Alzheimer's disease (AD) is an irreversible neurodegenerative disorder that damages patients' memory and cognitive abilities. Therefore, the diagnosis of AD holds significant importance. The interactions between regions of interest (ROIs) in the brain often involve multiple areas collaborating in a nonlinear manner. Leveraging these nonlinear higher-order interaction features to their fullest potential contributes to enhancing the accuracy of AD diagnosis. To address this, a framework combining nonlinear higher-order feature extraction and three-dimensional (3D) hypergraph neural networks is proposed for computer-assisted diagnosis of AD. First, a support vector machine regression model based on the radial basis function kernel was trained on ROI data to obtain a base estimator. Then, a recursive feature elimination algorithm based on the base estimator was applied to extract nonlinear higher-order features from functional magnetic resonance imaging (fMRI) data. These features were subsequently constructed into a hypergraph, leveraging the complex interactions captured in the data. Finally, a four-dimensional (4D) spatiotemporal hypergraph convolutional neural network model was constructed based on the fMRI data for classification. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) database demonstrated that the proposed framework outperformed the Hyper Graph Convolutional Network (HyperGCN) framework by 8% and traditional two-dimensional (2D) linear feature extraction methods by 12% in the AD/normal control (NC) classification task. In conclusion, this framework demonstrates an improvement in AD classification compared to mainstream deep learning methods, providing valuable evidence for computer-assisted diagnosis of AD.
Humans ; Alzheimer Disease/diagnostic imaging* ; Neural Networks, Computer ; Magnetic Resonance Imaging/methods* ; Neuroimaging/methods* ; Diagnosis, Computer-Assisted ; Brain ; Cognitive Dysfunction

Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.
X-Rays ; Algorithms ; Diagnosis, Computer-Assisted ; Thorax/diagnostic imaging* ; Lung/diagnostic imaging* ; Image Processing, Computer-Assisted

Heart valve disease (HVD) is one of the common cardiovascular diseases. Heart sound is an important physiological signal for diagnosing HVDs. This paper proposed a model based on combination of basic component features and envelope autocorrelation features to detect early HVDs. Initially, heart sound signals lasting 5 minutes were denoised by empirical mode decomposition (EMD) algorithm and segmented. Then the basic component features and envelope autocorrelation features of heart sound segments were extracted to construct heart sound feature set. Then the max-relevance and min-redundancy (MRMR) algorithm was utilized to select the optimal mixed feature subset. Finally, decision tree, support vector machine (SVM) and k-nearest neighbor (KNN) classifiers were trained to detect the early HVDs from the normal heart sounds and obtained the best accuracy of 99.9% in clinical database. Normal valve, abnormal semilunar valve and abnormal atrioventricular valve heart sounds were classified and the best accuracy was 99.8%. Moreover, normal valve, single-valve abnormal and multi-valve abnormal heart sounds were classified and the best accuracy was 98.2%. In public database, this method also obtained the good overall accuracy. The result demonstrated this proposed method had important value for the clinical diagnosis of early HVDs.
Humans ; Heart Sounds ; Heart Valve Diseases/diagnosis* ; Algorithms ; Support Vector Machine ; Signal Processing, Computer-Assisted

Objective: To investigate the detection and diagnostic efficacy of chest radiographs for ≤30 mm pulmonary nodules and the factors affecting them, and to compare the level of consistency among readers. Methods: A total of 43 patients with asymptomatic pulmonary nodules who consulted in Cancer Hospital, Chinese Academy of Medical Sciences from 2012 to 2014 and had chest CT and X-ray chest radiographs during the same period were retrospectively selected, and one nodule ≤30 mm was visible on chest CT images in the whole group (total 43 nodules in the whole group). One senior radiologist with more than 20 years of experience in imaging diagnosis reviewed CT images and recording the size, morphology, location, and density of nodules was selected retrospectively. Six radiologists with different levels of experience (2 residents, 2 attending physicians and 2 associate chief physicians independently reviewed the chest images and recorded the time of review, nodule detection, and diagnostic opinion. The CT imaging characteristics of detected and undetected nodules on X images were compared, and the factors affecting the detection of nodules on X-ray images were analyzed. Detection sensitivity and diagnosis accuracy rate of 6 radiologists were calculated, and the level of consistency among them was compared to analyze the influence of radiologists' seniority and reading time on the diagnosis results. Results: The number of nodules detected by all 6 radiologists was 17, with a sensitivity of detection of 39.5%(17/43). The number of nodules detected by ≥5, ≥4, ≥3, ≥2, and ≥1 physicians was 20, 21, 23, 25, and 28 nodules, respectively, with detection sensitivities of 46.5%, 48.8%, 53.5%, 58.1%, and 65.1%, respectively. Reasons for false-negative result of detection on X-ray images included the size, location, density, and morphology of the nodule. The sensitivity of detecting ≤30 mm, ≤20 mm, ≤15 mm, and ≤10 mm nodules was 46.5%-58.1%, 45.9%-54.1%, 36.0%-44.0%, and 36.4% for the 6 radiologists, respectively; the diagnosis accuracy rate was 19.0%-85.0%, 16.7%-6.5%, 18.2%-80.0%, and 0%-75.0%, respectively. The consistency of nodule detection among 6 doctors was good (Kappa value: 0.629-0.907) and the consistency of diagnostic results among them was moderate or poor (Kappa value: 0.350-0.653). The higher the radiologist's seniority, the shorter the time required to read the images. The reading time and the seniority of the radiologists had no significant influence on the detection and diagnosis results (P>0.05). Conclusions: The ability of radiographs to detect lung nodules ≤30 mm is limited, and the ability to determine the nature of the nodules is not sufficient, and the increase in reading time and seniority of the radiologists will not improve the diagnostic accuracy. X-ray film exam alone is not suitable for lung cancer diagnosis.
Humans ; Retrospective Studies ; Solitary Pulmonary Nodule/diagnostic imaging* ; Radiography ; Multiple Pulmonary Nodules/diagnostic imaging* ; Tomography, X-Ray Computed/methods* ; Lung Neoplasms/diagnostic imaging* ; Sensitivity and Specificity ; Radiographic Image Interpretation, Computer-Assisted/methods*

Computer-aided diagnosis (CAD) systems play a very important role in modern medical diagnosis and treatment systems, but their performance is limited by training samples. However, the training samples are affected by factors such as imaging cost, labeling cost and involving patient privacy, resulting in insufficient diversity of training images and difficulty in data obtaining. Therefore, how to efficiently and cost-effectively augment existing medical image datasets has become a research hotspot. In this paper, the research progress on medical image dataset expansion methods is reviewed based on relevant literatures at home and abroad. First, the expansion methods based on geometric transformation and generative adversarial networks are compared and analyzed, and then improvement of the augmentation methods based on generative adversarial networks are emphasized. Finally, some urgent problems in the field of medical image dataset expansion are discussed and the future development trend is prospected.
Humans ; Diagnosis, Computer-Assisted ; Diagnostic Imaging ; Datasets as Topic

Objective To explore the optimal parameters for virtual mono-energetic imaging of liver solid lesions. Methods A retrospective analysis was performed on 60 patients undergoing contrast-enhanced spectral CT of the abdomen.The iodine concentration values of hepatic arterial phase images and the CT values of different mono-energetic images were measured.The correlation coefficient and coefficient of variation were calculated. Results The average correlation coefficients between iodine concentrations and CT values of hepatic solid lesion images at 40,45,50,55,60,65,and 70 keV were 0.996,0.995,0.993,0.989,0.978,0.970,and 0.961,respectively.The correlation coefficients at 40(P=0.007),45(P=0.022),50 keV (P=0.035)were higher than that at 55 keV,and the correlation coefficients at 40 keV(P=0.134) and 45 keV(P=0.368) had no significant differences from that at 50 keV.The coefficients of variation of the CT values at 40,45,and 50 keV were 0.146,0.154,and 0.163,respectively. Conclusion The energy of 40 keV is optimal for virtual mono-energetic imaging of liver solid lesions in the late arterial phase,which is helpful for the diagnosis of liver diseases.
Humans ; Tomography, X-Ray Computed ; Retrospective Studies ; Abdomen ; Iodine ; Liver/diagnostic imaging* ; Signal-To-Noise Ratio ; Radiographic Image Interpretation, Computer-Assisted/methods*

Objective To evaluate the impact of deep learning reconstruction algorithm on the image quality of head and neck CT angiography (CTA) at 100 kVp. Methods CT scanning was performed at 100 kVp for the 37 patients who underwent head and neck CTA in PUMC Hospital from March to April in 2021.Four sets of images were reconstructed by three-dimensional adaptive iterative dose reduction (AIDR 3D) and advanced intelligent Clear-IQ engine (AiCE) (low,medium,and high intensity algorithms),respectively.The average CT value,standard deviation (SD),signal-to-noise ratio (SNR),and contrast-to-noise ratio (CNR) of the region of interest in the transverse section image were calculated.Furthermore,the four sets of sagittal maximum intensity projection images of the anterior cerebral artery were scored (1 point:poor,5 points:excellent). Results The SNR and CNR showed differences in the images reconstructed by AiCE (low,medium,and high intensity) and AIDR 3D (all P<0.01).The quality scores of the image reconstructed by AiCE (low,medium,and high intensity) and AIDR 3D were 4.78±0.41,4.92±0.27,4.97±0.16,and 3.92±0.27,respectively,which showed statistically significant differences (all P<0.001). Conclusion AiCE outperformed AIDR 3D in reconstructing the images of head and neck CTA at 100 kVp,being capable of improving image quality and applicable in clinical examinations.
Humans ; Computed Tomography Angiography/methods* ; Radiation Dosage ; Deep Learning ; Radiographic Image Interpretation, Computer-Assisted/methods* ; Signal-To-Noise Ratio ; Algorithms

In recent years, epileptic seizure detection based on electroencephalogram (EEG) has attracted the widespread attention of the academic. However, it is difficult to collect data from epileptic seizure, and it is easy to cause over fitting phenomenon under the condition of few training data. In order to solve this problem, this paper took the CHB-MIT epilepsy EEG dataset from Boston Children's Hospital as the research object, and applied wavelet transform for data augmentation by setting different wavelet transform scale factors. In addition, by combining deep learning, ensemble learning, transfer learning and other methods, an epilepsy detection method with high accuracy for specific epilepsy patients was proposed under the condition of insufficient learning samples. In test, the wavelet transform scale factors 2, 4 and 8 were set for experimental comparison and verification. When the wavelet scale factor was 8, the average accuracy, average sensitivity and average specificity was 95.47%, 93.89% and 96.48%, respectively. Through comparative experiments with recent relevant literatures, the advantages of the proposed method were verified. Our results might provide reference for the clinical application of epilepsy detection.
Algorithms ; Child ; Deep Learning ; Electroencephalography ; Epilepsy/diagnosis* ; Humans ; Seizures/diagnosis* ; Signal Processing, Computer-Assisted ; Wavelet Analysis

Electrocardiogram (ECG) can visually reflect the physiological electrical activity of human heart, which is important in the field of arrhythmia detection and classification. To address the negative effect of label imbalance in ECG data on arrhythmia classification, this paper proposes a nested long short-term memory network (NLSTM) model for unbalanced ECG signal classification. The NLSTM is built to learn and memorize the temporal characteristics in complex signals, and the focal loss function is used to reduce the weights of easily identifiable samples. Then the residual attention mechanism is used to modify the assigned weights according to the importance of sample characteristic to solve the sample imbalance problem. Then the synthetic minority over-sampling technique is used to perform a simple manual oversampling process on the Massachusetts institute of technology and Beth Israel hospital arrhythmia (MIT-BIH-AR) database to further increase the classification accuracy of the model. Finally, the MIT-BIH arrhythmia database is applied to experimentally verify the above algorithms. The experimental results show that the proposed method can effectively solve the issues of imbalanced samples and unremarkable features in ECG signals, and the overall accuracy of the model reaches 98.34%. It also significantly improves the recognition and classification of minority samples and has provided a new feasible method for ECG-assisted diagnosis, which has practical application significance.
Algorithms ; Arrhythmias, Cardiac/diagnosis* ; Electrocardiography ; Humans ; Memory, Short-Term ; Neural Networks, Computer ; Signal Processing, Computer-Assisted

Early screening based on computed tomography (CT) pulmonary nodule detection is an important means to reduce lung cancer mortality, and in recent years three dimensional convolutional neural network (3D CNN) has achieved success and continuous development in the field of lung nodule detection. We proposed a pulmonary nodule detection algorithm by using 3D CNN based on a multi-scale attention mechanism. Aiming at the characteristics of different sizes and shapes of lung nodules, we designed a multi-scale feature extraction module to extract the corresponding features of different scales. Through the attention module, the correlation information between the features was mined from both spatial and channel perspectives to strengthen the features. The extracted features entered into a pyramid-similar fusion mechanism, so that the features would contain both deep semantic information and shallow location information, which is more conducive to target positioning and bounding box regression. On representative LUNA16 datasets, compared with other advanced methods, this method significantly improved the detection sensitivity, which can provide theoretical reference for clinical medicine.
Algorithms ; Humans ; Lung Neoplasms/diagnostic imaging* ; Neural Networks, Computer ; Radiographic Image Interpretation, Computer-Assisted/methods* ; Tomography, X-Ray Computed/methods*