Chinese Version
陕西省科技期刊编辑学会
Latest Issue
Issue 3 ， 2023
- Abstract：Computer-aided technologies have achieved excellent results in lung diseases screening.However, most of the existing studies models the known type of disease, which can lead to the risk of misdiagnosis and missed diagnosis to the unknown type of disease.In addition, current research primarily focuses on achieving high accuracy without solving the problems of misdiagnosis and missed diagnosis, making it difficult to apply in clinical practice.This paper proposes a more clinically applicable goal for computer-aided pulmonary disease screening by combing the doctor's diagnosis process: to ensure a zero missed diagnosis rate while reducing the misdiagnosis rate. To achieve the screening goal mentioned above, this paper proposes an improved variational autoencoder network based on one-class classification for preliminary screening of lung diseases and extraction of deep encoding features from X-ray images. Then, by combining the complementary advantages between radiomics features based on doctors' experience and deep learning features, an ensemble learning model is constructed to complete the final lung disease screening. The method in this study improved the classification performance and reduced the missed diagnosis rate with only normal X-ray images involved in training. Experimental results show that the proposed method achieves an AUC value of 0.984 8±0.002 3 and reduces the misdiagnosis rate to 0.149 8±0.005 7 when the missed diagnosis rate is zero, further validating that the method can effectively achieve the pulmonary diseases screening goal of this paper. At the same time, we compared the screening results of the ensemble model and individual deep learning model.We found that the results of the ensemble model was significantly better than the deep learning model, which further highlights the effectiveness of integrating doctors' experience.Keywords：lung disease screening;chest X-ray;radiomics;one-class classification;ensemble learning
- 4
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Depression is one of the most prevalent psychological and psychiatric disorders today. Traditional diagnostic approaches have subjective limitations that rely on doctors' experience; artificial intelligence applied to the detection of depression can perform specific data analysis, thus assisting doctors engaged in the diagnosis of psychological and psychiatric disorders to improve diagnostic efficiency. The first generation of knowledge-driven depression detection can only solve the problem of certainty in a fully informed and structured environment, where the choice of depression-related features directly affects the recognition results. The second generation of data-driven depression detection needs to be driven by a large amount of data, and the results obtained under black box models alone are not credible enough. The third generation of depression detection ensures the processing of information through information fusion, combining heterogeneous information from different sources high quality, combining the respective advantages of the first two generations of depression analysis systems, manually extracted features combined with depth features can better tap into depression feature information, decision fusion is highly fault tolerant, and the fused model can increase the reliability of the results and provide a more comprehensive analysis of depression data. This paper examines a large amount of relevant literature, summarises and analyses existing research results, and points out the future development direction of AI depression diagnosis research.Keywords：artificial intelligence(AI);diagnosis of depression;machine learning;deep learning;data fusion
- 4
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：With the increasing incidence of anterior segment diseases such as glaucoma, the analysis of anterior segment images has received more and more attention. Moreover, the precise localization of the scleral spur(SS) is of great significance for the measurement of anterior segment structural parameters and clinical diagnosis. It presents a two-stage localization network from " coarse" to " fine" for optical coherence tomography images of the anterior segment. First, a ROI region detection network was used to identify ROI regions centered on the scleral spur, and the feature extraction ability of the network was improved by adding the ACmix module to the backbone network. Afterwards, a lightweight network Lite-HRNet was used as a fine-tuning correction network to further extract image detail features, based on heatmap regression to obtain a more accurate scleral process location. Finally, we tested our method on two datasets, reaching an average error of 11.74 and 9.82 respectively. Many experiments show that our method is better than other existing deep learning-based methods and has good detection effect.Keywords：scleral spur localization;anterior segment optical coherence tomography;deep convolutional network
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Breast cancer MRI data often have the problem of different sequences missing from the same patient due to different acquisition methods, different equipment or patients and other self-inflicted reasons in different hospitals. These methods often require different MRI sequences to appear in pairs, making it difficult to handle missing data. In addition, these methods tend to focus on the quality of the entire image, and lack the ability to monitor the quality of the focal area, which is more valuable for disease diagnosis. In this paper, we design a new feature-enhanced dual-attention aligned generative adversarial network, DA-RegGAN, inspired by the adaptive alignment of image spatial distribution in RegGAN. The gradient normalization constraint is added to the discriminator, which mainly solves the phenomenon that the network is unstable and prone to pattern running, and enables the network to generate a global map containing clearer lesion details. In this paper, ablation experiments, comparison experiments between different image generation algorithms and tumour classification experiments are carried out on 1 697 breast case data to further validate the effectiveness of the method in this paper. Compared with the original RegGAN, the global image generation quality and local lesion image generation quality were both improved, with the local image quality improved by 0.518 and SSIM improved by 0.021 compared with the original PSNR; the global image quality improved by 0.584 and SSIM improved by 0.020 compared with the original PSNR.Keywords：generative adversarial network;breast MRI image generation;attention mechanism;gradient normalisation
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Insomnia is a typical sleep disorder, which is characterized by difficulty falling asleep, short duration of deep sleep and early awakening etc. Clinically, some patients with insomnia exhibit increased EEG alpha activity during rapid eye movement (REM) sleep stage, but the relevant biophysical mechanisms still remain unclear. Therefore, by combining Liley neural computational model and clinical EEG data from insomnia patients, this paper focuses on exploring the underlying mechanisms of the typical rhythms during REM stage of insomnia patient from a computational neuroscience perspective. Firstly, an automatic key parameter selection and estimation method for Liley model is designed based on Markov chain Monte Carlo algorithm. Secondly, by combining EEG data from insomnia patients, the key model parameters are identified and a mechanistic hypothesis of increased EEG alpha activity during REM stage is developed for insomnia patients: The decrease in the inhibitory synaptic activity leads to the enhanced alpha activity. The obtained results are helpful in improving the sleep quality and controlling the progression of insomnia patients.Keywords：insomnia;EEG alpha rhythms;Liley model;key parameters
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Prolonged disorders of consciousness (PDOC) is a kind of neurological disease caused by severe brain damage, which results in loss of consciousness more than 28 days. Vegetative state (VS), minimally conscious stateplus (MCS+ ) and minimally conscious state minus (MCS-) are the main states of prolonged disorders of consciousness. PDOC assessment is helpful for formulating reasonable treatment plans, promoting recovery of consciousness in PDOC patients.In clinic, the main assessment methods are behavioral rating scales, imaging examinations and so on.But above methods are impossible for continuously monitoring patients' consciousness in real-time. Electroencephalogram(EEG)can record the state of brain's electrical activity reflecting the level of consciousness in real-time. Moreover, sleep EEG is closely related to the level of consciousness in PDOC patients. Therefore, a novelfusion feature extraction method for PDOC assessment is proposed based on EEG data. Firstly, the PDOC-EEG signals are preprocessed by data expanding, filtering and denoising. Secondly, the pathological features of PDOC-EEG are extracted using time-domain, frequency-domain and nonlinear analysis. In this process, two new features, power weight-based channel coherence and dispersion of frequency correlation are designed. Meanwhile, consider the proportion of sleep stage duration as feature, which is related to the level of consciousnes, using EEG, EOG(electro-oculogram) and EMG(electromyogram) data. Then, fuse the extracted features. Finally, the automatic PDOC assessment is realized using random forest and back propagation neural network classifier. This method is verified by dataset of PDOC patients collected in the federal research and clinical center of intensive care medicine and rehabilitology in Russia. Numerical experiment shows that accuracy and sensitivity of the proposed method are 94.2%and 94.1%.Keywords：prolonged disorders of consciousness(PDOC);electroencephalogram(EEG);sleep stage;fusion feature;back propagation neuron netwok
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Multi-modal corpus is one of the important tools for medical research, clinical diagnosis and teaching. Most of the existing medical corpus only have text data, lacking matching images, which leads to inadequate information. Additionally, a large number of medical images don't have clear semantic labels, which makes them difficult to be used in corpus construction. To solve the above problems, a novel dermoscopic image classification method for multi-modal medical corpus construction is proposed. Through accurate classification of dermoscopic images, we obtained semantic labels, and then matching them with relevant text by natural language processing method. In this way, a multi-modal corpus with images and texts was established. First, traditional image classification methods based on machine learning are weak in feature extraction of lesions and susceptible to background noise, resulting in poor classification accuracy. Considering the above, in this paper, a two-stream network was constructed to enhance the feature representation by fusing lesions' shapes and texture features. Second, in order to reduce information redundancy caused by feature fusion, a feature selection method based on channel attention mechanism was introduced to focus on the key features and suppress the influence of noise. In addition, aiming at the problem of model optimization difficulty caused by the imbalance in the number of benign and malignant samples in dermatoscopic images, asymmetric loss function was introduced to improve the robustness of model. Experimental results on ISIC dermatoscopic image dataset proved that the proposed method can accurately and efficiently categorize dermatoscopic images and match images with corresponding medical records to construct a multi-modal medical corpus.Keywords：multi-modal corpus;dermoscopic image;image classification;convolutional neural network;natual language processing
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Due to the increasing number and complexity of diagnostic imaging studies, radiologists are now faced with a heavy workload in their daily image reviewing task. It has become a major concern to reduce the burden of image reviewing process for radiologists and help them improve the efficiency of diagnosis. The recognition and understanding of interactive intent during radiologists image review can be used to develop new intelligent review systems that can provide adaptive tools and optimize user workflow to help radiologists perform digital image review tasks more efficiently and accurately. Currently, radiologists still primarily use a graphical user interface based on mouse input for medical image reviewing. To this end, this paper proposes an intention understanding method of medical image reviewing based on mouse interaction trajectories.Firstly, semantic segmentation of mouse interaction trajectories is performed, and then the semantic annotation of mouse interaction behaviors is implemented based on logical reasoning and supervised learning for the segmented trajectory subsequences. The method is validated on a self-built mouse trajectory dataset under the TIoU threshold of [0.3∶0.8∶0.1], and the average recall, precision and F-score of the method reach 86.7%, 83.1% and 85.4%, respectively. The results show that the method can effectively identify the interactive intention based on the implicit mouse interaction data, which confirms the feasibility and effectiveness of the interactive intention recognition method based on semantic understanding of mouse interaction trajectories in the field of medical images assisted reviewing research.Keywords：interactive intention;mouse interaction trajectory;trajectory semantic understanding;medical imaging diagnosis;human-computer interaction
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：The research on spatial and temporal distribution is a necessary prerequisite and important basis for the spatial integration and protection of historical and cultural heritage. Taking 166 grottoes in Gansu Province as an example, the spatial and temporal distribution characteristics and influencing factors of grottoes were analyzed by GIS spatial analysis technology. The results show that: ① The open niche statues in grottoes show an evolutionary trend of increasing first and then decreasing and then increasing, with the peak periods of open niche statues in Wei, Jin, Southern and Northern Dynasties, Sui, Tang and Five dynasties. ② A belt-shaped high-density area with Tianshui and Pingliang as the core has been formed in eastern Gansu. From the Wei, Jin, Southern and Northern Dynasties to the Ming and Qing Dynasties, the high density area of new grottoes was Tianshui, Jiuquan and Zhangye.③ The spatial distribution of grottoes shifted significantly in different periods, and the distribution center of grottoes shifted from the southeast to the northwest and then continued to the southeast. ④ The spatial and temporal distribution of grottoes is mainly affected by topography, river system, stratum lithology, political economy, buddhism development, road traffic and other factors. This has important reference significance for the integrated protection, value inheritance and sustainable utilization of the grottoes in Gansu Province.Keywords：grottoes;spatial and temporal distribution;influencing factors;spatial analysis;Gansu province
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Taking the national key cultural relics protection units in Gansu Province as the research object, based on the spatial analysis technology of geographic information, the time evolution, spatial distribution characteristics and influencing factors of cultural relics in Gansu Province is studied through GIS and other quantitative analysis tools.It presents that the distribution of cultural relics in Gansu Province is in the form of aggregation distribution as a whole, which has significant regional differences in regional space, and there are also significant stage characteristics in each historical period. By analyzing the causes of its layout, it is found that the interaction of natural factors and social factors has a synergistic driving effect on the formation of the spatio-temporal pattern of national key cultural relics protection units. Based on this, some suggestions are put forward for the protection and utilization of cultural relics.Keywords：National Key Cultural Relics Protection Units;GIS;spatio-temporal distribution;forming factors;Gansu province
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：In order to explore the correlation between weathering diseases and meteorological environment characteristics in Cave 147 of Bingling Temple Grottoes, the weight of weathering products, temperature and humidity characteristics at different spatial locations were compared and analyzed.The results showed that May to November was the main period of weathering, the weathering products weight accounted for 98.7% of the total, and July to August is the most severe weathering months accounted for 73.4% of the total amount.The rear of the cave is the main area of weathering, the weight accounting for 92.3% of the total monitored area.The relative humidity inside the cave is mainly affected by the rainfall. The relative humidity in the rainy season from May to October is relatively high and fluctuates greatly, with the number of days exceeding 60% being 178 days. The relative humidity in different areas of the cave is negatively correlated with the temperature. The relative humidity in the rear space is higher than that in the front, and the upper space is lower than that in the middle and lower parts.The results show that the degree of weathering damage in Cave 147 corresponds to the meteorological environment in space and time. Combined with the results of soluble salt analysis, it can be preliminarily inferred that the high humidity environment is the important meteorological element of weathering damage in Cave 147.Keywords：grottoes;weathering disease;meteorological environment;temperature;relative humidity
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Classical Gauss sums is one kind sums of the exponential functions weighted by character functions, which occupies an important position in the study and practical application of number theory. In this paper, we focus on the problem of calculating formula of one kind square power mean of special Gauss sums. By using elementary methods, analytical methods and the properties of character sums, we obtain an exact calculating formula involving the classical Gauss sums τ(χ8 ) when p is an odd prime with p≡1 mod 8, where χ8 denotes an eight-order character modulo p. The results not only expand the research content of classical Gauss sums, but also contribute to the further development of relevant research work.Keywords：the classical Gauss sums;elementary method;analytic method;calculating formula
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：As a new generalization of the Dedekind type DC sums, the poly-Dedekind type DC sums are introduced, which are obtained from the Dedekind type DC sums by replacing Euler functions by poly-Euler functions of arbitrary indices arising from polylogarithm functions. By using the definitions of polylogarithm functions, Stirling numbers of second kind, and Euler polynomials, several properties of poly-Euler functions are obtained, including the relations between this type of poly-Euler numbers and Stirling numbers of second kind, the relations between this type of poly-Euler polynomials and Euler polynomials and Stirling numbers of second kind. The poly-Dedekind type DC sums are shown to satisfy a reciprocity relation. It can be further explored in connection with modular forms, ζ functions, and trigonometric sums, just as in the cases of Apostol-Dedekind sums.Keywords：poly-Dedekind type DC sums;polylogarithm functions;poly-Euler polynomials
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：This paper mainly presents a new class of generalized Gauss sums. In order to find the potential relationship between these sums, we start from their definition, and study the fourth means of this new generalized Gauss sums by applying elementary analytic methods and some important qualities related to trigonometric sums. This result extends the classical Gauss sums and Kloosterman sums in analytic number theory, and makes a new contribution to the further development of this field. Finally, by calculating, an important identity is given. At the same time, we also put forward some problems that still exist and have not been solved in this field.Keywords：a new generalized Gauss sums;the fourth power mean;elementary method;computational formula
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：The research on exponential sums is very important in number theory and practical application. This paper mainly discusses the properties of generalized two-term exponential sums. By means of elementary method, analytical method and the number of solutions of congruence equation, this paper studies the calculation of the fourth power mean of a kind of generalized two-term exponential sums, and gives an exact calculation formula and asymptotic formula. At the same time, the research results of this paper also provide some new and effective ideas and methods for the calculation of high-th two-term exponential sums, which is innovative.Keywords：the generalized two-term exponential sums;fourth power mean;elementary method;calculating formula;asymptotic formula
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：The calculation of the mean value of exponential sums C(m, n, r, s; q) and its upper bound estimation is closely related to many number theory problems, such as Waring's problem. Let p be an odd prime, this paper focuses on the problem of the calculation of the fourth power mean value of one kind two-term exponential sums when parameter n=1 and exponent r=4, s=2. By utilizing the analytic methods, the odd-even property and orthogonality of Dirichlet character, and the properties of the character sums, we study the calculating problem of the fourth power mean of the two-term exponential sums for the form as C(m, 1, 4, 2; p), and give an exact calculating formula for it when the prime p≡3 mod 4. At the same time, for such research content, some open problems in this field are also proposed.Keywords：the two-term exponential sums;fourth power mean;computational formula;analytic mathods
- 0
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：The distribution properties of the error term of the D. H. Lehmer problem on incomplete intervals are helpful for studying the distribution of integers and their inverse. This paper mainly discusses the mean value distribution properties of the error term of D. H. Lehmer problem E(a, p) on incomplete intervals. By using the relations between E(a, p) and Dirichlet L-function and some mean value properties of Dirichlet L-function, several strong asymptotic formulas of E(a, p) are given. Combined with the conclusion in reference [4], it can be seen that there are significant differences in the cancellation of the error of D. H. Lehmer problem in these two intervals. This result not only expands the research content of the error term of the D. H. Lehmer problem on incomplete intervals, but also contributes to the further development of relevant research work.Keywords：D. H. Lehmer problem on half interval;error term;Dirichlet L-function;mean value;cancellation
- 2
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Based on drilling, seismic and gas testing data, the structure, paleogeomorphology, sedimentary facies, trap, gas and water distribution are analyzed for Benxi Formation in Ganquan Fuxian area. The results show that reservoirs and stones deposited in tidal-flat-lagoon barrier environment. The sandstones mainly consist of two barrier bars parallel to the NW orientation shorelines, located on both sides of the ancient karst high belt. The underlying stratum in the middle east of the study area is the 6th Member of Ordovician Maiagou Formation. Due to the lack of Majiagou reservoir and downward migration channel, oil and gas are mainly accumulated in the east barrier of Benxi Formation. In the southwest of the study area, the ancient karst groove exited under the Benxi Formation, which make the coal measure hydrocarbon source rock to connect laterally with the karst limestone reservoir of 5th Member of Miajiagou Formation. Therefore, the 5th Member becomes the main gas reservoir while the western barrier of the Benxi Formation is relatively poorly charged with gas. The trap type is dominated by lenticular sandstone bodies, with a small amount of sandstone pinching out traps.The water zones consist mainly of thin sand layers with a single layer thickness of less than 2 m, which is tidal channel or barrier edge sandstone. Some thicker water layer sandstones are located between gas zone laterally, which may be related to the activity and destruction of local large offset faults during the reservoir forming period. The dry zones consist of tight sandstones with porosity less than 3.2% or permeability less than 0.07×10-3μm2, mainly composed of dark gray tuffaceous sandstone and light gray lithic quartz. The logging porosity of dry zones is less than 3.2%, or 0~3.2% under the microscope.The tuffaceous sandstone has dark color (dark gray, referred to as black sandstone for short), fine grain size (fine sandstone or silty fine sandstone), thin single layer thickness of about 0.5~2 m, and is randomly sandwiched in the light gray barrier or tidal channel sandstone. The upper and lower Member of Benxi Formatioin may contain one layer of tuffaceous sandstone, which is characterized by high volcanic dust matrix, high content of chert and rock debris, basal cementation, poor particle sorting and roundness. Light grey tight lithic quartz sandstone is characterized by clayey and dolomitic cementation, grain linear contact or stylolite contact, strong compaction and pore uneven distribution. According to the control of sedimentary facies and physical properties on gas accumulation, favorable reservoir distribution are predicted using seismic attributes and gas detection, it is believed that there are two barriers oriented towards the northwest that have developed in each of the first and second sections of the study area. The interior of the sandbar barrier is a highly productive area, while the physical attributes of the barrier's edge deteriorate, leading to a decrease in productivity. The thick sandstone, which has a high water content, is mainly influenced by the activity of the Yanshanian North Northeast fault.Keywords：Benxi Formation;paleogeomorphy;sedimentary facies;sandbody distribution;reservoir control factor;gas identification
- 4
- |
- 0
- |
- 0
Published：2023-06-26 - Abstract：Geochemical research on the crude oils in the strata shallower than the Chang-6 member of Yanchang Formation in the Zhidan-Jingbian area was carried out using the full hydrocarbon gas chromatography and saturated hydrocarbon chromatography-mass spectrometry. Our results show that the source-related indexes of these oils are similar, which suggest aparent material imported by mixed organic matter and a sedimentary environment of source rocks with weak oxidation and reduction and poor water column stratification. Their maturity indexes are also similar and indicate that all of them are mature oils. However, the distribution characteristics of n-alkanes and phase fractionation indexes are obviously different between the oils in the Yan'an and Yanchang formations. The former were characterized by the disorderly distribution of n-alkanes below C18, " dislocation" occurring at C11, and the values of toluene/n-heptane generally less than 0.2. The latter were characterized by the relatively regular distribution of normal alkanes and the values of toluene/n-heptane generally greater than 0.2. In Yan'an Formation, the maturities of crude oils near the ancient river channel are generally lower than those far from the ancient river channel, and the oil maturity distribution on the plane is very disorderly. According to the analysis, the studied oils in the area are expected to originate from the Chang 7 source rocks in the central basin. The abnormal n-alkanes distribution of the oils in Yan'an Formation is related to the separation and mixing of light-heavy components of oils during the vertical migration along faults/fractures. The oils from the Chang 7 source rocks first migrated laterally through sand body towards the northeast within Yanchang Formation, and then migrated vertically along faults/fractures and charged into Yan'an Formation. The distribution of oil reservoirs within Yan'an Formation is controlled by the distribution of oil-migration-related faults/fractures, which is the cause that oil reservoirs are still developed in Yan'an Formation far away from the ancient rivers.Keywords：Ordos Basin;Yan'an Formation;Zhidan;Jingbian;crude oil geochemistry;oil accumulation
- 3
- |
- 0
- |
- 0
Published：2023-06-26
0