Dimensional Convolutional Neural Network Research Articles

A hybrid 1D CNN-BiLSTM model for epileptic seizure detection using multichannel EEG feature fusion

Epilepsy, a chronic non-communicable disease is characterized by repeated unprovoked seizures, which are transient episodes of abnormal electrical activity in the brain. While Electroencephalography (EEG) is considered as the gold standard for diagnosis in current clinical practice, manual inspection of EEG is time consuming and biased. This paper presents a novel hybrid 1D CNN-Bi LSTM feature fusion model for automatically detecting seizures. The proposed model leverages spatial features extracted by one dimensional convolutional neural network and temporal features extracted by bi directional long short-term memory network. Ictal and inter ictal data is first acquired from the long multichannel EEG record. The acquired data is segmented and labelled using small fixed windows. Signal features are then extracted from the segments concurrently by the parallel combination of CNN and Bi-LSTM. The spatial and temporal features thus captured are then fused to enhance classification accuracy of model. The approach is validated using benchmark CHB-MIT dataset and 5-fold cross validation which resulted in an average accuracy of 95.90%, with precision 94.78%, F1 score 95.95%. Notably model achieved average sensitivity of 97.18% with false positivity rate at 0.05/hr. The significantly lower false positivity and false negativity rates indicate that the proposed model is a promising tool for detecting seizures in epilepsy patients. The employed parallel path network benefits from memory function of Bi-LSTM and strong feature extraction capabilities of CNN. Moreover, eliminating the need for any domain transformation or additional preprocessing steps, model effectively reduces complexity and enhances efficiency, making it suitable for use by clinicians during the epilepsy diagnostic process.

Deep Learning for Automated Measurement of Total Cardiac Volume for Heart Transplantation Size Matching.

Total Cardiac Volume (TCV)-based size matching using Computed Tomography (CT) is a novel technique to compare donor and recipient heart size in pediatric heart transplant that may increase overall utilization of available grafts. TCV requires manual segmentation, which limits its widespread use due to time and specialized software and training needed for segmentation. This study aims to determine the accuracy of a Deep Learning (DL) approach using 3-dimensional Convolutional Neural Networks (3D-CNN) to calculate TCV, with the clinical aim of enabling fast and accurate TCV use at all transplant centers. Ground truth TCV was segmented on CT scans of subjects aged 0-30years, identified retrospectively. Ground truth segmentation masks were used to train and test a custom 3D-CNN model consisting of a DenseNet architecture in combination with residual blocks of ResNet architecture. The model was trained on a cohort of 270 subjects and a validation cohort of 44 subjects (36 normal, 8 heart disease retained for model testing). The average Dice similarity coefficient of the validation cohort was 0.94 ± 0.03 (range 0.84-0.97). The mean absolute percent error of TCV estimation was 5.5%. There is no significant association between model accuracy and subject age, weight, or height. DL-TCV was on average more accurate for normal hearts than those listed for transplant (mean absolute percent error 4.5 ± 3.9 vs. 10.5 ± 8.5, p = 0.08). A deep learning-based 3D-CNN model can provide accurate automatic measurement of TCV from CT images. This initial study is limited as a single-center study, though future multicenter studies may enable generalizable and more accurate TCV measurement by inclusion of more diverse cardiac pathology and increasing the training data.

Multichannel consecutive data cross-extraction with 1DCNN-attention for diagnosis of power transformer

Power transformer plays a critical role in grid infrastructure, and its diagnosis is paramount for maintaining stable operation. However, the current methods for transformer diagnosis focus on discrete dissolved gas analysis, neglecting deep feature extraction of multichannel consecutive data. The unutilized sequential data contains the significant temporal information reflecting the transformer condition. In light of this, the structure of multichannel consecutive data cross-extraction (MCDC) is proposed in this article in order to comprehensively exploit the intrinsic characteristic and evaluate the states of transformer. Moreover, for the better accommodation in scenario of transformer diagnosis, one dimensional convolution neural network attention (1DCNN-attention) mechanism is introduced and offers a more efficient solution given the simplified spatial complexity. Finally, the effectiveness of MCDC and the superior generalization ability, compared with other algorithms, are validated in experiments conducted on a dataset collected from real operation cases of power transformer. Additionally, the better stability of 1DCNN-attention has also been certified.

Predicting Obstructive Sleep Apnea Based on Computed Tomography Scan Using Deep Learning Models.

The incidence of clinically undiagnosed obstructive sleep apnea (OSA) is high among the general population due to limited access to polysomnography. Computed tomography (CT) of craniofacial regions obtained for other purposes can be beneficial in predicting OSA and its severity. To predict OSA and its severity based on paranasal CT using a 3-dimensional deep learning algorithm. One internal dataset (n=798) and two external datasets (n=135 and 85) were used in this study. In the internal dataset, 92 normal, 159 mild, 201 moderate, and 346 severe OSA participants were enrolled to derive the deep learning model. A multimodal deep learning model was elicited from the connection between a 3-dimensional convolutional neural network (CNN)-based part treating unstructured data (CT images) and a multi-layer perceptron (MLP)-based part treating structured data (age, sex, and body mass index) to predict OSA and its severity. In four-class classification for predicting the severity of OSA, the AirwayNet-MM-H model (multimodal model with airway-highlighting preprocessing algorithm) showed an average accuracy of 87.6% (95% confidence interval [CI] 86.8-88.6) in the internal dataset and 84.0% (95% CI 83.0-85.1) and 86.3% (95% CI 85.3-87.3) in the two external datasets, respectively. In the two-class classification for predicting significant OSA (moderate to severe OSA), The area under the receiver operating characteristics (AUROC), accuracy, sensitivity, specificity, and F1 score were 0.910 (95% CI 0.899-0.922), 91.0% (95% CI 90.1-91.9), 89.9% (95% CI 88.8-90.9), 93.5% (95% CI 92.7-94.3), and 93.2% (95% CI 92.5-93.9), respectively, in the internal dataset. Furthermore, the diagnostic performance of the Airway Net-MM-H model outperformed that of the other six state-of-the-art deep learning models in terms of accuracy for both four- and two-class classifications and AUROC for two-class classification (p<0.001). A novel deep learning model, including a multimodal deep learning model and an airway-highlighting preprocessing algorithm from CT images obtained for other purposes, can provide significantly precise outcomes for OSA diagnosis.

Acoustic data detection in large-scale emergency vehicle sirens and road noise dataset

This paper presents a novel deep learning model called Self-Attention Layer within a Convolutional Neural Network (SACNN), specifically designed for detecting acoustic data in extensive datasets containing emergency vehicle sirens and road noise. SACNN leverages a combination of EfficientNet and One Dimensional Convolutional Neural Networks (1D_CNN) to improve the precision and efficiency of detection. The dataset comprises 3-second WAV-format audio files categorized into Emergency Vehicles (Ambulance and Firetruck sirens) and Traffic (plain traffic sounds), with each category having 200 sound files and their corresponding 200 spectrogram images per audio file. Experimental results demonstrate SACNN's superior performance across various metrics, including accuracy, precision, recall, and F1 score, while also achieving notable advancements in computational efficiency. The research addresses the need for more effective solutions in the domain of emergency vehicle siren and road noise detection by introducing SACNN as a cutting-edge solution. By integrating EfficientNet and 1D_CNN, SACNN surpasses existing models in accuracy and computational efficiency. Comparative analysis with EfficientNet and 1D_CNN using a large-scale dataset validates SACNN's superior performance, with an average accuracy, precision, recall, and F1 score of 1.00. Additionally, SACNN exhibits the highest computational efficiency, averaging 0.20883 s per sample. These findings highlight SACNN's efficacy in detecting and classifying emergency vehicle sirens and road noise in large-scale datasets, with implications for traffic management, public safety, and noise pollution monitoring. SACNN offers the potential for constructing real-time acoustic data detection systems.

Research on Sea State Signal Recognition Based on Beluga Whale Optimization-Slope Entropy and One Dimensional-Convolutional Neural Network.

This study introduces a novel nonlinear dynamic analysis method, known as beluga whale optimization-slope entropy (BWO-SlEn), to address the challenge of recognizing sea state signals (SSSs) in complex marine environments. A method of underwater acoustic signal recognition based on BWO-SlEn and one-dimensional convolutional neural network (1D-CNN) is proposed. Firstly, particle swarm optimization-slope entropy (PSO-SlEn), BWO-SlEn, and Harris hawk optimization-slope entropy (HHO-SlEn) were used for feature extraction of noise signal and SSS. After 1D-CNN classification, BWO-SlEn were found to have the best recognition effect. Secondly, fuzzy entropy (FE), sample entropy (SE), permutation entropy (PE), and dispersion entropy (DE) were used to extract the signal features. After 1D-CNN classification, BWO-SlEn and 1D-CNN were found to have the highest recognition rate compared with them. Finally, compared with the other six recognition methods, the recognition rates of BWO-SlEn and 1D-CNN for the noise signal and SSS are at least 6% and 4.75% higher, respectively. Therefore, the BWO-SlEn and 1D-CNN recognition methods proposed in this paper are more effective in the application of SSS recognition.

High-spatial resolution ground-level ozone in Yunnan, China: A spatiotemporal estimation based on comparative analyses of machine learning models

Monitoring ground-level ozone concentrations is a critical aspect of atmospheric environmental studies. Given the existing limitations of satellite data products, especially the lack of ground-level ozone characterization, and the discontinuity of ground observations, there is a pressing need for high-precision models to simulate ground-level ozone to assess surface ozone pollution. In this study, we have compared several widely utilized ensemble learning and deep learning methods for ground-level ozone simulation. Furthermore, we have thoroughly contrasted the temporal and spatial generalization performances of the ensemble learning and deep learning models. The 3-Dimensional Convolutional Neural Network (3-D CNN) model has emerged as the optimal choice for evaluating the daily maximum 8-h average ozone in Yunnan Province. The model has good performance: a spatial resolution of 0.05° × 0.05° and strong predictive power, as indicated by a Coefficient of Determination (R2) of 0.83 and a Root Mean Square Error (RMSE) of 12.54 μg/m³ in sample-based 5-fold cross-validation (CV).In the final stage of our study, we applied the 3-D CNN model to generate a comprehensive daily maximum 8-h average ozone dataset for Yunnan Province for the year 2021. This application has furnished us with a crucial high-resolution and highly accurate dataset for further in-depth studies on the issue of ozone pollution in Yunnan Province.

Three-Dimensional Residual Neural Architecture Search for Ultrasonic Defect Detection.

This study presents a deep-learning (DL) methodology using 3-D convolutional neural networks (CNNs) to detect defects in carbon fiber-reinforced polymer (CFRP) composites through volumetric ultrasonic testing (UT) data. Acquiring large amounts of ultrasonic training data experimentally is expensive and time-consuming. To address this issue, a synthetic data generation method was extended to incorporate volumetric data. By preserving the complete volumetric data, complex preprocessing is reduced, and the model can utilize spatial and temporal information that is lost during imaging. This enables the model to utilize important features that might be overlooked otherwise. The performance of three architectures was compared. The first architecture is prevalent in the literature for the classification of volumetric datasets. The second demonstrated a hand-designed approach to architecture design, with modifications to the first architecture to address the challenges of this specific task. A key modification was the use of cuboidal kernels to account for the large aspect ratios seen in ultrasonic data. The third architecture was discovered through neural architecture search (NAS) from a modified 3-D residual neural network (ResNet) search space. In addition, domain-specific augmentation methods were incorporated during training, resulting in significant improvements in model performance, with a mean accuracy improvement of 22.4% on the discovered architecture. The discovered architecture demonstrated the best performance with a mean accuracy increase of 7.9% over the second-best model. It was able to consistently detect all defects while maintaining a model size smaller than most 2-D ResNets. Each model had an inference time of less than 0.5 s, making them efficient for the interpretation of large amounts of data.

Three dimensional convolutional neural network-based automated detection of midline shift in traumatic brain injury cases from head computed tomography scans.

Midline shift (MLS) is a critical indicator of the severity of brain trauma and is even suggestive of changes in intracranial pressure. At present, radiologists have to manually measure the MLS using laborious techniques. Automatic detection of MLS using artificial intelligence can be a cutting-edge solution for emergency health-care personnel to help in prompt diagnosis and treatment. In this study, we sought to determine the accuracy and the prognostic value of our screening tool that automatically detects MLS on computed tomography (CT) images in patients with traumatic brain injuries (TBIs). The study enrolled TBI cases, who presented at the Department of Neurosurgery, All India Institute of Medical Sciences, New Delhi. Institutional ethics committee permission was taken before starting the study. The data collection was carried out for over nine months, i.e., from January 2020 to September 2020. The data collection included head CT scans, patient demographics, clinical details as well as radiologist's reports. The radiologist's reports were considered the "gold standard" for evaluating the MLS. A deep learning-based three dimensional (3D) convolutional neural network (CNN) model was developed using 176 head CT scans. The developed 3D CNN model was trained using 156 scans and was tested on 20 head CTs to determine the accuracy and sensitivity of the model. The screening tool was correctly able to detect 7/10 MLS cases and 4/10 non-MLS cases. The model showed an accuracy of 55% with high specificity (70%) and moderate sensitivity of 40%. An automated solution for screening the MLS can prove useful for neurosurgeons. The results are strong evidence that 3D CNN can assist clinicians in screening MLS cases in an emergency setting.

Artificial intelligence-based classification of echocardiographic views

Abstract Aims Augmenting echocardiography with artificial intelligence would allow for automated assessment of routine parameters and identification of disease patterns not easily recognized otherwise. View classification is an essential first step before deep learning can be applied to the echocardiogram. Methods and results We trained two- and three-dimensional convolutional neural networks (CNNs) using transthoracic echocardiographic (TTE) studies obtained from 909 patients to classify nine view categories (10 269 videos). Transthoracic echocardiographic studies from 229 patients were used in internal validation (2582 videos). Convolutional neural networks were tested on 100 patients with comprehensive TTE studies (where the two examples chosen by CNNs as most likely to represent a view were evaluated) and 408 patients with five view categories obtained via point-of-care ultrasound (POCUS). The overall accuracy of the two-dimensional CNN was 96.8%, and the averaged area under the curve (AUC) was 0.997 on the comprehensive TTE testing set; these numbers were 98.4% and 0.998, respectively, on the POCUS set. For the three-dimensional CNN, the accuracy and AUC were 96.3% and 0.998 for full TTE studies and 95.0% and 0.996 on POCUS videos, respectively. The positive predictive value, which defined correctly identified predicted views, was higher with two-dimensional rather than three-dimensional networks, exceeding 93% in apical, short-axis aortic valve, and parasternal long-axis left ventricle views. Conclusion An automated view classifier utilizing CNNs was able to classify cardiac views obtained using TTE and POCUS with high accuracy. The view classifier will facilitate the application of deep learning to echocardiography.

Fusarium head blight detection, spikelet estimation, and severity assessment in wheat using 3D convolutional neural networks

Fusarium head blight (FHB) is one of the most significant diseases affecting wheat and other small grain cereals worldwide. Developing FHB-resistant cultivars is critical but requires field and greenhouse disease assessment which are typically laborious and time-consuming. In this work, we developed automated applications based on 3-dimensional (3D) convolutional neural networks (CNN) that detect FHB symptoms expressed in wheat, estimate the total number of spikelets versus the total number of infected spikelets on a wheat head, and subsequently calculate FHB severity index. Such tools are an important step toward the creation of automated and efficient phenotyping methods. The data used to generate the results are 3D point clouds consisting of four color channels – red, green, blue (RGB), and near-infrared (NIR) – collected using a multispectral 3D scanner. Our 3D CNN models for FHB detection achieved 100% accuracy. The influence of the multispectral information on performance was evaluated; the results showed the dominance of the RGB channels over both the NIR (720 nm peak wavelength) and the NIR plus RGB channels combined. Our best 3D CNN models for estimation of total and infected number of spikelets achieved mean absolute errors (MAE) of 1.13 and 1.56, respectively. Our best 3D CNN models for FHB severity estimation achieved 8.6 MAE. A linear regression analysis between the visual FHB severity assessment and the FHB severity predicted by our 3D CNN showed a significant correlation.

Deep learning aided prostate cancer detection for early diagnosis &amp; treatment using MR with TRUS images

Although difficult, robust and reliable synchronization of multimodal medical pictures has several practical uses. For instance, in MR-TRUS fusing guided prostate treatments, picture registration between the two modalities is essential. However, due to the significant variety in image appearance and correlation, MR-TRUS picture registration remains a challenging issue. In this research, we suggest employing deep convolutional neural networks (CNN) i.e. three dimensional CNN U-NET (3D-Conv-Net) to develop a resemblance measure for MR-TRUS registration. Finally, for the second-order optimal of the taught measure, we apply a composite optimisation method that searches the solution space for an appropriate starting point. We also use a multi-stage process to improve the optimisation metric.

Deep learning based ultrasonic reconstruction of rough surface morphology

This paper introduces a methodology to recover the morphology of a complex rough surface from ultrasonic pulse echo measurements with an array of equidistant sensors using the one dimensional convolution neural network (1DCNN). The neural network is trained by the datasets simulated from high-fidelity finite element simulations for surfaces with a range of roughness parameters and is tested on both numerical and real experimental data. To assess the performance of our proposed method, the rough surface reconstruction results from the deep learning approach are compared with those obtained from conventional ultrasonic array imaging methods. Unlike array imaging-based methods that require a large number of sensors (e.g., 128, 64 or 32), the deep learning-based method uses pulse echo signals and can achieve accurate results with much fewer sensors. The developed deep learning approach has the potential to enable low-cost, accurate, and real-time reconstruction of complex surface profiles.

Optimal tuning of three deep learning methods with signal processing and anomaly detection for multi-class damage detection of a large-scale bridge

Long-span bridges play a crucial role in urbanization, connecting communities across vast obstacles. Structural health monitoring techniques have been deployed on these bridges, generate large amounts of data through sensor measurements, requiring data-driven approaches like deep learning (DL) for effective analysis. However, feature extraction from time-domain vibration response signals poses challenges for DL methods. To address this, the study proposes utilizing signal processing techniques such as the multivariate empirical mode decomposition (MEMD) and Wavelet transform (WT) to extract essential features for damage classification. The incorporation of MEMD and WT aims to overcome limitations and process nonstationary and nonlinear signals effectively. Three DL techniques, long-short-term memory (LSTM), one dimensional convolutional neural network (1D-CNN), multi-layer perceptron (MLP) are tuned and applied to Structural Health Monitoring of Tianjin Yonghe Bridge (located in China) as a real-world case study, in order to detect its condition by Deep signal anomaly detection and identify types of the damage. A powerful meta-heuristic algorithm called Observer-Teacher-Learner-Based Optimization, is used to optimize both hyperparameters and architecture of each DL models. The results demonstrate that the optimally tuned DLs are successful in identifying types of damage, as well as the condition of the structure, for the Tianjin Yonghe Bridge. The average accuracy values are obtained as 98.13, 97.96, and 97.79 for 1D-CNN, LSTM, and MLP, respectively. Such optimally tuned DLs are evaluated as effective solutions for detecting damage on large-scale bridges by extracting statistical time-domain and time–frequency domain features using the WT and MEMD.

Artificial Intelligence–Guided Segmentation and Path Planning Software for Transthoracic Lung Biopsy

PurposeTo validate the sensitivity and specificity of a 3-dimensional (3D) convolutional neural network (CNN) artificial intelligence (AI) software for lung lesion detection and to establish concordance between AI-generated needle paths and those used in actual biopsy procedures. Materials and MethodsThis was a retrospective study using computed tomography (CT) scans from 3 hospitals. Inclusion criteria were scans with 1–5 nodules of diameter ≥5 mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm in diameter. In the lesion detection phase, 2,147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. In the path planning phase, Bayesian optimization was used to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared with actual biopsy path trajectories from intraprocedural CT scans in 150 patients, with a match defined as an angular deviation of <5° between the 2 trajectories. ResultsThe model achieved an overall AUC of 97.4% (95% CI, 96.3%–98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. Among the software-proposed needle trajectories, 85.3% were feasible, with 82% matching actual paths and similar performance between supine and prone/oblique patient orientations (P = .311). The mean angular deviation between matching trajectories was 2.30° (SD ± 1.22); the mean path deviation was 2.94 mm (SD ± 1.60). ConclusionsSegmentation, lesion detection, and path planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way toward fully automated biopsy procedures.

Establishment and comparison of in situ detection models for foodborne pathogen contamination on mutton based on SWIR-HSI.

Rapid and accurate detection of food-borne pathogens on mutton is of great significance to ensure the safety of mutton and its products and the health of consumers. The feasibility of short-wave infrared hyperspectral imaging (SWIR-HSI) in detecting the contamination status and species of Escherichia coli (EC), Staphylococcus aureus (SA) and Salmonella typhimurium (ST) contaminated on mutton was explored. The hyperspectral images of uncontaminated and contaminated mutton samples with different concentrations (108, 107, 106, 105, 104, 103 and 102 CFU/mL) of EC, SA and ST were acquired. The one dimensional convolutional neural network (1D-CNN) model was constructed and the influence of structure hyperparameters on the model was explored. The effects of different spectral preprocessing methods on partial least squares-discriminant analysis (PLS-DA), support vector machine (SVM) and 1D-CNN models were discussed. In addition, the feasibility of using the characteristic wavelength to establish simplified models was explored. The best full band model was the 1D-CNN model with the convolution kernels number of (64, 16) and the activation function of tanh established by the original spectra, and its accuracy of training set, test set and external validation set were 100.00, 92.86 and 97.62%, respectively. The optimal simplified model was genetic algorithm optimization support vector machine (GA-SVM). For discriminating the pathogen species, the accuracies of SVM models established by full band spectra preprocessed by 2D and all 1D-CNN models with the convolution kernel number of (32, 16) and the activation function of tanh were 100.00%. In addition, the accuracies of all simplified models were 100.00% except for the 1D-CNN models. Considering the complexity of features and model calculation, the 1D-CNN models established by original spectra were the optimal models for pathogenic bacteria contamination status and species. The simplified models provide basis for developing multispectral detection instruments. The results proved that SWIR-HSI combined with machine learning and deep learning could accurately detect the foodborne pathogen contamination on mutton, and the performance of deep learning models were better than that of machine learning. This study can promote the application of HSI technology in the detection of foodborne pathogens on meat.

Discriminative spatial-temporal feature learning for modeling network intrusion detection systems

Increasing interest and advancement of internet and communication technologies have made network security rise as a vibrant research domain. Network intrusion detection systems (NIDSs) have developed as indispensable defense mechanisms in cybersecurity that are employed in discovery and prevention of malicious network activities. In the recent years, researchers have proposed deep learning approaches in the development of NIDSs owing to their ability to extract better representations from large corpus of data. In the literature, convolutional neural network architecture is extensively used for spatial feature learning, while the long short term memory networks are employed to learn temporal features. In this paper, a novel hybrid method that learn the discriminative spatial and temporal features from the network flow is proposed for detecting network intrusions. A two dimensional convolution neural network is proposed to intelligently extract the spatial characteristics whereas a bi-directional long short term memory is used to extract temporal features of network traffic data samples consequently, forming a deep hybrid neural network architecture for identification and classification of network intrusion samples. Extensive experimental evaluations were performed on two well-known benchmarks datasets: CIC-IDS 2017 and the NSL-KDD datasets. The proposed network model demonstrated state-of-the-art performance with experimental results showing that the accuracy and precision scores of the intrusion detection model are significantly better than those of other existing models. These results depicts the applicability of the proposed model in the spatial-temporal feature learning in network intrusion detection systems.

Comparing deep learning and handcrafted radiomics to predict chemoradiotherapy response for locally advanced cervical cancer using pretreatment MRI

Concurrent chemoradiotherapy (CRT) is the standard treatment for locally advanced cervical cancer (LACC), but its responsiveness varies among patients. A reliable tool for predicting CRT responses is necessary for personalized cancer treatment. In this study, we constructed prediction models using handcrafted radiomics (HCR) and deep learning radiomics (DLR) based on pretreatment MRI data to predict CRT response in LACC. Furthermore, we investigated the potential improvement in prediction performance by incorporating clinical factors. A total of 252 LACC patients undergoing curative chemoradiotherapy are included. The patients are randomly divided into two independent groups for the training (167 patients) and test datasets (85 patients). Contrast-enhanced T1- and T2-weighted MR scans are obtained. For HCR analysis, 1890 imaging features are extracted and a support vector machine classifier with a five-fold cross-validation is trained on training dataset to predict CRT response and subsequently validated on test dataset. For DLR analysis, a 3-dimensional convolutional neural network was trained on training dataset and validated on test dataset. In conclusion, both HCR and DLR models could predict CRT responses in patients with LACC. The integration of clinical factors into radiomics prediction models tended to improve performance in HCR analysis. Our findings may contribute to the development of personalized treatment strategies for LACC patients.

Deep transfer learning-based SSVEP frequency domain decoding method

ObjectiveImproving the decoding accuracy and information transfer rate (ITR) of a steady-state visual evoked potential-based brain-computer interface (SSVEP-BCI) system and narrowing the inter-subject variance are key to the application of the SSVEP-BCI system. To this end, we proposed a deep transfer learning-based SSVEP frequency domain decoding method to improve the decoding performance. MethodsInput data representations with rich spatial and frequency domain features were extracted using filter bank and zero-padding-based fast Fourier transform techniques. A concise and efficient 3-dimensional convolutional neural network (3DCNN) model was designed for feature extraction and decoding of the input data. A transfer learning strategy was proposed to further improve the decoding accuracy and narrow the inter-subject variance. ResultsOur proposed 3DCNN achieves 89.35 % average classification accuracy and 173.02 bits/min ITR on the benchmark dataset with 1 s signal length. On our laboratory dataset, the average classification accuracy and ITR of 3DCNN reach 88.75 % and 120.33 bits/min, respectively, when the signal length is 0.6 s. ConclusionsIn this study, we experimentally confirmed the effectiveness and superiority of our proposed method for SSVEP decoding, which provides a promising decoding method for the application of SSVEP-BCI.

EEGDepressionNet: A Novel Self Attention-Based Gated DenseNet With Hybrid Heuristic Adopted Mental Depression Detection Model Using EEG Signals.

World Health Organization (WHO) has identified depression as a significant contributor to global disability, creating a complex thread in both public and private health. Electroencephalogram (EEG) can accurately reveal the working condition of the human brain, and it is considered an effective tool for analyzing depression. However, manual depression detection using EEG signals is time-consuming and tedious. To address this, fully automatic depression identification models have been designed using EEG signals to assist clinicians. In this study, we propose a novel automated deep learning-based depression detection system using EEG signals. The required EEG signals are gathered from publicly available databases, and three sets of features are extracted from the original EEG signal. Firstly, spectrogram images are generated from the original EEG signal, and 3-dimensional Convolutional Neural Networks (3D-CNN) are employed to extract deep features. Secondly, 1D-CNN is utilized to extract deep features from the collected EEG signal. Thirdly, spectral features are extracted from the collected EEG signal. Following feature extraction, optimal weights are fused with the three sets of features. The selection of optimal features is carried out using the developed Chaotic Owl Invasive Weed Search Optimization (COIWSO) algorithm. Subsequently, the fused features undergo analysis using the Self-Attention-based Gated Densenet (SA-GDensenet) for depression detection. The parameters within the detection network are optimized with the assistance of the same COIWSO. Finally, implementation results are analyzed in comparison to existing detection models. The experimentation findings of the developed model show 96% of accuracy. Throughout the empirical result, the findings of the developed model show better performance than traditional approaches.