AIM: To explore a segmentation algorithm based on deep learning to achieve accurate diagnosis and treatment of patients with retinal fluid.METHODS: A two-dimensional(2D) fully convolutional network for retinal segment...AIM: To explore a segmentation algorithm based on deep learning to achieve accurate diagnosis and treatment of patients with retinal fluid.METHODS: A two-dimensional(2D) fully convolutional network for retinal segmentation was employed. In order to solve the category imbalance in retinal optical coherence tomography(OCT) images, the network parameters and loss function based on the 2D fully convolutional network were modified. For this network, the correlations of corresponding positions among adjacent images in space are ignored. Thus, we proposed a three-dimensional(3D) fully convolutional network for segmentation in the retinal OCT images.RESULTS: The algorithm was evaluated according to segmentation accuracy, Kappa coefficient, and F1 score. For the 3D fully convolutional network proposed in this paper, the overall segmentation accuracy rate is 99.56%, Kappa coefficient is 98.47%, and F1 score of retinal fluid is 95.50%. CONCLUSION: The OCT image segmentation algorithm based on deep learning is primarily founded on the 2D convolutional network. The 3D network architecture proposed in this paper reduces the influence of category imbalance, realizes end-to-end segmentation of volume images, and achieves optimal segmentation results. The segmentation maps are practically the same as the manual annotations of doctors, and can provide doctors with more accurate diagnostic data.展开更多
BACKGROUND The accurate classification of focal liver lesions(FLLs)is essential to properly guide treatment options and predict prognosis.Dynamic contrast-enhanced computed tomography(DCE-CT)is still the cornerstone i...BACKGROUND The accurate classification of focal liver lesions(FLLs)is essential to properly guide treatment options and predict prognosis.Dynamic contrast-enhanced computed tomography(DCE-CT)is still the cornerstone in the exact classification of FLLs due to its noninvasive nature,high scanning speed,and high-density resolution.Since their recent development,convolutional neural network-based deep learning techniques has been recognized to have high potential for image recognition tasks.AIM To develop and evaluate an automated multiphase convolutional dense network(MP-CDN)to classify FLLs on multiphase CT.METHODS A total of 517 FLLs scanned on a 320-detector CT scanner using a four-phase DCECT imaging protocol(including precontrast phase,arterial phase,portal venous phase,and delayed phase)from 2012 to 2017 were retrospectively enrolled.FLLs were classified into four categories:Category A,hepatocellular carcinoma(HCC);category B,liver metastases;category C,benign non-inflammatory FLLs including hemangiomas,focal nodular hyperplasias and adenomas;and category D,hepatic abscesses.Each category was split into a training set and test set in an approximate 8:2 ratio.An MP-CDN classifier with a sequential input of the fourphase CT images was developed to automatically classify FLLs.The classification performance of the model was evaluated on the test set;the accuracy and specificity were calculated from the confusion matrix,and the area under the receiver operating characteristic curve(AUC)was calculated from the SoftMax probability outputted from the last layer of the MP-CDN.RESULTS A total of 410 FLLs were used for training and 107 FLLs were used for testing.The mean classification accuracy of the test set was 81.3%(87/107).The accuracy/specificity of distinguishing each category from the others were 0.916/0.964,0.925/0.905,0.860/0.918,and 0.925/0.963 for HCC,metastases,benign non-inflammatory FLLs,and abscesses on the test set,respectively.The AUC(95%confidence interval)for differentiating each category from the others was 0.92(0.837-0.992),0.99(0.967-1.00),0.88(0.795-0.955)and 0.96(0.914-0.996)for HCC,metastases,benign non-inflammatory FLLs,and abscesses on the test set,respectively.CONCLUSION MP-CDN accurately classified FLLs detected on four-phase CT as HCC,metastases,benign non-inflammatory FLLs and hepatic abscesses and may assist radiologists in identifying the different types of FLLs.展开更多
To minimize radiation risk,dose reduction is important in the diagnostic and therapeutic applications of computed tomography(CT).However,image noise degrades image quality owing to the reduced X-ray dose and a possibl...To minimize radiation risk,dose reduction is important in the diagnostic and therapeutic applications of computed tomography(CT).However,image noise degrades image quality owing to the reduced X-ray dose and a possible unacceptably reduced diagnostic performance.Deep learning approaches with convolutional neural networks(CNNs)have been proposed for natural image denoising;however,these approaches might introduce image blurring or loss of original gradients.The aim of this study was to compare the dose-dependent properties of a CNN-based denoising method for low-dose CT with those of other noise-reduction methods on unique CT noise-simulation images.To simulate a low-dose CT image,a Poisson noise distribution was introduced to normal-dose images while convoluting the CT unit-specific modulation transfer function.An abdominal CT of 100 images obtained from a public database was adopted,and simulated dose-reduction images were created from the original dose at equal 10-step dose-reduction intervals with a final dose of 1/100.These images were denoised using the denoising network structure of CNN(DnCNN)as the general CNN model and for transfer learning.To evaluate the image quality,image similarities determined by the structural similarity index(SSIM)and peak signal-to-noise ratio(PSNR)were calculated for the denoised images.Significantly better denoising,in terms of SSIM and PSNR,was achieved by the DnCNN than by other image denoising methods,especially at the ultra-low-dose levels used to generate the 10%and 5%dose-equivalent images.Moreover,the developed CNN model can eliminate noise and maintain image sharpness at these dose levels and improve SSIM by approximately 10%from that of the original method.In contrast,under small dose-reduction conditions,this model also led to excessive smoothing of the images.In quantitative evaluations,the CNN denoising method improved the low-dose CT and prevented over-smoothing by tailoring the CNN model.展开更多
The three dimensional(3D) geometry of soil macropores largely controls preferential flow, which is a significant infiltrating mechanism for rainfall in forest soils and affects slope stability. However, detailed studi...The three dimensional(3D) geometry of soil macropores largely controls preferential flow, which is a significant infiltrating mechanism for rainfall in forest soils and affects slope stability. However, detailed studies on the 3D geometry of macropore networks in forest soils are rare. The intense rainfall-triggered potentially unstable slopes were threatening the villages at the downstream of Touzhai valley(Yunnan, China). We visualized and quantified the 3D macropore networks in undisturbed soil columns(Histosols) taken from a forest hillslope in Touzhai valley, and compared them with those in agricultural soils(corn and soybean in USA; barley, fodder beet and red fescue in Denmark) and grassland soils in USA. We took two large undisturbed soil columns(250 mm×250 mm×500 mm), and scanned the soil columns at in-situ soil water content conditions using X-ray computed tomography at a voxel resolution of 0.945 × 0.945 × 1.500 mm^3. After reconstruction and visualization, we quantified the characteristics of macropore networks. In the studiedforest soils, the main types of macropores were root channels, inter-aggregate voids, macropores without knowing origin, root-soil interface and stone-soil interface. While macropore networks tend to be more complex, larger, deeper and longer. The forest soils have high macroporosity, total macropore wall area density, node density, and large macropore volume, hydraulic radius, mean macropore length, angle, and low tortuosity. The findings suggest that macropore networks in the forest soils have high interconnectivity, vertical continuity, linearity and less vertically oriented.展开更多
BACKGROUND Efforts should be made to develop a deep-learning diagnosis system to distinguish pancreatic cancer from benign tissue due to the high morbidity of pancreatic cancer.AIM To identify pancreatic cancer in com...BACKGROUND Efforts should be made to develop a deep-learning diagnosis system to distinguish pancreatic cancer from benign tissue due to the high morbidity of pancreatic cancer.AIM To identify pancreatic cancer in computed tomography(CT)images automatically by constructing a convolutional neural network(CNN)classifier.METHODS A CNN model was constructed using a dataset of 3494 CT images obtained from 222 patients with pathologically confirmed pancreatic cancer and 3751 CT images from 190 patients with normal pancreas from June 2017 to June 2018.We established three datasets from these images according to the image phases,evaluated the approach in terms of binary classification(i.e.,cancer or not)and ternary classification(i.e.,no cancer,cancer at tail/body,cancer at head/neck of the pancreas)using 10-fold cross validation,and measured the effectiveness of the RESULTS The overall diagnostic accuracy of the trained binary classifier was 95.47%,95.76%,95.15%on the plain scan,arterial phase,and venous phase,respectively.The sensitivity was 91.58%,94.08%,92.28%on three phases,with no significant differences(χ2=0.914,P=0.633).Considering that the plain phase had same sensitivity,easier access,and lower radiation compared with arterial phase and venous phase,it is more sufficient for the binary classifier.Its accuracy on plain scans was 95.47%,sensitivity was 91.58%,and specificity was 98.27%.The CNN and board-certified gastroenterologists achieved higher accuracies than trainees on plain scan diagnosis(χ2=21.534,P<0.001;χ2=9.524,P<0.05;respectively).However,the difference between CNN and gastroenterologists was not significant(χ2=0.759,P=0.384).In the trained ternary classifier,the overall diagnostic accuracy of the ternary classifier CNN was 82.06%,79.06%,and 78.80%on plain phase,arterial phase,and venous phase,respectively.The sensitivity scores for detecting cancers in the tail were 52.51%,41.10%and,36.03%,while sensitivity for cancers in the head was 46.21%,85.24%and 72.87%on three phases,respectively.Difference in sensitivity for cancers in the head among the three phases was significant(χ2=16.651,P<0.001),with arterial phase having the highest sensitivity.CONCLUSION We proposed a deep learning-based pancreatic cancer classifier trained on medium-sized datasets of CT images.It was suitable for screening purposes in pancreatic cancer detection.展开更多
An image-reconstruction approach for optical tomography is presented,in which a two-layered BP neural network is used to distinguish the tumor location.The inverse problem is solved as optimization problem by Femlab s...An image-reconstruction approach for optical tomography is presented,in which a two-layered BP neural network is used to distinguish the tumor location.The inverse problem is solved as optimization problem by Femlab software and Levenberg–Marquardt algorithm.The concept of the average optical coefficient is proposed in this paper,which is helpful to understand the distribution of the scattering photon from tumor.The reconstructive¯µs by the trained network is reasonable for showing the changes of photon number transporting inside tumor tissue.It realized the fast reconstruction of tissue optical properties and provided optical OT with a new method.展开更多
Electrical capacitance tomography technique reconstructs dielectric constant distribution in anobject by measuring the capacitances between the eletrode pairs which are mounted around this object. Because of the limit...Electrical capacitance tomography technique reconstructs dielectric constant distribution in anobject by measuring the capacitances between the eletrode pairs which are mounted around this object. Because of the limitation of measurement condition, the measured data are imcomplet. This paper describes amultiresolution reconstructive algorithm which is based on network theory for electrical capacitance tomography technique. The dielectric constant distribution of flow of two components in a pipeline is reconstructed.The algorithm is as rollows: Firstly, construct a rough, first level system model, and assume the dielectricconstant distdbution of the region to be reconstructed. After iteration, the dielectic constant of each unit canbe reconstructed. Secondly, construct a finer, second level the system model and determine the initial dielectric constant of each unit in the region to be reconstructed according to related information between two levels. After iteration, the image of the pipeline’s cross section can be reconstructed.The results of simulated experiments about different kinds or medium distributions show that this algorithm is effective and can converge.展开更多
Effective thermal conductivity of soils can be enhanced to achieve higher efficiencies in the operation of shallow geothermal systems.Soil cementation is a ground improvement technique that can increase the interparti...Effective thermal conductivity of soils can be enhanced to achieve higher efficiencies in the operation of shallow geothermal systems.Soil cementation is a ground improvement technique that can increase the interparticle contact area,leading to a high effective thermal conductivity.However,cementation may occur at different locations in the soil matrix,i.e.interparticle contacts,evenly or unevenly around particles,in the pore space or a combination of these.The topology of cementation at the particle scale and its influence on soil response have not been studied in detail to date.Additionally,soils are made of particles with different shapes,but the impact of particle shape on the cementation and the resulting change of effective thermal conductivity require further research.In this work,three kinds of sands with different particle shapes were selected and cementation was formed either evenly around the particles,or along the direction parallel or perpendicular to that of heat transfer.The effective thermal conductivity of each sample was computed using a thermal conductance network model.Results show that dry sand with more irregular particle shape and cemented along the heat transfer direction will lead to a more efficient thermal enhancement of the soil,i.e.a comparatively higher soil effective thermal conductivity.展开更多
Artificial Intelligence(AI)becomes one hotspot in the field of the medical images analysis and provides rather promising solution.Although some research has been explored in smart diagnosis for the common diseases of ...Artificial Intelligence(AI)becomes one hotspot in the field of the medical images analysis and provides rather promising solution.Although some research has been explored in smart diagnosis for the common diseases of urinary system,some problems remain unsolved completely A nine-layer Convolutional Neural Network(CNN)is proposed in this paper to classify the renal Computed Tomography(CT)images.Four group of comparative experiments prove the structure of this CNN is optimal and can achieve good performance with average accuracy about 92.07±1.67%.Although our renal CT data is not very large,we do augment the training data by affine,translating,rotating and scaling geometric transformation and gamma,noise transformation in color space.Experimental results validate the Data Augmentation(DA)on training data can improve the performance of our proposed CNN compared to without DA with the average accuracy about 0.85%.This proposed algorithm gives a promising solution to help clinical doctors automatically recognize the abnormal images faster than manual judgment and more accurately than previous methods.展开更多
Medical Imaging Segmentation is an essential technique for modern medical applications.It is the foundation of many aspects of clinical diagnosis,oncology,and computer-integrated surgical intervention.Although signifi...Medical Imaging Segmentation is an essential technique for modern medical applications.It is the foundation of many aspects of clinical diagnosis,oncology,and computer-integrated surgical intervention.Although significant successes have been achieved in the segmentation of medical images,DL(deep learning)approaches.Manual delineation of OARs(organs at risk)is vastly dominant but it is prone to errors given the complex irregularities in shape,low texture diversity between tissues and adjacent blood area,patientwide location of organisms,and weak soft tissue contrast across adjacent organs in CT images.Till now several models have been implemented onmulti organs segmentation but not caters to the problemof imbalanced classes some organs have relatively small pixels as compared to others.To segment OARs in thoracic CT images,we proposed the model based on the encoder-decoder approach using transfer learning with the efficientnetB7 DL model.We have built a fully connected CNN(Convolutional Neural network)having 5 layers of encoding and 5 layers of decoding with efficientnetB7 specifically to tackle imbalance class pixels in an accurate way for the segmentation of OARs.Proposed methodology achieves 0.93405 IOU score,0.95138 F1 score and class-wise dice score for esophagus 0.92466,trachea 0.94257,heart 0.95038,aorta 0.9351 and background 0.99891.The results showed that our proposed framework can be segmented organs accurately.展开更多
Convolutional neural network (CNN), a class of deep neural networks (most commonly used in visual image analysis), has become one of the most influential innovations in the field of computer vision. In our research, w...Convolutional neural network (CNN), a class of deep neural networks (most commonly used in visual image analysis), has become one of the most influential innovations in the field of computer vision. In our research, we built a system which allows the computer to extract the feature and recognize the image of human lungs and to automatically conclude the health level of the lungs based on database. Here, we built a CNN model to train the datasets. After the training, the system could do certain preliminary analysis already. In addition, we used the fixed coordinate to reduce the noise and combined the Canny algorithm and the Mask algorithm to further improve the accuracy of the system. The final accuracy turned out to be 87.0%, which is convincing. Our system can contribute a lot to the efficiency and accuracy of doctors’ analysis of the patients’ health level. In the future, we will do more improvement to reduce noise and increase accuracy.展开更多
Electrical impedance tomography (EIT) is a new computer tomography technology, which reconstructs an impedance (resistivity, conductivity) distribution, or change of impedance, by making voltage and current measuremen...Electrical impedance tomography (EIT) is a new computer tomography technology, which reconstructs an impedance (resistivity, conductivity) distribution, or change of impedance, by making voltage and current measurements on the object's periphery.Image reconstruction in EIT is an ill-posed, non-linear inverse problem. A method for finding the place of impedance change in EIT is proposed in this paper, in which a multilevel BP neural network (MBPNN) is used to express the non-linear relation between theimpedance change inside the object and the voltage change measured on the surface of the object. Thus, the location of the impedance change can be decided by the measured voltage variation on the surface. The impedance change is then reconstructed using a linear approximate method. MBPNN can decide the impedance change location exactly without long training time. It alleviates some noise effects and can be expanded, ensuring high precision and space resolution of the reconstructed image that are not possible by using the back projection method.展开更多
Computed tomography(CT)scan diagnostics procedures adopt the use of image infbnnation retrieval system with the help of radiographer's expertise.However,this technique is prone to errors,Significant height of accu...Computed tomography(CT)scan diagnostics procedures adopt the use of image infbnnation retrieval system with the help of radiographer's expertise.However,this technique is prone to errors,Significant height of accuracy is required in healthcare decision support,as 20%of CT scans are associated with error.The application of artificial intelligence(Al)can improve performance level,mitigate human error,and enhance clinical decision support in the context of time and accuracy.The study introduced machine learning algorithm to analyze stream of anonymous CT scans of kidney.The research adopted deep learning approach for segmentation and classification of kidney stone(renal calculi)images in Python(with Keras and TensorFlow)environment.A control volume of data along with 336 kidney stone images were used to train the deep learning network with 10 testing images.The training images were divided into two sets(folders)as follows;one was labeled as STONE(containing 167 images)and the other as NO-STONE(containing 169 images);10 iterations were performed for model training.The network layers were structured as input layer in the following with 2-D convolutional neural network machine learning(CNN-ML),ReLU activation,Maxpooling,and fully connected(dense)layer including the sigmoid activation layer.The training adopted a batch size of 8 with 10%validation.The output result,upon testing the model,has an accuracy of 90%,sensitivity value of 80%and effectiveness of 89%.The segmentation and classification algorithm model could be embedded in future CT diagnostic procedure to enhance medical decision support and accuracy.展开更多
The number of dispersion curves increases significantly when the scale of a short-period dense array increases.Owing to a substantial increase in data volume,it is important to quickly evaluate dispersion curve qualit...The number of dispersion curves increases significantly when the scale of a short-period dense array increases.Owing to a substantial increase in data volume,it is important to quickly evaluate dispersion curve quality as well as select the available dispersion curve.Accordingly,this study quantitatively evaluated dispersion curve quality by training a convolutional neural network model for ambient noise tomography using a short-period dense array.The model can select high-quality dispersion curves that exhibit a≤10%difference between the results of manual screening and the proposed model.In addition,this study established a dispersion curve loss function by analyzing the quality of the dispersion curve and the corresponding influencing factors,thereby estimating the number of available dispersion curves for the existing observation systems.Furthermore,a Monte Carlo simulation experiment is used to illustrates the station-pair interval distance probability density function,which is independent of station number in the observational system with randomly deployed stations.The results suggested that the straight-line length should exceed 15 km to ensure that loss rate of dispersion curves remains<0.5,while maintaining the threshold ambient noise tomography accuracy within the study area.展开更多
基金Supported by National Science Foundation of China(No.81800878)Interdisciplinary Program of Shanghai Jiao Tong University(No.YG2017QN24)+1 种基金Key Technological Research Projects of Songjiang District(No.18sjkjgg24)Bethune Langmu Ophthalmological Research Fund for Young and Middle-aged People(No.BJ-LM2018002J)
文摘AIM: To explore a segmentation algorithm based on deep learning to achieve accurate diagnosis and treatment of patients with retinal fluid.METHODS: A two-dimensional(2D) fully convolutional network for retinal segmentation was employed. In order to solve the category imbalance in retinal optical coherence tomography(OCT) images, the network parameters and loss function based on the 2D fully convolutional network were modified. For this network, the correlations of corresponding positions among adjacent images in space are ignored. Thus, we proposed a three-dimensional(3D) fully convolutional network for segmentation in the retinal OCT images.RESULTS: The algorithm was evaluated according to segmentation accuracy, Kappa coefficient, and F1 score. For the 3D fully convolutional network proposed in this paper, the overall segmentation accuracy rate is 99.56%, Kappa coefficient is 98.47%, and F1 score of retinal fluid is 95.50%. CONCLUSION: The OCT image segmentation algorithm based on deep learning is primarily founded on the 2D convolutional network. The 3D network architecture proposed in this paper reduces the influence of category imbalance, realizes end-to-end segmentation of volume images, and achieves optimal segmentation results. The segmentation maps are practically the same as the manual annotations of doctors, and can provide doctors with more accurate diagnostic data.
基金Supported by National Natural Science Foundation of China,No.91959118Science and Technology Program of Guangzhou,China,No.201704020016+1 种基金SKY Radiology Department International Medical Research Foundation of China,No.Z-2014-07-1912-15Clinical Research Foundation of the 3rd Affiliated Hospital of Sun Yat-Sen University,No.YHJH201901.
文摘BACKGROUND The accurate classification of focal liver lesions(FLLs)is essential to properly guide treatment options and predict prognosis.Dynamic contrast-enhanced computed tomography(DCE-CT)is still the cornerstone in the exact classification of FLLs due to its noninvasive nature,high scanning speed,and high-density resolution.Since their recent development,convolutional neural network-based deep learning techniques has been recognized to have high potential for image recognition tasks.AIM To develop and evaluate an automated multiphase convolutional dense network(MP-CDN)to classify FLLs on multiphase CT.METHODS A total of 517 FLLs scanned on a 320-detector CT scanner using a four-phase DCECT imaging protocol(including precontrast phase,arterial phase,portal venous phase,and delayed phase)from 2012 to 2017 were retrospectively enrolled.FLLs were classified into four categories:Category A,hepatocellular carcinoma(HCC);category B,liver metastases;category C,benign non-inflammatory FLLs including hemangiomas,focal nodular hyperplasias and adenomas;and category D,hepatic abscesses.Each category was split into a training set and test set in an approximate 8:2 ratio.An MP-CDN classifier with a sequential input of the fourphase CT images was developed to automatically classify FLLs.The classification performance of the model was evaluated on the test set;the accuracy and specificity were calculated from the confusion matrix,and the area under the receiver operating characteristic curve(AUC)was calculated from the SoftMax probability outputted from the last layer of the MP-CDN.RESULTS A total of 410 FLLs were used for training and 107 FLLs were used for testing.The mean classification accuracy of the test set was 81.3%(87/107).The accuracy/specificity of distinguishing each category from the others were 0.916/0.964,0.925/0.905,0.860/0.918,and 0.925/0.963 for HCC,metastases,benign non-inflammatory FLLs,and abscesses on the test set,respectively.The AUC(95%confidence interval)for differentiating each category from the others was 0.92(0.837-0.992),0.99(0.967-1.00),0.88(0.795-0.955)and 0.96(0.914-0.996)for HCC,metastases,benign non-inflammatory FLLs,and abscesses on the test set,respectively.CONCLUSION MP-CDN accurately classified FLLs detected on four-phase CT as HCC,metastases,benign non-inflammatory FLLs and hepatic abscesses and may assist radiologists in identifying the different types of FLLs.
基金This work was supported by JSPS KAKENHI,No.18 K15563.
文摘To minimize radiation risk,dose reduction is important in the diagnostic and therapeutic applications of computed tomography(CT).However,image noise degrades image quality owing to the reduced X-ray dose and a possible unacceptably reduced diagnostic performance.Deep learning approaches with convolutional neural networks(CNNs)have been proposed for natural image denoising;however,these approaches might introduce image blurring or loss of original gradients.The aim of this study was to compare the dose-dependent properties of a CNN-based denoising method for low-dose CT with those of other noise-reduction methods on unique CT noise-simulation images.To simulate a low-dose CT image,a Poisson noise distribution was introduced to normal-dose images while convoluting the CT unit-specific modulation transfer function.An abdominal CT of 100 images obtained from a public database was adopted,and simulated dose-reduction images were created from the original dose at equal 10-step dose-reduction intervals with a final dose of 1/100.These images were denoised using the denoising network structure of CNN(DnCNN)as the general CNN model and for transfer learning.To evaluate the image quality,image similarities determined by the structural similarity index(SSIM)and peak signal-to-noise ratio(PSNR)were calculated for the denoised images.Significantly better denoising,in terms of SSIM and PSNR,was achieved by the DnCNN than by other image denoising methods,especially at the ultra-low-dose levels used to generate the 10%and 5%dose-equivalent images.Moreover,the developed CNN model can eliminate noise and maintain image sharpness at these dose levels and improve SSIM by approximately 10%from that of the original method.In contrast,under small dose-reduction conditions,this model also led to excessive smoothing of the images.In quantitative evaluations,the CNN denoising method improved the low-dose CT and prevented over-smoothing by tailoring the CNN model.
基金financially supported by the National Science Foundation of China-Yunnan Joint Fund(U1502232)the Natural Science Foundation of Yunnan Province(2014FD007)the Natural Science Foundation of Kunming University of Science and Technology(KKSY201406009)
文摘The three dimensional(3D) geometry of soil macropores largely controls preferential flow, which is a significant infiltrating mechanism for rainfall in forest soils and affects slope stability. However, detailed studies on the 3D geometry of macropore networks in forest soils are rare. The intense rainfall-triggered potentially unstable slopes were threatening the villages at the downstream of Touzhai valley(Yunnan, China). We visualized and quantified the 3D macropore networks in undisturbed soil columns(Histosols) taken from a forest hillslope in Touzhai valley, and compared them with those in agricultural soils(corn and soybean in USA; barley, fodder beet and red fescue in Denmark) and grassland soils in USA. We took two large undisturbed soil columns(250 mm×250 mm×500 mm), and scanned the soil columns at in-situ soil water content conditions using X-ray computed tomography at a voxel resolution of 0.945 × 0.945 × 1.500 mm^3. After reconstruction and visualization, we quantified the characteristics of macropore networks. In the studiedforest soils, the main types of macropores were root channels, inter-aggregate voids, macropores without knowing origin, root-soil interface and stone-soil interface. While macropore networks tend to be more complex, larger, deeper and longer. The forest soils have high macroporosity, total macropore wall area density, node density, and large macropore volume, hydraulic radius, mean macropore length, angle, and low tortuosity. The findings suggest that macropore networks in the forest soils have high interconnectivity, vertical continuity, linearity and less vertically oriented.
基金the National Natural Science Foundation of China,No.81900509Fundamental Research Funds for the Central Universities,No.2018XZZX002-10High-Level Talents Special Support Plan of Zhejiang Province(known as the Ten Thousand Talents Plan),No.ZJWR0108008.
文摘BACKGROUND Efforts should be made to develop a deep-learning diagnosis system to distinguish pancreatic cancer from benign tissue due to the high morbidity of pancreatic cancer.AIM To identify pancreatic cancer in computed tomography(CT)images automatically by constructing a convolutional neural network(CNN)classifier.METHODS A CNN model was constructed using a dataset of 3494 CT images obtained from 222 patients with pathologically confirmed pancreatic cancer and 3751 CT images from 190 patients with normal pancreas from June 2017 to June 2018.We established three datasets from these images according to the image phases,evaluated the approach in terms of binary classification(i.e.,cancer or not)and ternary classification(i.e.,no cancer,cancer at tail/body,cancer at head/neck of the pancreas)using 10-fold cross validation,and measured the effectiveness of the RESULTS The overall diagnostic accuracy of the trained binary classifier was 95.47%,95.76%,95.15%on the plain scan,arterial phase,and venous phase,respectively.The sensitivity was 91.58%,94.08%,92.28%on three phases,with no significant differences(χ2=0.914,P=0.633).Considering that the plain phase had same sensitivity,easier access,and lower radiation compared with arterial phase and venous phase,it is more sufficient for the binary classifier.Its accuracy on plain scans was 95.47%,sensitivity was 91.58%,and specificity was 98.27%.The CNN and board-certified gastroenterologists achieved higher accuracies than trainees on plain scan diagnosis(χ2=21.534,P<0.001;χ2=9.524,P<0.05;respectively).However,the difference between CNN and gastroenterologists was not significant(χ2=0.759,P=0.384).In the trained ternary classifier,the overall diagnostic accuracy of the ternary classifier CNN was 82.06%,79.06%,and 78.80%on plain phase,arterial phase,and venous phase,respectively.The sensitivity scores for detecting cancers in the tail were 52.51%,41.10%and,36.03%,while sensitivity for cancers in the head was 46.21%,85.24%and 72.87%on three phases,respectively.Difference in sensitivity for cancers in the head among the three phases was significant(χ2=16.651,P<0.001),with arterial phase having the highest sensitivity.CONCLUSION We proposed a deep learning-based pancreatic cancer classifier trained on medium-sized datasets of CT images.It was suitable for screening purposes in pancreatic cancer detection.
基金National Nature Sci-ence Foundation of China(Grant No.30671997).
文摘An image-reconstruction approach for optical tomography is presented,in which a two-layered BP neural network is used to distinguish the tumor location.The inverse problem is solved as optimization problem by Femlab software and Levenberg–Marquardt algorithm.The concept of the average optical coefficient is proposed in this paper,which is helpful to understand the distribution of the scattering photon from tumor.The reconstructive¯µs by the trained network is reasonable for showing the changes of photon number transporting inside tumor tissue.It realized the fast reconstruction of tissue optical properties and provided optical OT with a new method.
文摘Electrical capacitance tomography technique reconstructs dielectric constant distribution in anobject by measuring the capacitances between the eletrode pairs which are mounted around this object. Because of the limitation of measurement condition, the measured data are imcomplet. This paper describes amultiresolution reconstructive algorithm which is based on network theory for electrical capacitance tomography technique. The dielectric constant distribution of flow of two components in a pipeline is reconstructed.The algorithm is as rollows: Firstly, construct a rough, first level system model, and assume the dielectricconstant distdbution of the region to be reconstructed. After iteration, the dielectic constant of each unit canbe reconstructed. Secondly, construct a finer, second level the system model and determine the initial dielectric constant of each unit in the region to be reconstructed according to related information between two levels. After iteration, the image of the pipeline’s cross section can be reconstructed.The results of simulated experiments about different kinds or medium distributions show that this algorithm is effective and can converge.
文摘Effective thermal conductivity of soils can be enhanced to achieve higher efficiencies in the operation of shallow geothermal systems.Soil cementation is a ground improvement technique that can increase the interparticle contact area,leading to a high effective thermal conductivity.However,cementation may occur at different locations in the soil matrix,i.e.interparticle contacts,evenly or unevenly around particles,in the pore space or a combination of these.The topology of cementation at the particle scale and its influence on soil response have not been studied in detail to date.Additionally,soils are made of particles with different shapes,but the impact of particle shape on the cementation and the resulting change of effective thermal conductivity require further research.In this work,three kinds of sands with different particle shapes were selected and cementation was formed either evenly around the particles,or along the direction parallel or perpendicular to that of heat transfer.The effective thermal conductivity of each sample was computed using a thermal conductance network model.Results show that dry sand with more irregular particle shape and cemented along the heat transfer direction will lead to a more efficient thermal enhancement of the soil,i.e.a comparatively higher soil effective thermal conductivity.
基金This study was supported by National Educational Science Plan Foundation“in 13th Five-Year”(DIA170375),ChinaGuangxi Key Laboratory of Trusted Software(kx201901)British Heart Foundation Accelerator Award,UK.
文摘Artificial Intelligence(AI)becomes one hotspot in the field of the medical images analysis and provides rather promising solution.Although some research has been explored in smart diagnosis for the common diseases of urinary system,some problems remain unsolved completely A nine-layer Convolutional Neural Network(CNN)is proposed in this paper to classify the renal Computed Tomography(CT)images.Four group of comparative experiments prove the structure of this CNN is optimal and can achieve good performance with average accuracy about 92.07±1.67%.Although our renal CT data is not very large,we do augment the training data by affine,translating,rotating and scaling geometric transformation and gamma,noise transformation in color space.Experimental results validate the Data Augmentation(DA)on training data can improve the performance of our proposed CNN compared to without DA with the average accuracy about 0.85%.This proposed algorithm gives a promising solution to help clinical doctors automatically recognize the abnormal images faster than manual judgment and more accurately than previous methods.
基金Taif University Researchers Supporting Project number(TURSP-2020/98),Taif University,Taif,Saudi Arabia.
文摘Medical Imaging Segmentation is an essential technique for modern medical applications.It is the foundation of many aspects of clinical diagnosis,oncology,and computer-integrated surgical intervention.Although significant successes have been achieved in the segmentation of medical images,DL(deep learning)approaches.Manual delineation of OARs(organs at risk)is vastly dominant but it is prone to errors given the complex irregularities in shape,low texture diversity between tissues and adjacent blood area,patientwide location of organisms,and weak soft tissue contrast across adjacent organs in CT images.Till now several models have been implemented onmulti organs segmentation but not caters to the problemof imbalanced classes some organs have relatively small pixels as compared to others.To segment OARs in thoracic CT images,we proposed the model based on the encoder-decoder approach using transfer learning with the efficientnetB7 DL model.We have built a fully connected CNN(Convolutional Neural network)having 5 layers of encoding and 5 layers of decoding with efficientnetB7 specifically to tackle imbalance class pixels in an accurate way for the segmentation of OARs.Proposed methodology achieves 0.93405 IOU score,0.95138 F1 score and class-wise dice score for esophagus 0.92466,trachea 0.94257,heart 0.95038,aorta 0.9351 and background 0.99891.The results showed that our proposed framework can be segmented organs accurately.
文摘Convolutional neural network (CNN), a class of deep neural networks (most commonly used in visual image analysis), has become one of the most influential innovations in the field of computer vision. In our research, we built a system which allows the computer to extract the feature and recognize the image of human lungs and to automatically conclude the health level of the lungs based on database. Here, we built a CNN model to train the datasets. After the training, the system could do certain preliminary analysis already. In addition, we used the fixed coordinate to reduce the noise and combined the Canny algorithm and the Mask algorithm to further improve the accuracy of the system. The final accuracy turned out to be 87.0%, which is convincing. Our system can contribute a lot to the efficiency and accuracy of doctors’ analysis of the patients’ health level. In the future, we will do more improvement to reduce noise and increase accuracy.
基金National Natural Science Foundation of China (Grant No. 60075009)
文摘Electrical impedance tomography (EIT) is a new computer tomography technology, which reconstructs an impedance (resistivity, conductivity) distribution, or change of impedance, by making voltage and current measurements on the object's periphery.Image reconstruction in EIT is an ill-posed, non-linear inverse problem. A method for finding the place of impedance change in EIT is proposed in this paper, in which a multilevel BP neural network (MBPNN) is used to express the non-linear relation between theimpedance change inside the object and the voltage change measured on the surface of the object. Thus, the location of the impedance change can be decided by the measured voltage variation on the surface. The impedance change is then reconstructed using a linear approximate method. MBPNN can decide the impedance change location exactly without long training time. It alleviates some noise effects and can be expanded, ensuring high precision and space resolution of the reconstructed image that are not possible by using the back projection method.
文摘Computed tomography(CT)scan diagnostics procedures adopt the use of image infbnnation retrieval system with the help of radiographer's expertise.However,this technique is prone to errors,Significant height of accuracy is required in healthcare decision support,as 20%of CT scans are associated with error.The application of artificial intelligence(Al)can improve performance level,mitigate human error,and enhance clinical decision support in the context of time and accuracy.The study introduced machine learning algorithm to analyze stream of anonymous CT scans of kidney.The research adopted deep learning approach for segmentation and classification of kidney stone(renal calculi)images in Python(with Keras and TensorFlow)environment.A control volume of data along with 336 kidney stone images were used to train the deep learning network with 10 testing images.The training images were divided into two sets(folders)as follows;one was labeled as STONE(containing 167 images)and the other as NO-STONE(containing 169 images);10 iterations were performed for model training.The network layers were structured as input layer in the following with 2-D convolutional neural network machine learning(CNN-ML),ReLU activation,Maxpooling,and fully connected(dense)layer including the sigmoid activation layer.The training adopted a batch size of 8 with 10%validation.The output result,upon testing the model,has an accuracy of 90%,sensitivity value of 80%and effectiveness of 89%.The segmentation and classification algorithm model could be embedded in future CT diagnostic procedure to enhance medical decision support and accuracy.
基金supported by the Second Tibetan Plateau Scientific Expedition and Research Program(STEP)(No.2019QZKK0701)the Fund from the Key Laboratory of Deep-Earth Dynamics of the Ministry of Natural Resources(No.J1901-38)+1 种基金the National Natural Science Foundation of China(Nos.42174121 and 91962109)the China Geological Survey Project(No.DD20190001).
文摘The number of dispersion curves increases significantly when the scale of a short-period dense array increases.Owing to a substantial increase in data volume,it is important to quickly evaluate dispersion curve quality as well as select the available dispersion curve.Accordingly,this study quantitatively evaluated dispersion curve quality by training a convolutional neural network model for ambient noise tomography using a short-period dense array.The model can select high-quality dispersion curves that exhibit a≤10%difference between the results of manual screening and the proposed model.In addition,this study established a dispersion curve loss function by analyzing the quality of the dispersion curve and the corresponding influencing factors,thereby estimating the number of available dispersion curves for the existing observation systems.Furthermore,a Monte Carlo simulation experiment is used to illustrates the station-pair interval distance probability density function,which is independent of station number in the observational system with randomly deployed stations.The results suggested that the straight-line length should exceed 15 km to ensure that loss rate of dispersion curves remains<0.5,while maintaining the threshold ambient noise tomography accuracy within the study area.