Jia Fucang | Shen Zhen Institute of Advanced Technology (original) (raw)

Papers by Jia Fucang

Research paper thumbnail of Head and Neck CT Segmentation Based on a Combined U-Net Model

Head and neck (HaN) segmentation in CT image is difficult due to low contrast and large slice thi... more Head and neck (HaN) segmentation in CT image is difficult due to low contrast and large slice thickness that resulted in useless information in coronal and sagittal plane for some organs. In addition, complex and small organs have different requirements on neural network modeling. To achieve an accurate segmentation of 22 HaN organs, we combined three U-Net models. The first model was a 2D model that is advantage for dealing with thick slice images. The second model was a 3D model using a cropped input to

Research paper thumbnail of Digital Virtual Human Based Distance Education System

With Digital Virtual Human as a foundation, a distance education prototype system is presented in... more With Digital Virtual Human as a foundation, a distance education prototype system is presented in the paper. The implementation methods of two key technologies in the system are proposed and described. One is to manage Digital Virtual Human mass data based on data grid technology, and the other is to support group collaborations with application collaboration tools. A case study is used to show the validity and feasibility of the system.

Research paper thumbnail of The application of digital human in distance education

The digital human is a booming research area and its combination with distance education will gre... more The digital human is a booming research area and its combination with distance education will greatly promote the advances of medicine, anatomy and other relevant disciplines. In this paper, they are integrated to establish a local-network based distance education experimental system which contains functions such as teaching, practicing, tutoring and discussing, etc. The volume of the digital human datasets is too huge to deal with using traditional centralized storing methods, so grid technology is introduced to provide efficient, safe and transparent management of the mass data. Through this experiment our solution is proved to be valid and feasible.

Research paper thumbnail of Segmentation of hippocampus based on ROI atlas registration

ABSTRACT Since the change of hippocampal volume is an early symptom for Alzheimer's disea... more ABSTRACT Since the change of hippocampal volume is an early symptom for Alzheimer's disease, hippocampus segmentation of brain image can be used to assist the diagnosis of the Alzheimer's disease. This paper presents a multi-atlas based segmentation method which produces higher segmentation accuracy than single atlas-based segmentation. After the extraction of the ROI, a two-step registration from atlas images to target image is applied to obtain initial segmentations which are combined to generate the final segmentation by several atlas fusion strategies. In the experiments, four different strategies including single maximum, majority voting (MV) and simultaneous truth performance level estimation (STAPLE) and consensus level, labeler accuracy and truth estimation (COLLATE) are tested. Dice overlap between automatic and manual segmentation is employed to compare the results of these atlas selection strategies. The experimental results show that the COLLATE can achieve the better segmentation result in our study.

Research paper thumbnail of Automatic Detection of the Existence of Subarachnoid Hemorrhage from Clinical CT Images

Journal of Medical Systems

Subarachnoid hemorrhage (SAH) is a medical emergency which can lead to death or severe disability... more Subarachnoid hemorrhage (SAH) is a medical emergency which can lead to death or severe disability. Misinterpretation of computed tomography (CT) in patients with SAH is a common problem. How to improve the accuracy of diagnosis is a great challenge to both the clinical physicians and medical researchers. In this paper we proposed a method for the automatic detection of SAH on clinical non-contrast head CT scans. The novelty includes approximation of the subarachnoid space in head CT using an atlas based registration, and exploration of support vector machine to the detection of SAH. The study included 60 patients with SAH and 69 normal controls from clinical hospitals. Thirty patients with SAH and 30 normal controls were used for training, while the rest were used for testing to achieve a testing sensitivity of 100% and specificity of 89.7%. The proposed algorithm might be a potential tool to screen the existence of SAH.

Research paper thumbnail of Delineation of Intracerebral Hemorrhage from Clinical Non-Enhanced Computed Tomography Images

ABSTRACT We delineated intracerebral hemorrhage (ICH) from clinical non-enhanced computed tomogra... more ABSTRACT We delineated intracerebral hemorrhage (ICH) from clinical non-enhanced computed tomography (NCT) images through large grayscale, large grayscale asymmetry with respect to the midsagittal plane (MSP), and large grayscale local contrast. An adaptive approach is proposed to determine thresholds of the 3 features and adjust the window width for data conversion. The substantial grayscale variability of ICH for a subject is addressed by finding the bright portion followed by recovering. Those ICH voxels symmetrical to the MSP are recovered, partial volume effects are compensated and the non-ICH high grayscale regions are excluded. The algorithm is fast, and has been validated (37 cases) to yield a delineation accuracy of 0.915 and qualitatively (altogether 161 cases) with good results. The developed system could be a useful tool to aid quantifying ICH and enhancing stroke therapy.

Research paper thumbnail of An event-related fMRI study on the time difference between the basal ganglia and the cerebellum during finger movements

Research paper thumbnail of Registration of head CT images with subarachnoid hemorrhage

In this paper we propose a new atlas based image registration method of clinical head CT images w... more In this paper we propose a new atlas based image registration method of clinical head CT images with subarachnoid hemorrhage. The registration is based on a probability atlas from the international consortium for brain mapping. We use B-spline as basic warping transform and mutual information as intensity similarity metric. In order to improve the robustness of the method, the brain is extracted and normalized to standard position before the image registration. The proposed method has been tested on 36 clinical head CT images from several hospitals of China, and only one case returns undesirable results. The experimental results show the clinically usability of the registration method in computer aided diagnosis system.

Research paper thumbnail of Human Modeling: From Physical to Digital Some efforts toward building up The Digital Human in China 1

This presentation reviews the research and development of technologies related to Human Modeling ... more This presentation reviews the research and development of technologies related to Human Modeling in China, introduces the effort, the main idea and some key technologies towards building up the Chinese Digital Human with characteristics of Oriental Ethnic Groups. Visible Human Project has been initiated more than ten years ago, which is the first trial in the world to get high-precision

Research paper thumbnail of A Robust Algorithm for Nerve Slice Contours Correspondence

In this paper, the three-dimensional reconstruction of consecutive brachial plexus slices is disc... more In this paper, the three-dimensional reconstruction of consecutive brachial plexus slices is discussed. To get precise results, the contour-based re-construction method is adopted. As the contour correspondence problem is of great importance to the reconstruction, a cluster method is firstly used to get rid of the offsets between the contours introduced during the stage of data acquisi-tion. Besides correspondence check, a robust similarity-based correspondence algorithm is proposed which results in an automatic correspondence rate more than 97%.

Research paper thumbnail of Preprocessing based statistical segmentation of MRA dataset

This paper describes a preprocessing mask technique based statistical mixture components segmenta... more This paper describes a preprocessing mask technique based statistical mixture components segmentation method for extracting blood vessels from brain magnetic resonance angiography (MRA) dataset. The voxels whose intensity is high in the dataset belong to blood vessels or brain skulls, which may bias the adjustment of the blood vessels. Maximum intensity projection (MIP) of the dataset in the Z axis direction was computed and segmented as a mask. The masked MRA dataset was segmented by a low threshold and the remanent voxels were modeled by one normal distribution and one uniform distribution. The parameters were estimated by Expectation-Maximization (EM) algorithm. The results show that this method is feasible for vessel extraction from MRA dataset.

Research paper thumbnail of Human MT + activation is enhanced by adding color to high luminance motion

Research paper thumbnail of An IGSTK-based surgical navigation system connected with medical robot

A surgical navigation system based on IGSTK (Image-Guided Surgical Toolkit) that guide medical ro... more A surgical navigation system based on IGSTK (Image-Guided Surgical Toolkit) that guide medical robot to drill pedicle screw into vertebra precisely is presented. The surgical location device used is NDI Polaris Vicra® optical tracking system and the assistance robot is KUKA® Robot KR 5 sixx R650. Message communication between the navigation system and KUKA robot is implemented based on OpenIGTLink protocol client-server model. Multiple tracked tools can be tracked automatically by state-machine mechanism in a safe manner. To overcome the line of sight limitation of optical tracking system, a new instrument that we called it two-face instrument model has developed to enlarge the rotation angle of the tracked tool. The experiment showed that the navigation could guide robot to execute precise surgical operation in a simple and safe mode.

Research paper thumbnail of 3D nerve: A three-dimensional reconstruction system for peripheral nerves

Repair and regeneration of injured peripheral nerves have always been a focus in the field of ort... more Repair and regeneration of injured peripheral nerves have always been a focus in the field of orthopedics. Traditional nerve atlas contains only two-dimensional information and canpsilat display the real cross and recombination process of nerve bundles in its whole length. To solve this problem, a system, 3D nerve, is proposed for the D reconstruction of peripheral nerves. Through image registration, image segmentation, contour correspondence and surface reconstruction process, this system successfully represents the topographic anatomy of every nerve fascicle and its relationship with the nicety localization information of sense fibers and motor ones in arbitrary sections. It is a great help for clinical peripheral nerve repair and 3D peripheral nerve teaching.

Research paper thumbnail of Curvature-dependent surface visualization of vascular structures

Computerized Medical Imaging and Graphics, 2010

Research paper thumbnail of Several Practical Problems in Clinical Head CT Image Registration

This paper is about some practical problems related to image registration of clinical head CT ima... more This paper is about some practical problems related to image registration of clinical head CT images. The process of image registration is to bring two or more images into spatial alignment. The first step in image registration is to know correct image orientation relative to the world coordinates. The clinical head computed tomography (CT) images have several special features. One is related to different scanning protocol. Usually for detail information on posterior fossa, doctors do two series scan which have thinner slice thickness on the bottom part of the whole brain than the top part to result in two different slice spacing in the two series volumes. The second feature is related to CT gantry tilt angle. In clinical practice, physicians are required to tilt the CT gantry to prevent the X-ray exposure to eyes and other sensitive organs. The resultant image volume has geometrical distortion need to correct. The third feature is about patient position and patient orientation. All of these features need to be reconsidered in the clinical registration applications. We must check the correct image header carefully to get the detail information from head CT images for better registration results.

Research paper thumbnail of Scale-adaptive surface modeling of vascular structures

Biomedical Engineering Online, 2010

Background The effective geometric modeling of vascular structures is crucial for diagnosis, ther... more Background The effective geometric modeling of vascular structures is crucial for diagnosis, therapy planning and medical education. These applications require good balance with respect to surface smoothness, surface accuracy, triangle quality and surface size. Methods Our method first extracts the vascular boundary voxels from the segmentation result, and utilizes these voxels to build a three-dimensional (3D) point cloud whose normal vectors are estimated via covariance analysis. Then a 3D implicit indicator function is computed from the oriented 3D point cloud by solving a Poisson equation. Finally the vessel surface is generated by a proposed adaptive polygonization algorithm for explicit 3D visualization. Results Experiments carried out on several typical vascular structures demonstrate that the presented method yields both a smooth morphologically correct and a topologically preserved two-manifold surface, which is scale-adaptive to the local curvature of the surface. Furthermore, the presented method produces fewer and better-shaped triangles with satisfactory surface quality and accuracy. Conclusions Compared to other state-of-the-art approaches, our method reaches good balance in terms of smoothness, accuracy, triangle quality and surface size. The vessel surfaces produced by our method are suitable for applications such as computational fluid dynamics simulations and real-time virtual interventional surgery.

Research paper thumbnail of A Pilot Study of Functional Magnetic Resonance Imaging of the Brain During Manual and Electroacupuncture Stimulation of Acupuncture Point (LI4 Hegu) in Normal Subjects Reveals Differential Brain Activation Between Methods

Journal of Alternative and Complementary Medicine, 2002

Research paper thumbnail of The lateralization of cerebral hemisphere in the naming of Chinese word

Research paper thumbnail of Brain activity during simple and sequential movements as revealed by event-related fMRI

Neuroimage, 2001

... 首页 > NSTL 期刊 > NEUROIMAGE. Brain activity during simple and sequential ... more ... 首页 > NSTL 期刊 > NEUROIMAGE. Brain activity during simple and sequential movements as revealed by event-relatd fMRI. 通过DOI定位原文. DOI：, 10.1016/S1053-8119(01)92515-7. 作者 ：, Jia FC;Zhang MM;Zhu YH. 期刊 ：, NEUROIMAGE. 年，卷(期) ：, 2001, 13. 分类号 ：, 关键词 ...

Research paper thumbnail of Head and Neck CT Segmentation Based on a Combined U-Net Model

Head and neck (HaN) segmentation in CT image is difficult due to low contrast and large slice thi... more Head and neck (HaN) segmentation in CT image is difficult due to low contrast and large slice thickness that resulted in useless information in coronal and sagittal plane for some organs. In addition, complex and small organs have different requirements on neural network modeling. To achieve an accurate segmentation of 22 HaN organs, we combined three U-Net models. The first model was a 2D model that is advantage for dealing with thick slice images. The second model was a 3D model using a cropped input to

Research paper thumbnail of Digital Virtual Human Based Distance Education System

With Digital Virtual Human as a foundation, a distance education prototype system is presented in... more With Digital Virtual Human as a foundation, a distance education prototype system is presented in the paper. The implementation methods of two key technologies in the system are proposed and described. One is to manage Digital Virtual Human mass data based on data grid technology, and the other is to support group collaborations with application collaboration tools. A case study is used to show the validity and feasibility of the system.

Research paper thumbnail of The application of digital human in distance education

The digital human is a booming research area and its combination with distance education will gre... more The digital human is a booming research area and its combination with distance education will greatly promote the advances of medicine, anatomy and other relevant disciplines. In this paper, they are integrated to establish a local-network based distance education experimental system which contains functions such as teaching, practicing, tutoring and discussing, etc. The volume of the digital human datasets is too huge to deal with using traditional centralized storing methods, so grid technology is introduced to provide efficient, safe and transparent management of the mass data. Through this experiment our solution is proved to be valid and feasible.

Research paper thumbnail of Segmentation of hippocampus based on ROI atlas registration

ABSTRACT Since the change of hippocampal volume is an early symptom for Alzheimer's disea... more ABSTRACT Since the change of hippocampal volume is an early symptom for Alzheimer's disease, hippocampus segmentation of brain image can be used to assist the diagnosis of the Alzheimer's disease. This paper presents a multi-atlas based segmentation method which produces higher segmentation accuracy than single atlas-based segmentation. After the extraction of the ROI, a two-step registration from atlas images to target image is applied to obtain initial segmentations which are combined to generate the final segmentation by several atlas fusion strategies. In the experiments, four different strategies including single maximum, majority voting (MV) and simultaneous truth performance level estimation (STAPLE) and consensus level, labeler accuracy and truth estimation (COLLATE) are tested. Dice overlap between automatic and manual segmentation is employed to compare the results of these atlas selection strategies. The experimental results show that the COLLATE can achieve the better segmentation result in our study.

Research paper thumbnail of Automatic Detection of the Existence of Subarachnoid Hemorrhage from Clinical CT Images

Journal of Medical Systems

Subarachnoid hemorrhage (SAH) is a medical emergency which can lead to death or severe disability... more Subarachnoid hemorrhage (SAH) is a medical emergency which can lead to death or severe disability. Misinterpretation of computed tomography (CT) in patients with SAH is a common problem. How to improve the accuracy of diagnosis is a great challenge to both the clinical physicians and medical researchers. In this paper we proposed a method for the automatic detection of SAH on clinical non-contrast head CT scans. The novelty includes approximation of the subarachnoid space in head CT using an atlas based registration, and exploration of support vector machine to the detection of SAH. The study included 60 patients with SAH and 69 normal controls from clinical hospitals. Thirty patients with SAH and 30 normal controls were used for training, while the rest were used for testing to achieve a testing sensitivity of 100% and specificity of 89.7%. The proposed algorithm might be a potential tool to screen the existence of SAH.

Research paper thumbnail of Delineation of Intracerebral Hemorrhage from Clinical Non-Enhanced Computed Tomography Images

ABSTRACT We delineated intracerebral hemorrhage (ICH) from clinical non-enhanced computed tomogra... more ABSTRACT We delineated intracerebral hemorrhage (ICH) from clinical non-enhanced computed tomography (NCT) images through large grayscale, large grayscale asymmetry with respect to the midsagittal plane (MSP), and large grayscale local contrast. An adaptive approach is proposed to determine thresholds of the 3 features and adjust the window width for data conversion. The substantial grayscale variability of ICH for a subject is addressed by finding the bright portion followed by recovering. Those ICH voxels symmetrical to the MSP are recovered, partial volume effects are compensated and the non-ICH high grayscale regions are excluded. The algorithm is fast, and has been validated (37 cases) to yield a delineation accuracy of 0.915 and qualitatively (altogether 161 cases) with good results. The developed system could be a useful tool to aid quantifying ICH and enhancing stroke therapy.

Research paper thumbnail of An event-related fMRI study on the time difference between the basal ganglia and the cerebellum during finger movements

Research paper thumbnail of Registration of head CT images with subarachnoid hemorrhage

In this paper we propose a new atlas based image registration method of clinical head CT images w... more In this paper we propose a new atlas based image registration method of clinical head CT images with subarachnoid hemorrhage. The registration is based on a probability atlas from the international consortium for brain mapping. We use B-spline as basic warping transform and mutual information as intensity similarity metric. In order to improve the robustness of the method, the brain is extracted and normalized to standard position before the image registration. The proposed method has been tested on 36 clinical head CT images from several hospitals of China, and only one case returns undesirable results. The experimental results show the clinically usability of the registration method in computer aided diagnosis system.

Research paper thumbnail of Human Modeling: From Physical to Digital Some efforts toward building up The Digital Human in China 1

This presentation reviews the research and development of technologies related to Human Modeling ... more This presentation reviews the research and development of technologies related to Human Modeling in China, introduces the effort, the main idea and some key technologies towards building up the Chinese Digital Human with characteristics of Oriental Ethnic Groups. Visible Human Project has been initiated more than ten years ago, which is the first trial in the world to get high-precision

Research paper thumbnail of A Robust Algorithm for Nerve Slice Contours Correspondence

In this paper, the three-dimensional reconstruction of consecutive brachial plexus slices is disc... more In this paper, the three-dimensional reconstruction of consecutive brachial plexus slices is discussed. To get precise results, the contour-based re-construction method is adopted. As the contour correspondence problem is of great importance to the reconstruction, a cluster method is firstly used to get rid of the offsets between the contours introduced during the stage of data acquisi-tion. Besides correspondence check, a robust similarity-based correspondence algorithm is proposed which results in an automatic correspondence rate more than 97%.

Research paper thumbnail of Preprocessing based statistical segmentation of MRA dataset

This paper describes a preprocessing mask technique based statistical mixture components segmenta... more This paper describes a preprocessing mask technique based statistical mixture components segmentation method for extracting blood vessels from brain magnetic resonance angiography (MRA) dataset. The voxels whose intensity is high in the dataset belong to blood vessels or brain skulls, which may bias the adjustment of the blood vessels. Maximum intensity projection (MIP) of the dataset in the Z axis direction was computed and segmented as a mask. The masked MRA dataset was segmented by a low threshold and the remanent voxels were modeled by one normal distribution and one uniform distribution. The parameters were estimated by Expectation-Maximization (EM) algorithm. The results show that this method is feasible for vessel extraction from MRA dataset.

Research paper thumbnail of Human MT + activation is enhanced by adding color to high luminance motion

Research paper thumbnail of An IGSTK-based surgical navigation system connected with medical robot

A surgical navigation system based on IGSTK (Image-Guided Surgical Toolkit) that guide medical ro... more A surgical navigation system based on IGSTK (Image-Guided Surgical Toolkit) that guide medical robot to drill pedicle screw into vertebra precisely is presented. The surgical location device used is NDI Polaris Vicra® optical tracking system and the assistance robot is KUKA® Robot KR 5 sixx R650. Message communication between the navigation system and KUKA robot is implemented based on OpenIGTLink protocol client-server model. Multiple tracked tools can be tracked automatically by state-machine mechanism in a safe manner. To overcome the line of sight limitation of optical tracking system, a new instrument that we called it two-face instrument model has developed to enlarge the rotation angle of the tracked tool. The experiment showed that the navigation could guide robot to execute precise surgical operation in a simple and safe mode.

Research paper thumbnail of 3D nerve: A three-dimensional reconstruction system for peripheral nerves

Repair and regeneration of injured peripheral nerves have always been a focus in the field of ort... more Repair and regeneration of injured peripheral nerves have always been a focus in the field of orthopedics. Traditional nerve atlas contains only two-dimensional information and canpsilat display the real cross and recombination process of nerve bundles in its whole length. To solve this problem, a system, 3D nerve, is proposed for the D reconstruction of peripheral nerves. Through image registration, image segmentation, contour correspondence and surface reconstruction process, this system successfully represents the topographic anatomy of every nerve fascicle and its relationship with the nicety localization information of sense fibers and motor ones in arbitrary sections. It is a great help for clinical peripheral nerve repair and 3D peripheral nerve teaching.

Research paper thumbnail of Curvature-dependent surface visualization of vascular structures

Computerized Medical Imaging and Graphics, 2010

Research paper thumbnail of Several Practical Problems in Clinical Head CT Image Registration

This paper is about some practical problems related to image registration of clinical head CT ima... more This paper is about some practical problems related to image registration of clinical head CT images. The process of image registration is to bring two or more images into spatial alignment. The first step in image registration is to know correct image orientation relative to the world coordinates. The clinical head computed tomography (CT) images have several special features. One is related to different scanning protocol. Usually for detail information on posterior fossa, doctors do two series scan which have thinner slice thickness on the bottom part of the whole brain than the top part to result in two different slice spacing in the two series volumes. The second feature is related to CT gantry tilt angle. In clinical practice, physicians are required to tilt the CT gantry to prevent the X-ray exposure to eyes and other sensitive organs. The resultant image volume has geometrical distortion need to correct. The third feature is about patient position and patient orientation. All of these features need to be reconsidered in the clinical registration applications. We must check the correct image header carefully to get the detail information from head CT images for better registration results.

Research paper thumbnail of Scale-adaptive surface modeling of vascular structures

Biomedical Engineering Online, 2010

Background The effective geometric modeling of vascular structures is crucial for diagnosis, ther... more Background The effective geometric modeling of vascular structures is crucial for diagnosis, therapy planning and medical education. These applications require good balance with respect to surface smoothness, surface accuracy, triangle quality and surface size. Methods Our method first extracts the vascular boundary voxels from the segmentation result, and utilizes these voxels to build a three-dimensional (3D) point cloud whose normal vectors are estimated via covariance analysis. Then a 3D implicit indicator function is computed from the oriented 3D point cloud by solving a Poisson equation. Finally the vessel surface is generated by a proposed adaptive polygonization algorithm for explicit 3D visualization. Results Experiments carried out on several typical vascular structures demonstrate that the presented method yields both a smooth morphologically correct and a topologically preserved two-manifold surface, which is scale-adaptive to the local curvature of the surface. Furthermore, the presented method produces fewer and better-shaped triangles with satisfactory surface quality and accuracy. Conclusions Compared to other state-of-the-art approaches, our method reaches good balance in terms of smoothness, accuracy, triangle quality and surface size. The vessel surfaces produced by our method are suitable for applications such as computational fluid dynamics simulations and real-time virtual interventional surgery.

Research paper thumbnail of A Pilot Study of Functional Magnetic Resonance Imaging of the Brain During Manual and Electroacupuncture Stimulation of Acupuncture Point (LI4 Hegu) in Normal Subjects Reveals Differential Brain Activation Between Methods

Journal of Alternative and Complementary Medicine, 2002

Research paper thumbnail of The lateralization of cerebral hemisphere in the naming of Chinese word

Research paper thumbnail of Brain activity during simple and sequential movements as revealed by event-related fMRI

Neuroimage, 2001

... 首页 > NSTL 期刊 > NEUROIMAGE. Brain activity during simple and sequential ... more ... 首页 > NSTL 期刊 > NEUROIMAGE. Brain activity during simple and sequential movements as revealed by event-relatd fMRI. 通过DOI定位原文. DOI：, 10.1016/S1053-8119(01)92515-7. 作者 ：, Jia FC;Zhang MM;Zhu YH. 期刊 ：, NEUROIMAGE. 年，卷(期) ：, 2001, 13. 分类号 ：, 关键词 ...