The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning.While voxel-based deep learning frameworks have been proposed for this segmentation task,their performance remains limit...The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning.While voxel-based deep learning frameworks have been proposed for this segmentation task,their performance remains limited.In this study,we offer a two-step surface-based deep learning pipeline that achieves significantly better results.Our proposed model takes a surface model of an entire set of principal brain arteries containing aneurysms as input and returns aneurysm surfaces as output.A user first generates a surface model by manually specifying multiple thresholds for time-of-flight magnetic resonance angiography images.The system then samples small surface fragments from the entire set of brain arteries and classifies the surface fragments according to whether aneurysms are present using a point-based deep learning network(PointNet++).Finally,the system applies surface segmentation(SO-Net)to surface fragments containing aneurysms.We conduct a direct comparison of the segmentation performance of our proposed surface-based framework and an existing voxel-based method by counting voxels:our framework achieves a much higher Dice similarity(72%)than the prior approach(46%).展开更多
Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measuremen...Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measurement based on deep learning.A multi-stream convolutional neural network(CNN)is proposed to learn the mapping relationship between camera array light filed wrapped phases and fringe orders of the expected central view,and is used to predict the fringe order to achieve the phase unwrapping.Experiments are performed on the light field fringe projection data generated by the simulated camera array fringe projection measurement system in Blender and by the experimental 3×3 camera array light field fringe projection system.The performance of the proposed network with light field wrapped phases using multiple directions as network input data is studied,and the advantages of phase unwrapping based on deep learning in light filed fringe projection are demonstrated.展开更多
Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligenc...Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligence(AI)showed outstanding performance in effectively diagnosing this virus in real-time.Computed tomography is a complementary diagnostic tool to clarify the damage of COVID-19 in the lungs even before symptoms appear in patients.This paper conducts a systematic literature review of deep learning methods for classifying the segmentation of COVID-19 infection in the lungs.We used the methodology of systematic reviews and meta-analyses(PRISMA)flow method.This research aims to systematically analyze the supervised deep learning methods,open resource datasets,data augmentation methods,and loss functions used for various segment shapes of COVID-19 infection from computerized tomography(CT)chest images.We have selected 56 primary studies relevant to the topic of the paper.We have compared different aspects of the algorithms used to segment infected areas in the CT images.Limitations to deep learning in the segmentation of infected areas still need to be developed to predict smaller regions of infection at the beginning of their appearance.展开更多
While analytical solutions of critical(phase)transitions in dynamical systems are abundant for simple nonlinear systems,such analysis remains intractable for real-life dynamical systems.A key example is thermoacoustic...While analytical solutions of critical(phase)transitions in dynamical systems are abundant for simple nonlinear systems,such analysis remains intractable for real-life dynamical systems.A key example is thermoacoustic insta-bility in combustion,where prediction or early detection of the onset of instability is a hard technical challenge,which needs to be addressed to build safer and more energy-efficient gas turbine engines powering aerospace and energy industries.The instabilities arising in combustion chambers of engines are mathematically too complex to model.To address this issue in a data-driven manner instead,we propose a novel deep learning architecture called 3D convolutional selective autoencoder(3D-CSAE)to detect the evolution of self-excited oscillations using spatiotemporal data,i.e.,hi-speed videos taken from a swirl-stabilized combustor(laboratory surrogate of gas turbine engine combustor).3D-CSAE consists of filters to learn,in a hierarchical fashion,the complex visual and dynamic features related to combustion instability from the training videos(i.e.,two spatial dimensions for the image frames and the third dimension for time).We train the 3D-CSAE on frames of videos obtained from a limited set of operating conditions.We select the 3D-CSAE hyper-parameters that are effective for characterizing hierarchical and multiscale instability structure evolution by utilizing the dynamic information available in the video.The proposed model clearly shows performance improvement in detecting the precursors and the onset of instability.The machine learning-driven results are verified with physics-based off-line measures.Advanced active control mechanisms can directly leverage the proposed online detection capability of 3D-CSAE to mitigate the adverse effects of combustion instabilities on the engine operating under various stringent requirements and conditions.展开更多
Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding.Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and ...Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding.Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further exploit the inherent relationship between shape semantics and part instances.In this paper,we present a new method for 3D part instance segmentation.Our method exploits semantic segmentation to fuse nonlocal instance features,such as center prediction,and further enhances the fusion scheme in a multi-and cross-level way.We also propose a semantic region center prediction task to train and leverage the prediction results to improve the clustering of instance points.Our method outperforms existing methods with a large-margin improvement in the PartNet benchmark.We also demonstrate that our feature fusion scheme can be applied to other existing methods to improve their performance in indoor scene instance segmentation tasks.展开更多
基金This research was supported by AMED under Grant No.JP18he1602001.
文摘The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning.While voxel-based deep learning frameworks have been proposed for this segmentation task,their performance remains limited.In this study,we offer a two-step surface-based deep learning pipeline that achieves significantly better results.Our proposed model takes a surface model of an entire set of principal brain arteries containing aneurysms as input and returns aneurysm surfaces as output.A user first generates a surface model by manually specifying multiple thresholds for time-of-flight magnetic resonance angiography images.The system then samples small surface fragments from the entire set of brain arteries and classifies the surface fragments according to whether aneurysms are present using a point-based deep learning network(PointNet++).Finally,the system applies surface segmentation(SO-Net)to surface fragments containing aneurysms.We conduct a direct comparison of the segmentation performance of our proposed surface-based framework and an existing voxel-based method by counting voxels:our framework achieves a much higher Dice similarity(72%)than the prior approach(46%).
基金the National Natural Science Foundation of China(No.61905178)the Science&Technology Development Fund of Tianjin Education Commission for Higher Education(No.2019KJ021)the Natural Science Foundation of Tianjin(No.18JCQNJC71100)。
文摘Phase unwrapping is one of the key roles in fringe projection three-dimensional(3D)measurement technology.We propose a new method to achieve phase unwrapping in camera array light filed fringe projection 3D measurement based on deep learning.A multi-stream convolutional neural network(CNN)is proposed to learn the mapping relationship between camera array light filed wrapped phases and fringe orders of the expected central view,and is used to predict the fringe order to achieve the phase unwrapping.Experiments are performed on the light field fringe projection data generated by the simulated camera array fringe projection measurement system in Blender and by the experimental 3×3 camera array light field fringe projection system.The performance of the proposed network with light field wrapped phases using multiple directions as network input data is studied,and the advantages of phase unwrapping based on deep learning in light filed fringe projection are demonstrated.
文摘Coronavirus has infected more than 753 million people,ranging in severity from one person to another,where more than six million infected people died worldwide.Computer-aided diagnostic(CAD)with artificial intelligence(AI)showed outstanding performance in effectively diagnosing this virus in real-time.Computed tomography is a complementary diagnostic tool to clarify the damage of COVID-19 in the lungs even before symptoms appear in patients.This paper conducts a systematic literature review of deep learning methods for classifying the segmentation of COVID-19 infection in the lungs.We used the methodology of systematic reviews and meta-analyses(PRISMA)flow method.This research aims to systematically analyze the supervised deep learning methods,open resource datasets,data augmentation methods,and loss functions used for various segment shapes of COVID-19 infection from computerized tomography(CT)chest images.We have selected 56 primary studies relevant to the topic of the paper.We have compared different aspects of the algorithms used to segment infected areas in the CT images.Limitations to deep learning in the segmentation of infected areas still need to be developed to predict smaller regions of infection at the beginning of their appearance.
文摘While analytical solutions of critical(phase)transitions in dynamical systems are abundant for simple nonlinear systems,such analysis remains intractable for real-life dynamical systems.A key example is thermoacoustic insta-bility in combustion,where prediction or early detection of the onset of instability is a hard technical challenge,which needs to be addressed to build safer and more energy-efficient gas turbine engines powering aerospace and energy industries.The instabilities arising in combustion chambers of engines are mathematically too complex to model.To address this issue in a data-driven manner instead,we propose a novel deep learning architecture called 3D convolutional selective autoencoder(3D-CSAE)to detect the evolution of self-excited oscillations using spatiotemporal data,i.e.,hi-speed videos taken from a swirl-stabilized combustor(laboratory surrogate of gas turbine engine combustor).3D-CSAE consists of filters to learn,in a hierarchical fashion,the complex visual and dynamic features related to combustion instability from the training videos(i.e.,two spatial dimensions for the image frames and the third dimension for time).We train the 3D-CSAE on frames of videos obtained from a limited set of operating conditions.We select the 3D-CSAE hyper-parameters that are effective for characterizing hierarchical and multiscale instability structure evolution by utilizing the dynamic information available in the video.The proposed model clearly shows performance improvement in detecting the precursors and the onset of instability.The machine learning-driven results are verified with physics-based off-line measures.Advanced active control mechanisms can directly leverage the proposed online detection capability of 3D-CSAE to mitigate the adverse effects of combustion instabilities on the engine operating under various stringent requirements and conditions.
文摘Recognizing 3D part instances from a 3D point cloud is crucial for 3D structure and scene understanding.Several learning-based approaches use semantic segmentation and instance center prediction as training tasks and fail to further exploit the inherent relationship between shape semantics and part instances.In this paper,we present a new method for 3D part instance segmentation.Our method exploits semantic segmentation to fuse nonlocal instance features,such as center prediction,and further enhances the fusion scheme in a multi-and cross-level way.We also propose a semantic region center prediction task to train and leverage the prediction results to improve the clustering of instance points.Our method outperforms existing methods with a large-margin improvement in the PartNet benchmark.We also demonstrate that our feature fusion scheme can be applied to other existing methods to improve their performance in indoor scene instance segmentation tasks.
