our model provides clinicians with a powerful tool for improving patient outcomes through more precise prognostic predictions. This research contributes to the advancement of personalized medicine in lung cancer management, offering new avenues for early intervention and tailored treatment strategies.

Hybrid CNN-XGB Framework for Enhancing Human Activity Recognition

Human Activity Recognition (HAR) is one of the most important modern research fields concerned with studying and analyzing human actions and behaviors. Human activity recognition applications offer great potential for a wide range of applications in various fields that enhance health, safety, and efficiency. Due to the diversity of human activities and the way people carry out these activities, it is difficult to recognize human activity. The amazing capabilities provided By Artificial Intelligence (AI) tools in analyzing and understanding hidden patterns in complex data can greatly facilitate the HAR process. There has been a huge trend in the past 10 years to use Machine Learning (ML) and Deep Learning (DL) techniques to analyze and understand big data for HAR. Although there are many studies using these techniques, their accuracy still needs to be further improved due to several challenges: Data complexity, class imbalance, determining the appropriate feature selection technique with ML technique, and tuning the hyperparameters of the used ML technique. To overcome these challenges, this study proposes an effective framework based on two stages: a data preprocessing procedure that includes data balance and data normalization. Then, a hybrid CNN-XGB model combining Convolutional Neural Network (CNN) and a fine-tuned XGBoost (XGB) classifier is developed for accurate HAR. The CNN-XGB model achieved excellent results in HAR when trained and tested on the HCI-HAR dataset, achieving an accuracy of up to 99.0%. Effectively HAR provides the opportunity to apply many applications that contribute to improving the quality of life in various areas of our daily lives.

A Model Based on CNN-LSTM for the Remaining Life Prediction of Equipment in Aircraft Assembly Pulsation Production Line

The aircraft assembly pulsation production line is an advanced and efficient assembly method widely used in aircraft manufacturing. However, equipment malfunctions would occur and can disrupt production takt, affecting the production efficiency. Therefore, accurately predicting the remaining useful life (RUL) of equipment is very crucial. To meet the requirements of both prediction accuracy and efficiency for RUL model used in aircraft pulsation production line, this work proposed a model combining convolutional neural network (CNN) and long short-term memory (LSTM) for RUL prediction. Optimization was performed for the number of neurons in the proposed model with genetic algorithm (GA) to regulate the prediction accuracy and efficiency. Two public datasets representing typical equipment in the pulsation production line were used to validate the proposed model. The results show that the proposed model outperforms the traditional model with substantial improvements in the fitness function of 19.8%, and 30.2% for the two testing datasets. These findings demonstrate the effectiveness of the proposed model in enhancing the accuracy and efficiency of RUL prediction.

Parallel convolutional contrastive learning method for enzyme function prediction.

The function labeling of enzymes has a wide range of application value in the medical field, industrial biology and other fields. Scientists define enzyme categories by enzyme commission (EC) numbers. At present, although there are some tools for enzyme function prediction, their effects have not reached the application level. To improve the precision of enzyme function prediction, we propose a parallel convolutional contrastive learning (PCCL) method to predict enzyme functions. First, we use the advanced protein language model ESM-2 to preprocess the protein sequences. Second, PCCL combines convolutional neural networks (CNNs) and contrastive learning to improve the prediction precision of multifunctional enzymes. Contrastive learning can make the model better deal with the problem of class imbalance. Finally, the deep learning framework is mainly composed of three parallel CNNs for fully extracting sample features. we compare PCCL with state-of-art enzyme function prediction methods based on three evaluation metrics. The performance of our model improves on both two test sets. Especially on the smaller test set, PCCL improves the AUC by 2.57%. The source code can be downloaded from https://github.com/biomg/PCCL.

A Multiantenna Spectrum Sensing Method Based on HFDE‐CNN‐GRU under Non‐Gaussian Noise

In many practical communication environments, traditional feature extraction methods in spectrum sensing fail to fully exploit the information of primary users. Additionally, conventional machine learning methods have weak learning capabilities, making it difficult to maintain efficient and stable spectrum sensing performance in complex noise environments. Furthermore, non‐Gaussian noise can significantly affect the detection performance of spectrum sensing. To address these issues, this paper first proposes a feature extraction method based on Hierarchical Fuzzy Dispersion Entropy (HFDE) to better extract high‐frequency and low‐frequency information from signal samples, providing more comprehensive features for subsequent models to optimize feature extraction effectiveness. Then, a parallel model combining Convolutional Neural Networks (CNN) with Gated Recurrent Units (GRU) is constructed to enhance learning ability. While CNN extracts local features, GRU processes temporal relationships, and the features output by both are concatenated to achieve effective feature learning and temporal modeling of primary user signal data represented by HFDE. Finally, using the feature vectors output by the CNN‐GRU model, detection statistics and detection thresholds for spectrum sensing are constructed for online detection. Simulation results validate the effectiveness and robustness of this method in spectrum sensing under non‐Gaussian noise. In the presence of significant non‐Gaussian noise intensity and a signal‐to‐noise ratio of −14 dB, the detection probability can reach 97.1%. Additionally, for the detection of unknown signals, the model can still maintain a detection probability of over 90%.

The SSHVEP Paradigm-Based Brain Controlled Method for Grasping Robot Using MVMD Combined CNN Model.

In recent years, the steady-state visual evoked potentials (SSVEP) based brain control method has been employed to help people with disabilities because of its advantages of high information transmission rate and low training time. However, the existing SSVEP brain control methods cannot adapt to dynamic or unstructured environments. Moreover, the recognition accuracy from the conventional decoding algorithm still needs to improve. To address the above problems, this study proposed a steady-state hybrid visual evoked potentials (SSHVEP) paradigm using the grasping targets in their environment to improve the connection between the subjects' and their dynamic environments. Moreover, a novel EEG decoding method, using the multivariate variational mode decomposition (MVMD) algorithm for adaptive sub-band division and convolutional neural network (CNN) for target recognition, was applied to improve the decoding accuracy of the SSHVEPs. 18 subjects participated in the offline and online experiments. The offline accuracy across 18 subjects by the 9-target SSHVEP paradigm was up to 95.41 ± 2.70 %, which is a 5.80% improvement compared to the conventional algorithm. To further validate the performance of the proposed method, the brain-controlled grasping robot system using the SSHVEP paradigm was built. The average accuracy reached 93.21 ± 10.18 % for the online experiment. All the experimental results demonstrated the effectiveness of the brain-computer interaction method based on the SSHVEP paradigm and the MVMD combined CNN algorithm studied in this paper.

Study on recognition and classification of English accents using deep learning algorithms

Abstract The recognition and classification of English accents have high practical value in areas such as security management and information retrieval. This study introduced two English accent features, filter bank (FBank) and Mel-frequency cepstral coefficient (MFCC), based on deep learning techniques. It then combined convolutional neural network (CNN), gated recurrent unit, and an attention mechanism to design a 1D CNN-BiGRU-Attention model for English accent recognition and classification. Experimental tests were conducted on the VoxForge dataset. The results showed that compared to MFCC, FBank performed better in English accent recognition and classification, and 70FBank achieved the highest F1 value. Among the recurrent neural network, long short-term memory, and other models, the BiGRU model had the best performance. The average F1 value of the 1D CNN-BiGRU-attention model was the highest, reaching 85.52%, and all the F1 values were above 80% for different accents, indicating that the addition of the attention mechanism effectively improved the model’s recognition and classification effectiveness. The results prove the reliability of the method proposed in this article for English accent recognition and classification, making it suitable for practical application and promotion.

Improving Electric Vehicle Structural-Borne Noise Based on Convolutional Neural Network-Support Vector Regression

In order to enhance the predictive accuracy and control capabilities pertaining to low- and medium-frequency road noise in automotive contexts, this study introduces a methodology for Structural-borne Road Noise (SRN) prediction and optimization. This approach relies on a multi-level target decomposition and a hybrid model combining Convolutional Neural Network (CNN) and Support Vector Regression (SVR). Initially, a multi-level target analysis method is proposed, grounded in the hierarchical decomposition of vehicle road noise along the chassis parts, delineated layer by layer, in accordance with the vibration transmission path. Subsequently, the CNN–SVR hybrid model, predicated on the multi-level target framework, is proposed. Notably, the hybrid model exhibits a superior predictive accuracy exceeding 0.97, surpassing both traditional CNN and SVR models. Finally, the method and model are deployed for sensitivity analysis of chassis parameters in relation to road noise, as well as for the prediction and optimization analysis of SRN in vehicles. The outcomes underscore the high sensitivity of parameters such as the dynamic stiffness of the rear axle bushing and the large front swing arm bushing influencing SRN. The optimization results, facilitated by the CNN–SVR hybrid model, align closely with the measured outcomes, displaying a negligible relative error of 0.82%. Furthermore, the measured results indicate a noteworthy enhancement of 4.07% in the driver’s right-ear Sound Pressure Level (SPL) following the proposed improvements compared to the original state.

A lightweight hybrid CNN-LSTM explainable model for ECG-based arrhythmia detection

Objective:Electrocardiogram (ECG) is the most frequent and routine diagnostic tool used for monitoring heart electrical signals and evaluating its functionality. The human heart can suffer from a variety of diseases, including cardiac arrhythmias. Arrhythmia is an irregular heart rhythm that in severe cases can lead to stroke and can be diagnosed via ECG recordings. Since early detection of cardiac arrhythmias is of great importance, computerized and automated classification and identification of these abnormal heart signals have received much attention for the past decades. Methods:This paper introduces a light Deep Learning (DL) approach for high accuracy detection of 8 different cardiac arrhythmias and normal rhythms. To employ DL techniques, the ECG signals were preprocessed using resampling and baseline wander removal techniques. The classification was performed using an 11-layer network employing a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). Results:In order to evaluate the proposed technique, ECG signals are chosen from the two physionet databases, the MIT-BIH arrhythmia database and the long-term AF database. The proposed DL framework based on the combination of CNN and LSTM showed promising results than most of the state-of-the-art methods. The proposed method reaches the mean diagnostic accuracy of 98.24%. Conclusion:A trained model for arrhythmia classification using diverse ECG signals were successfully developed and tested. Significance:This study presents a lightweight classification technique with high diagnostic accuracy compared to other notable methods, making it a potential candidate for implementation in Holter monitor devices for arrhythmia detection. Finally, we used SHapley Additive exPlanations (SHAP), the most popular Explainable Artificial Intelligence (XAI) method to understand how our model make predictions. The results indicate that those features (ECG samples) that have contributed the most to a prediction are consonant with clinicians’ decisions. Therefore, the use of interpretable models increases the trust of clinicians in AI and thus leads to decreasing the number of misdiagnoses of cardiovascular diseases.

Combined control of rehabilitation wheelchair using periocular electromyography and electroencephalography

To improve the convenience of life for the people with reduced mobility, a combined control method of wheelchair utilizing periocular electromyography (Per-EMG) and electroencephalography (EEG) is presented. Based on the Per-EMG and EEG signals obtained from the bioelectric sensors, a novel feature classification combined model is proposed by combining convolutional neural network (CNN) and long short-term memory (LSTM) neural network. These two deep learning architectures enable the comprehensive analysis and accurate classification of the acquired signals. Then the inferencing results can be converted to the corresponding driving command of the rehabilitation wheelchair. Furthermore, the important metrics such as accuracy, precision and recall are adopted to evaluate the performance of this combined model. These metrics provide a quantitative assessment of the model’s classification capabilities. By practical experiments, the proposed combined control method for rehabilitation wheelchair demonstrates its reasonability and effectiveness. And the wheelchair with combined control method can enhance the mobility and independence of the people with reduced mobility. These findings contribute to the development of assistive technologies in the field of rehabilitation.

Fusion Networks of CNN and Transformer with Channel Attention for Accurate Tumor Imaging in Magnetic Particle Imaging.

Magnetic Particle Imaging (MPI) is an emerging molecular imaging technique. However, since X-space reconstruction ignores system properties, it can lead to blurring of the reconstructed image, posing challenges for accurate quantification. To address this issue, we propose the use of deep learning to remove the blurry artifacts; (2) Methods: Our network architecture consists of a combination of Convolutional Neural Network (CNN) and Transformer. The CNN utilizes convolutional layers to automatically extract pixel-level local features and reduces the size of feature maps through pooling layers, effectively capturing local information within the images. The Transformer module is responsible for extracting contextual features from the images and efficiently capturing long-range dependencies, enabling a more effective modeling of global features in the images. By combining the features extracted by both CNN and Transformer, we capture both global and local features simultaneously, thereby improving the quality of reconstructed images; (3) Results: Experimental results demonstrate that the network effectively removes blurry artifacts from the images, and it exhibits high accuracy in precise tumor quantification. The proposed method shows superior performance over the state-of-the-art methods; (4) Conclusions: This bears significant implications for the image quality improvement and clinical application of MPI technology.