3D Residual Network Research Articles

3D residual attention network for hyperspectral image classification

Convolutional neural network (CNN) has been widely applied to hyperspectral image (HSI) classification and shows good performance. In this paper, a novel 3D residual attention network (3D-RAN) based on CNN is proposed for HSI classification. The main contributions and novelties of the method are as follows: (1) the 3D-RAN can directly process the 3D HSI data and effectively preserve the data structure of HSI; (2) the constructed residual module can supplement the loss of some important information during the process of information transmission, so that it makes the extracted features contain richer information; (3) the embedded attention module can strengthen the important features and suppress the unimportant features by adjusting weights, which effectively improves the classification performance. Moreover, weight sharing makes the attention module require fewer parameters. The experiments on three public HSI data sets demonstrate that the proposed 3D-RAN outperforms several state-of-the-art methods.

A Self-Attention-Guided 3D Deep Residual Network With Big Transfer to Predict Local Failure in Brain Metastasis After Radiotherapy Using Multi-Channel MRI

A noticeable proportion of larger brain metastases (BMs) are not locally controlled after stereotactic radiotherapy, and it may take months before local progression is apparent on standard follow-up imaging. This work proposes and investigates new explainable deep-learning models to predict the radiotherapy outcome for BM. A novel self-attention-guided 3D residual network is introduced for predicting the outcome of local failure (LF) after radiotherapy using the baseline treatment-planning MRI. The 3D self-attention modules facilitate capturing long-range intra/inter slice dependencies which are often overlooked by convolution layers. The proposed model was compared to a vanilla 3D residual network and 3D residual network with CBAM attention in terms of performance in outcome prediction. A training recipe was adapted for the outcome prediction models during pretraining and training the down-stream task based on the recently proposed big transfer principles. A novel 3D visualization module was coupled with the model to demonstrate the impact of various intra/peri-lesion regions on volumetric multi-channel MRI upon the network's prediction. The proposed self-attention-guided 3D residual network outperforms the vanilla residual network and the residual network with CBAM attention in accuracy, F1-score, and AUC. The visualization results show the importance of peri-lesional characteristics on treatment-planning MRI in predicting local outcome after radiotherapy. This study demonstrates the potential of self-attention-guided deep-learning features derived from volumetric MRI in radiotherapy outcome prediction for BM. The insights obtained via the developed visualization module for individual lesions can possibly be applied during radiotherapy planning to decrease the chance of LF.

3D CT-Inclusive Deep-Learning Model to Predict Mortality, ICU Admittance, and Intubation in COVID-19 Patients

Chest CT is a useful initial exam in patients with coronavirus disease 2019 (COVID-19) for assessing lung damage. AI-powered predictive models could be useful to better allocate resources in the midst of the pandemic. Our aim was to build a deep-learning (DL) model for COVID-19 outcome prediction inclusive of 3D chest CT images acquired at hospital admission. This retrospective multicentric study included 1051 patients (mean age 69, SD = 15) who presented to the emergency department of three different institutions between 20th March 2020 and 20th January 2021 with COVID-19 confirmed by real-time reverse transcriptase polymerase chain reaction (RT-PCR). Chest CT at hospital admission were evaluated by a 3D residual neural network algorithm. Training, internal validation, and external validation groups included 608, 153, and 290 patients, respectively. Images, clinical, and laboratory data were fed into different customizations of a dense neural network to choose the best performing architecture for the prediction of mortality, intubation, and intensive care unit (ICU) admission. The AI model tested on CT and clinical features displayed accuracy, sensitivity, specificity, and ROC-AUC, respectively, of 91.7%, 90.5%, 92.4%, and 95% for the prediction of patient’s mortality; 91.3%, 91.5%, 89.8%, and 95% for intubation; and 89.6%, 90.2%, 86.5%, and 94% for ICU admission (internal validation) in the testing cohort. The performance was lower in the validation cohort for mortality (71.7%, 55.6%, 74.8%, 72%), intubation (72.6%, 74.7%, 45.7%, 64%), and ICU admission (74.7%, 77%, 46%, 70%) prediction. The addition of the available laboratory data led to an increase in sensitivity for patient’s mortality (66%) and specificity for intubation and ICU admission (50%, 52%, respectively), while the other metrics maintained similar performance results. We present a deep-learning model to predict mortality, ICU admittance, and intubation in COVID-19 patients.Key Points• 3D CT-based deep learning model predicted the internal validation set with high accuracy, sensibility and specificity (> 90%) mortality, ICU admittance, and intubation in COVID-19 patients.• The model slightly increased prediction results when laboratory data were added to the analysis, despite data imbalance. However, the model accuracy dropped when CT images were not considered in the analysis, implying an important role of CT in predicting outcomes.

Attention-based Deep Learning for the Preoperative Differentiation of Axillary Lymph Node Metastasis in Breast Cancer on DCE-MRI.

Previous studies have explored the potential on radiomics features of primary breast cancer tumor to identify axillary lymph node (ALN) metastasis. However, the value of deep learning (DL) to identify ALN metastasis remains unclear. To investigate the potential of the proposed attention-based DL model for the preoperative differentiation of ALN metastasis in breast cancer on dynamic contrast-enhanced MRI (DCE-MRI). Retrospective. A total of 941 breast cancer patients who underwent DCE-MRI before surgery were included in the training (742 patients), internal test (83 patients), and external test (116 patients) cohorts. A 3.0 T MR scanner, DCE-MRI sequence. A DL model containing a 3D deep residual network (ResNet) architecture and a convolutional block attention module, named RCNet, was proposed for ALN metastasis identification. Three RCNet models were established based on the tumor, ALN, and combined tumor-ALN regions on the images. The performance of these models was compared with ResNet models, radiomics models, the Memorial Sloan-Kettering Cancer Center (MSKCC) model, and three radiologists (W.L., H.S., and F. L.). Dice similarity coefficient for breast tumor and ALN segmentation. Accuracy, sensitivity, specificity, intercorrelation and intracorrelation coefficients, area under the curve (AUC), and Delong test for ALN classification. The optimal RCNet model, that is, RCNet-tumor+ALN , achieved an AUC of 0.907, an accuracy of 0.831, a sensitivity of 0.824, and a specificity of 0.837 in the internal test cohort, as well as an AUC of 0.852, an accuracy of 0.828, a sensitivity of 0.792, and a specificity of 0.853 in the external test cohort. Additionally, with the assistance of RCNet-tumor+ALN , the radiologists' performance was improved (external test cohort, P< 0.05). DCE-MRI-based RCNet model could provide a noninvasive auxiliary tool to identify ALN metastasis preoperatively in breast cancer, which may assist radiologists in conducting more accurate evaluation of ALN status. 3 TECHNICAL EFFICACY: Stage 2.

MLRD-Net: 3D multiscale local cross-channel residual denoising network for MRI-based brain tumor segmentation

The precise segmentation of multimodal MRI images is the primary stage of tumor diagnosis and treatment. Current segmentation strategies often underutilize multiscale features, which can easily lead to loss of contextual information, reduction of low-level features and noise interference. To overcome these issues, a 3D multiscale local cross-channel residual denoising network (MLRD-Net) for an MRI-based brain tumor segmentation algorithm is proposed in this paper. Specifically, we employ encoder-decoder structure to connect local and global features, and enhance the receptive field of the network. Random slice operation has been conducted to enhance robustness. Then, residual blocks with pre-activation operation are developed in down-sampling stage, which effectively improves signal propagation along the network and alleviates network overfitting. Finally, the local cross-channel denoising mechanism is established to eliminate unimportant features without dimensionality reduction. Our proposal was evaluated in Brain Tumor Segmentation 2020 dataset (BraTS 2020), obtaining significantly improved results with mean Dice Similarity Coefficient metric of 0.91, 0.79, and 0.73 for the complete, tumor core, and enhancing tumor regions respectively. Besides, we conduct further practice on BraTS 2019, with the mean Dice Similarity Coefficient metric of 0.89, 0.80, and 0.75. Massive experiments demonstrate that our method is powerful and reliable. It increases little model complexity while achieving very competitive performance.

Driver Distraction Detection Based on the True Driver’s Focus of Attention

Effective driver distraction detection (DDD) can significantly improve driving safety. Inspired by the definition of driver distraction, this work aims to detect driver distraction based on the true driver’s focus of attention (TDFoA). This is accomplished based on two stages, the prediction of TDFoA and DDD based on the driver’s focus of attention (DFoA) and the TDFoA. However, this process is challenging due to the complex and dynamic traffic environment, momentary glimpses not related to the TDFoA in normal driving, the interference of noise (information unrelated to the TDFoA), the ignoring of multi-scale information from driving scenarios, and the variability of thresholds used to distinguish between driver distraction and non-distraction. To solve these problems, we design a deep 3D residual network with attention mechanism and encoder-decoder (D3DRN-AMED) based on successive frames with convolution LSTM for the prediction of TDFoA, where successive frames are used to eliminate the impact of momentary glimpses. The convolution LSTM achieves the transition of features in successive frames, considering the historical variation of driving scenarios. Attention mechanism based on soft thresholding is inserted into the D3DRN-AMED as nonlinear transformation layers to eliminate the noise-related features, and the encoder-decoder module is introduced to extract multi-scale features. A method based on a neural network is then proposed to detect driver distraction according to the difference or similarity between DFoA and TDFoA, which can accurately detect driver distraction without determining the threshold. Experimental results show that the proposed method can effectively detect driver distraction.

Ultrasound-based radiomics analysis for differentiating benign and malignant breast lesions: From static images to CEUS video analysis.

BackgroundContinuous contrast-enhanced ultrasound (CEUS) video is a challenging direction for radiomics research. We aimed to evaluate machine learning (ML) approaches with radiomics combined with the XGBoost model and a convolutional neural network (CNN) for discriminating between benign and malignant lesions in CEUS videos with a duration of more than 1 min.MethodsWe gathered breast CEUS videos of 109 benign and 81 malignant tumors from two centers. Radiomics combined with the XGBoost model and a CNN was used to classify the breast lesions on the CEUS videos. The lesions were manually segmented by one radiologist. Radiomics combined with the XGBoost model was conducted with a variety of data sampling methods. The CNN used pretrained 3D residual network (ResNet) models with 18, 34, 50, and 101 layers. The machine interpretations were compared with prospective interpretations by two radiologists. Breast biopsies or pathological examinations were used as the reference standard. Areas under the receiver operating curves (AUCs) were used to compare the diagnostic performance of the models.ResultsThe CNN model achieved the best AUC of 0.84 on the test cohort with the 3D-ResNet-50 model. The radiomics model obtained AUCs between 0.65 and 0.75. Radiologists 1 and 2 had AUCs of 0.75 and 0.70, respectively.ConclusionsThe 3D-ResNet-50 model was superior to the radiomics combined with the XGBoost model in classifying enhanced lesions as benign or malignant on CEUS videos. The CNN model was superior to the radiologists, and the radiomics model performance was close to the performance of the radiologists.

RETRACTED: A stroke image recognition model based on 3D residual network and attention mechanism

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

ME-PLAN: A deep prototypical learning with local attention network for dynamic micro-expression recognition

As one of the important psychological stress reactions, Micro-expressions (MEs) are spontaneous and subtle facial movements, which usually occur in a high-stake situation and can reveal genuine human feelings and cognition. ME, Recognition (MER) has essential applications in many fields such as lie detection, criminal investigation, and psychological healing. However, due to the challenges of learning discriminative ME features via fleeting facial subtle reactions as well as the shortage of available MEs data, this research topic is still far from well-studied. To this end, in this paper, we propose a deep prototypical learning framework, namely ME-PLAN, with a local attention mechanism for the MER problem. Specifically, ME-PLAN consists of two components, i.e., a 3D residual prototypical network and a local-wise attention module, where the former aims to learn the precise ME feature prototypes through expression-related knowledge transfer and episodic training, and the latter could facilitate the attention to the local facial movements. Furthermore, to alleviate the dilemma that most MER methods need to depend on manually annotated apex frames, we propose an apex frame spotting method with Unimodal Pattern Constrained (UPC) and further extract ME key-frames sequences based on the detected apex frames to train our proposed ME-PLAN in an end-to-end manner. Finally, through extensive experiments and interpretable analysis regarding the apex frame spotting and MER on composite-database, we demonstrate the superiority and effectiveness of the proposed methods.

Low-dose helical CT projection data restoration using noise estimation

To build a helical CT projection data restoration model at random low-dose levels. We used a noise estimation module to achieve noise estimation and obtained a low-dose projection noise variance map, which was used to guide projection data recovery by the projection data restoration module. A filtering back-projection algorithm (FBP) was finally used to reconstruct the images. The 3D wavelet group residual dense network (3DWGRDN) was adopted to build the network architecture of the noise estimation and projection data restoration module using asymmetric loss and total variational regularization. For validation of the model, 1/10 and 1/15 of normal dose helical CT images were restored using the proposed model and 3 other restoration models (IRLNet, REDCNN and MWResNet), and the results were visually and quantitatively compared. Quantitative comparisons of the restored images showed that the proposed helical CT projection data restoration model increased the structural similarity index by 5.79% to 17.46% compared with the other restoration algorithms (P < 0.05). The image quality scores of the proposed method rated by clinical radiologists ranged from 7.19% to 17.38%, significantly higher than the other restoration algorithms (P < 0.05). The proposed method can effectively suppress noises and reduce artifacts in the projection data at different low-dose levels while preserving the integrity of the edges and fine details of the reconstructed CT images.

ShChain_3D-ResNet: Sharding Blockchain with 3D-Residual Network (3D-ResNet) Deep Learning Model for Classifying DDoS Attack in Software Defined Network

The distributed denial of service (DDoS) vulnerabilities have rapidly extended and have been given different possibilities for even more advanced assaults on specific targets in recent times, thanks to the growth of innovative technology such as the Internet of Things (IoT) and Software-Defined Networking (SDN). The attack patterns route comprises unprotected and susceptible IoT systems that are internet-connected, as well as denial of service weaknesses in the SDN controllers, such as southbound connection exhaustion. (1) Background: The review does not go into detail about the symmetry blockchain approaches used to mitigate DDoS attacks, nor does it classify them in IoT; (2) To overcome the privacy issues, a novel deep learning-based privacy preservation method was proposed named ShChain_3D-ResNet. This novel method combines Sharding, blockchain and Residual Network for securing the SDN. Under this network, the proposed efficient attention module jointly learns attention to enforce the symmetry on weights for various channels in spatial dimension as well as attention weights of multiple frames in temporal dimension assistance of pre-training, updating, and dense convolution process; (3) Results: the proposed ShChain_3D-ResNet achieves 95.6% of accuracy, 97.3% of precision, 95.2% of recall, 94.4% of F1-score, 32.5 ms of encryption time and 35.2 ms of decryption time for dataset-1. Further, it achieves 97.3% accuracy, 95.3% precision, 96.1% recall, 98.2% F1-score, 32.1 ms of encryption time, and 36.2 ms of decryption time for dataset-2; (4) Conclusions: The Sharding strategy can increase ShChain performance while simultaneously utilizing Multi User (MU) resources for SDN.

Utility of unsupervised deep learning using a 3D variational autoencoder in detecting inner ear abnormalities on CT images

Background and purposeTo examine the diagnostic performance of unsupervised deep learning using a 3D variational autoencoder (VAE) for detecting and localizing inner ear abnormalities on CT images. MethodTemporal bone CT images of 6663 normal inner ears and 113 malformations were analyzed. For unsupervised learning, 113 images from both the malformation and normal cases were used as test data. Other normal images were used for training. A colored difference map representing differences between input and output images of 3D-VAE and the ratio of colored to total pixel numbers were calculated. Supervised learning was also investigated using a 3D deep residual network and all data were classified as normal or malformation using 10-fold cross-validation. ResultsFor unsupervised learning, a significant difference in the colored pixel ratio was seen between normal (0.00021 ± 0.00022) and malformation (0.00148 ± 0.00087) cases with an area under the curve of 0.99 (specificity = 92.0%, sensitivity = 99.1%). Upon evaluation of the difference map, abnormal regions were partially and not highlighted in 7% and 0% of the malformations, respectively. For supervised learning, which achieved 99.8% specificity and 90.3% sensitivity, a part of and no abnormal regions were highlighted on interpretation maps in 34% and 8% of the malformations, respectively. Abnormal regions were not highlighted in 4 malformation cases diagnosed as malformations and were highlighted in 6 cases misdiagnosed as normal. ConclusionsUnsupervised deep learning of 3D-VAE precisely detected inner ear malformations and localized abnormal regions. Supervised learning did not identify whole abnormal regions frequently and basis for diagnosis was sometimes unclear.

Channel-Wise Attention Mechanism in the 3D Convolutional Network for Lung Nodule Detection

Pulmonary nodule detection is essential to reduce the mortality of lung cancer. One-stage detection methods have recently emerged as high-performance and lower-power alternatives to two-stage lung nodule detection methods. However, it is difficult for existing one-stage detection networks to balance sensitivity and specificity. In this paper, we propose an end-to-end detection mechanism combined with a channel-wise attention mechanism based on a 3D U-shaped residual network. First, an improved attention gate (AG) is introduced to reduce the false positive rate by employing critical feature dimensions at skip connections for feature propagation. Second, a channel interaction unit (CIU) is designed before the detection head to further improve detection sensitivity. Furthermore, the gradient harmonizing mechanism (GHM) loss function is adopted to solve the problem caused by the imbalance of positive and negative samples. We conducted experiments on the LUNA16 dataset and achieved a performance with a competition performance metric (CPM) score of 89.5% and sensitivity of 95%. The proposed method outperforms existing models in terms of sensitivity and specificity while maintaining the attractiveness of being lightweight, making it suitable for automatic lung nodule detection.

Separable 3D residual attention network for human action recognition

Separable 3D residual attention network for human action recognition

3-Dimensional convolutional neural networks for predicting StarCraft Ⅱ results and extracting key game situations.

In real-time strategy games, players collect resources, control various units, and create strategies to win. The creation of winning strategies requires accurately analyzing previous games; therefore, it is important to be able to identify the key situations that determined the outcomes of those games. However, previous studies have mainly focused on predicting game results. In this study, we propose a methodology to predict outcomes and to identify information about the turning points that determine outcomes in StarCraft Ⅱ, one of the most popular real-time strategy games. We used replay data from StarCraft Ⅱ that is similar to video data providing continuous multiple images. First, we trained a result prediction model using 3D-residual networks (3D-ResNet) and replay data to improve prediction performance by utilizing in-game spatiotemporal information. Second, we used gradient-weighted class activation mapping to extract information defining the key situations that significantly influenced the outcomes of the game. We then proved that the proposed method outperforms by comparing 2D-residual networks (2D-ResNet) using only one time-point information and 3D-ResNet with multiple time-point information. We verified the usefulness of our methodology on a 3D-ResNet with a gradient class activation map linked to a StarCraft Ⅱ replay dataset.

Detection and staging of chronic obstructive pulmonary disease using a computed tomography-based weakly supervised deep learning approach.

Chronic obstructive pulmonary disease (COPD) is underdiagnosed globally. The present study aimed to develop weakly supervised deep learning (DL) models that utilize computed tomography (CT) image data for the automated detection and staging of spirometry-defined COPD. A large, highly heterogeneous dataset was established, consisting of 1393 participants retrospectively recruited from outpatient, inpatient, and physical examination center settings of four large public hospitals in China. All participants underwent both inspiratory chest CT scans and pulmonary function tests. CT images, spirometry data, demographic information, and clinical information of each participant were collected. An attention-based multi-instance learning (MIL) model for COPD detection was trained using CT scans from 837 participants. External validation of the COPD detection was performed with 620 low-dose CT (LDCT) scans acquired from the National Lung Screening Trial (NLST) cohort. A multi-channel 3D residual network was further developed to categorize GOLD stages among confirmed COPD patients. The attention-based MIL model used for COPD detection achieved an area under the receiver operating characteristic curve (AUC) of 0.934 (95% CI: 0.903, 0.961) on the internal test set and 0.866 (95% CI: 0.805, 0.928) on the LDCT subset acquired from the NLST. The multi-channel 3D residual network was able to correctly grade 76.4% of COPD patients in the test set (423/553) using the GOLD scale. The proposed chest CT-DL approach can automatically identify spirometry-defined COPD and categorize patients according to the GOLD scale. As such, this approach may be an effective case-finding tool for COPD diagnosis and staging. • Chronic obstructive pulmonary disease is underdiagnosed globally, particularly in developing countries. • The proposed chest computed tomography (CT)-based deep learning (DL) approaches could accurately identify spirometry-defined COPD and categorize patients according to the GOLD scale. • The chest CT-DL approach may be an alternative case-finding tool for COPD identification and evaluation.

LungSeek: 3D Selective Kernel residual network for pulmonary nodule diagnosis.

Early detection and diagnosis of pulmonary nodules is the most promising way to improve the survival chances of lung cancer patients. This paper proposes an automatic pulmonary cancer diagnosis system, LungSeek. LungSeek is mainly divided into two modules: (1) Nodule detection, which detects all suspicious nodules from computed tomography (CT) scan; (2) Nodule Classification, classifies nodules as benign or malignant. Specifically, a 3D Selective Kernel residual network (SK-ResNet) based on the Selective Kernel Network and 3D residual network is located. A deep 3D region proposal network with SK-ResNet is designed for detection of pulmonary nodules while a multi-scale feature fusion network is designed for the nodule classification. Both networks use the SK-Net module to obtain different receptive field information, thereby effectively learning nodule features and improving diagnostic performance. Our method has been verified on the luna16 data set, reaching 89.06, 94.53% and 97.72% when the average number of false positives is 1, 2 and 4, respectively. Meanwhile, its performance is better than the state-of-the-art method and other similar networks and experienced doctors. This method has the ability to adaptively adjust the receptive field according to multiple scales of the input information, so as to better detect nodules of various sizes. The framework of LungSeek based on 3D SK-ResNet is proposed for nodule detection and nodule classification from chest CT. Our experimental results demonstrate the effectiveness of the proposed method in the diagnosis of pulmonary nodules.

A Hybrid Parallelization Approach for Distributed and Scalable Deep Learning

Recently, Deep Neural Networks (DNNs) have recorded significant success in handling medical and other complex classification tasks. However, as the sizes of DNN models and the available datasets increase, the training process becomes more complex and computationally intensive, usually taking longer to complete. In this work, we have proposed a generic full end-to-end hybrid parallelization approach combining model and data parallelism for efficiently distributed and scalable training of DNN models. We have also proposed a Genetic Algorithm Based Heuristic Resources Allocation (GABRA) mechanism for optimal distribution of partitions on the available GPUs for computing performance optimization. We have applied our proposed approach to a real use case based on 3D Residual Attention Deep Neural Network (3D-ResAttNet) for efficient Alzheimer Disease (AD) diagnosis on multiple GPUs and compared with the existing state-of-the-art parallel methods. The experimental evaluation shows that our proposed approach is 20% averagely better than existing parallel methods in terms of training time and achieves almost linear speedup with little or no differences in accuracy performance when compared with the existing non-parallel DNN models.

A Hybrid Parallelization Approach for Distributed and Scalable Deep Learning

Recently, Deep Neural Networks (DNNs) have recorded great success in handling medical and other complex classification tasks. However, as the sizes of a DNN model and the available dataset increase, the training process becomes more complex and computationally intensive, which usually takes a longer time to complete. In this work, we have proposed a generic full end-to-end hybrid parallelization approach combining both model and data parallelism for efficiently distributed and scalable training of DNN models. We have also proposed a Genetic Algorithm based heuristic resources allocation mechanism (GABRA) for optimal distribution of partitions on the available GPUs for computing performance optimization. We have applied our proposed approach to a real use case based on 3D Residual Attention Deep Neural Network (3D-ResAttNet) for efficient Alzheimer Disease (AD) diagnosis on multiple GPUs. The experimental evaluation shows that the proposed approach is efficient and scalable, which achieves almost linear speedup with little or no differences in accuracy performance when compared with the existing non-parallel DNN models.

Research on the Identification and Evaluation of Aerobics Movements Based on Deep Learning

A deep learning approach is used in this study to provide insight into aerobics movement recognition, and the model is used for aerobics movement recognition. The model complexity is significantly reduced, while the multi-scale features of the target at the fine-grained level are extracted, significantly improving the characterization of the target, by embedding lightweight multi-scale convolution modules in 3D convolutional residual networks to increase the local perceptual field range in each layer of the network. Finally, using the channel attention mechanism, the key features are extracted from the multi-scale features. To create a dual-speed frame rate detection model, the fast-slow combination idea is fused into a 3D convolutional network. To obtain spatial semantic information and motion information in the video, the model uses different frame rates, and the two-channel information is fused with features using lateral concatenation. Following the acquisition of all features, the features are fed into a temporal detection network to identify temporal actions and to design a behavior recognition system for the network model to demonstrate the network model's applicability. The average scores of students in the experimental group were significantly higher than those in the control group in seven areas: set accuracy, movement amplitude, movement strength, body coordination, coordination of movement and music, movement expression, and aesthetics; the average scores of movement proficiency and body control in the experimental group were also significantly higher than those in the control group, but the differences were not significant. The differences between the eight indicators in the experimental group were not significant when compared to those in the preexperimental group, indicating that intensive rhythm training for students improves secondary school students' comprehension, proficiency, and presentation of aerobics sets.