Diseases not only bring troubles to people’s body functions and mind but also influence the appearances and behaviours of human beings.Similarly,we can analyse the diseases from people’s appearances and behaviours a...Diseases not only bring troubles to people’s body functions and mind but also influence the appearances and behaviours of human beings.Similarly,we can analyse the diseases from people’s appearances and behaviours and use the personal medical history for human identification.In this article,medical indicators presented in abnormal changes of human appearances and behaviours caused by physiological or psychological diseases were introduced,and were applied in the field of forensic identification of human images,which we called medical forensic identification of human images(mFIHI).The proposed method analysed the people’s medical signs by studying the appearance and behaviour characteristics depicted in images or videos,and made a comparative examination between the medical indicators of the questioned human images and the corresponding signs or medical history of suspects.Through a conformity and difference analysis on medical indicators and their indicated diseases,it would provide an important information for human identification from images or videos.A case study was carried out to demonstrate and verify the feasibility of the proposed method of mFIHI,and our results showed that it would be important contents and angles for forensic expert manual examination in forensic human image identification.展开更多
In order to effectively improve the pathological diagnosis capability and feature resolution of 3D human brain CT images,a threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel ...In order to effectively improve the pathological diagnosis capability and feature resolution of 3D human brain CT images,a threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is proposed in this paper.In this method,first,original 3D human brain image information is collected,and CT image filtering is performed to the collected information through the gradient value decomposition method,and edge contour features of the 3D human brain CT image are extracted.Then,the threshold segmentation method is adopted to segment the regional pixel feature block of the 3D human brain CT image to segment the image into block vectors with high-resolution feature points,and the 3D human brain CT image is reconstructed with the salient feature point as center.Simulation results show that the method proposed in this paper can provide accuracy up to 100%when the signal-to-noise ratio is 0,and with the increase of signal-to-noise ratio,the accuracy provided by this method is stable at 100%.Comparison results show that the threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is signicantly better than traditional methods in pathological feature estimation accuracy,and it effectively improves the rapid pathological diagnosis and positioning recognition abilities to CT images.展开更多
Objective To establish a 3D atlas of the lenticular nuclei and its subnucleus with the cryosection images of the male from "Atlas of Chinese Visible Human". Methods The lenticular nuclei and its subnucleus w...Objective To establish a 3D atlas of the lenticular nuclei and its subnucleus with the cryosection images of the male from "Atlas of Chinese Visible Human". Methods The lenticular nuclei and its subnucleus were segmented from the cryosection images and reconstructed with the software展开更多
Human neural stem cells(h NSCs) derived from the ventral mesencephalon are powerful research tools and candidates for cell therapies in Parkinson's disease. However, their clinical translation has not been fully re...Human neural stem cells(h NSCs) derived from the ventral mesencephalon are powerful research tools and candidates for cell therapies in Parkinson's disease. However, their clinical translation has not been fully realized due, in part, to the limited ability to track stem cell regional localization and survival over long periods of time after in vivo transplantation. Magnetic resonance imaging provides an excellent non-invasive method to study the fate of transplanted cells in vivo. For magnetic resonance imaging cell tracking, cells need to be labeled with a contrast agent, such as magnetic nanoparticles, at a concentration high enough to be easily detected by magnetic resonance imaging. Grafting of human neural stem cells labeled with magnetic nanoparticles allows cell tracking by magnetic resonance imaging without impairment of cell survival, proliferation, self-renewal, and multipotency. However, the results reviewed here suggest that in long term grafting, activated microglia and macrophages could contribute to magnetic resonance imaging signal by engulfing dead labeled cells or iron nanoparticles dispersed freely in the brain parenchyma over time.展开更多
We propose a novel end-to-end deep learning framework, the Joint Matting Network(JMNet), to automatically generate alpha mattes for human images.We utilize the intrinsic structures of the human body as seen in images ...We propose a novel end-to-end deep learning framework, the Joint Matting Network(JMNet), to automatically generate alpha mattes for human images.We utilize the intrinsic structures of the human body as seen in images by introducing a pose estimation module,which can provide both global structural guidance and a local attention focus for the matting task. Our network model includes a pose network, a trimap network, a matting network, and a shared encoder to extract features for the above three networks. We also append a trimap refinement module and utilize gradient loss to provide a sharper alpha matte. Extensive experiments have shown that our method outperforms state-of-theart human matting techniques;the shared encoder leads to better performance and lower memory costs.Our model can process real images downloaded from the Internet for use in composition applications.展开更多
Photoacoustic (PA) microscopy comes with high potential for human skin imaging, since it allows noninvasively high-resolution imaging of the natural hemoglobin at depths of several millimeters. Here, we developed a ...Photoacoustic (PA) microscopy comes with high potential for human skin imaging, since it allows noninvasively high-resolution imaging of the natural hemoglobin at depths of several millimeters. Here, we developed a PA microscopy to achieve high-resolution, high-contrast, and large field of view imaging of skin. A three-dimensional (3D) depth-coding technology was used to encode the depth information in PA images, which is very intuitive for identifying the depth of blood vessels in a two-dimensional image, and the vascular structure can be analyzed at different depths. Imaging results demonstrate that the 3D depth-coded PA microscopy should be translated from the bench to the bedside.展开更多
Searching for effective biomarkers is one of the most challenging tasks in the research ?eld of Autism Spectrum Disorder(ASD). Magnetic resonance imaging(MRI) provides a non-invasive and powerful tool for investi...Searching for effective biomarkers is one of the most challenging tasks in the research ?eld of Autism Spectrum Disorder(ASD). Magnetic resonance imaging(MRI) provides a non-invasive and powerful tool for investigating changes in the structure, function, maturation,connectivity, and metabolism of the brain of children with ASD. Here, we review the more recent MRI studies in young children with ASD, aiming to provide candidate biomarkers for the diagnosis of childhood ASD. The review covers structural imaging methods, diffusion tensor imaging, resting-state functional MRI, and magnetic resonance spectroscopy. Future advances in neuroimaging techniques, as well as cross-disciplinary studies and largescale collaborations will be needed for an integrated approach linking neuroimaging, genetics, and phenotypic data to allow the discovery of new, effective biomarkers.展开更多
基金This work is supported by Shanghai Sailing Program[grant number 17YF1420000]Ministry of Finance of the People's Republic of China[grant numbers GY2018G-6 and GY2020G-8].
文摘Diseases not only bring troubles to people’s body functions and mind but also influence the appearances and behaviours of human beings.Similarly,we can analyse the diseases from people’s appearances and behaviours and use the personal medical history for human identification.In this article,medical indicators presented in abnormal changes of human appearances and behaviours caused by physiological or psychological diseases were introduced,and were applied in the field of forensic identification of human images,which we called medical forensic identification of human images(mFIHI).The proposed method analysed the people’s medical signs by studying the appearance and behaviour characteristics depicted in images or videos,and made a comparative examination between the medical indicators of the questioned human images and the corresponding signs or medical history of suspects.Through a conformity and difference analysis on medical indicators and their indicated diseases,it would provide an important information for human identification from images or videos.A case study was carried out to demonstrate and verify the feasibility of the proposed method of mFIHI,and our results showed that it would be important contents and angles for forensic expert manual examination in forensic human image identification.
文摘In order to effectively improve the pathological diagnosis capability and feature resolution of 3D human brain CT images,a threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is proposed in this paper.In this method,first,original 3D human brain image information is collected,and CT image filtering is performed to the collected information through the gradient value decomposition method,and edge contour features of the 3D human brain CT image are extracted.Then,the threshold segmentation method is adopted to segment the regional pixel feature block of the 3D human brain CT image to segment the image into block vectors with high-resolution feature points,and the 3D human brain CT image is reconstructed with the salient feature point as center.Simulation results show that the method proposed in this paper can provide accuracy up to 100%when the signal-to-noise ratio is 0,and with the increase of signal-to-noise ratio,the accuracy provided by this method is stable at 100%.Comparison results show that the threshold segmentation method of multi-resolution 3D human brain CT image based on edge pixel grayscale feature decomposition is signicantly better than traditional methods in pathological feature estimation accuracy,and it effectively improves the rapid pathological diagnosis and positioning recognition abilities to CT images.
文摘Objective To establish a 3D atlas of the lenticular nuclei and its subnucleus with the cryosection images of the male from "Atlas of Chinese Visible Human". Methods The lenticular nuclei and its subnucleus were segmented from the cryosection images and reconstructed with the software
基金To AMS:Instituto de Salud Carlos-III(RETICS Ter Cel RD12/0019/0013)Comunidad Autónoma de Madrid(S2010-BMD-2336)+3 种基金MINECO(SAF2010-17167)the institutional grant of the Fundación Ramón Areces to the CBMSOTo MRG:Reina Sofia FoundationComunidad Autónoma Madrid(S2010-BMD-2460)
文摘Human neural stem cells(h NSCs) derived from the ventral mesencephalon are powerful research tools and candidates for cell therapies in Parkinson's disease. However, their clinical translation has not been fully realized due, in part, to the limited ability to track stem cell regional localization and survival over long periods of time after in vivo transplantation. Magnetic resonance imaging provides an excellent non-invasive method to study the fate of transplanted cells in vivo. For magnetic resonance imaging cell tracking, cells need to be labeled with a contrast agent, such as magnetic nanoparticles, at a concentration high enough to be easily detected by magnetic resonance imaging. Grafting of human neural stem cells labeled with magnetic nanoparticles allows cell tracking by magnetic resonance imaging without impairment of cell survival, proliferation, self-renewal, and multipotency. However, the results reviewed here suggest that in long term grafting, activated microglia and macrophages could contribute to magnetic resonance imaging signal by engulfing dead labeled cells or iron nanoparticles dispersed freely in the brain parenchyma over time.
基金supported by National Natural Science Foundation of China(Grant Nos.61561146393 and61521002)supported by a Victoria Early-Career Research Excellence Award。
文摘We propose a novel end-to-end deep learning framework, the Joint Matting Network(JMNet), to automatically generate alpha mattes for human images.We utilize the intrinsic structures of the human body as seen in images by introducing a pose estimation module,which can provide both global structural guidance and a local attention focus for the matting task. Our network model includes a pose network, a trimap network, a matting network, and a shared encoder to extract features for the above three networks. We also append a trimap refinement module and utilize gradient loss to provide a sharper alpha matte. Extensive experiments have shown that our method outperforms state-of-theart human matting techniques;the shared encoder leads to better performance and lower memory costs.Our model can process real images downloaded from the Internet for use in composition applications.
基金supported by the National Natural Science Foundation of China(Nos.11774101,61627827,81630046,and 91539127)the Science and Technology Planning Project of Guangdong Province,China(No.2015B020233016)+1 种基金the Distinguished Young Teacher Project in Higher Education of Guangdong,China(No.YQ2015049)the Science and Technology Youth Talent for Special Program of Guangdong,China(No.2015TQ01X882)
文摘Photoacoustic (PA) microscopy comes with high potential for human skin imaging, since it allows noninvasively high-resolution imaging of the natural hemoglobin at depths of several millimeters. Here, we developed a PA microscopy to achieve high-resolution, high-contrast, and large field of view imaging of skin. A three-dimensional (3D) depth-coding technology was used to encode the depth information in PA images, which is very intuitive for identifying the depth of blood vessels in a two-dimensional image, and the vascular structure can be analyzed at different depths. Imaging results demonstrate that the 3D depth-coded PA microscopy should be translated from the bench to the bedside.
文摘Searching for effective biomarkers is one of the most challenging tasks in the research ?eld of Autism Spectrum Disorder(ASD). Magnetic resonance imaging(MRI) provides a non-invasive and powerful tool for investigating changes in the structure, function, maturation,connectivity, and metabolism of the brain of children with ASD. Here, we review the more recent MRI studies in young children with ASD, aiming to provide candidate biomarkers for the diagnosis of childhood ASD. The review covers structural imaging methods, diffusion tensor imaging, resting-state functional MRI, and magnetic resonance spectroscopy. Future advances in neuroimaging techniques, as well as cross-disciplinary studies and largescale collaborations will be needed for an integrated approach linking neuroimaging, genetics, and phenotypic data to allow the discovery of new, effective biomarkers.