首页分享科技大数据知识发现平台

科技大数据知识发现平台

来源：花匠小妙招时间：2026-01-24 18:40

Br J Radiol，2022，20210031

Liwen Wan; Haoxiang Li; Lei Zhang; Shi Su; Cheng Wang; Baochang Zhang; Dong Liang; Hairong Zheng; Xin Liu; Na Zhang;

中国CT和MRI杂志，1672-5131，2022，020(008)，180-185

戚玉龙; 赵琴琴; 程传力; 邹超; 刘新; 郑海荣; 成官迅;

摘要：目的磁共振质子密度脂肪分数(PDFF)图像可定量反映全身脂肪分布,本文基于全身脂肪分布特征的自动分析方法,探索了脂肪分布特征与传统人体学指标之间的相关性。方法对37名志愿者分别进行全身横断位磁共振PDFF图像扫描,覆盖范围从颈部到膝盖,每位志愿者获得约160张PDFF图像;利用基于深度学习的全自动脂肪分割法对全身脂肪(TAT)进行分割,得到各部位皮下脂肪(SAT)和内部脂肪(IAT)分布图;最终分析基于PDFF图像的全身脂肪分布特征与人体学指标:身体质量指数(BMI)和腰臀比(WHR)之间的相关性。结果仅全身脂肪体积比例与传统人体学指标呈中度相关性,其他指标与人体学指标相关性均较低。与人体学指标不同,全身脂肪分布特征在性别之间体现出较大差异。结论基于磁共振成像的全身脂肪分布特征能为肥胖的相关研究提供全新的手段和工具。…展开更多>>

IEEE TRANSACTIONS ON MEDICAL IMAGING，0278-0062，2021，40(1)，48-58

Su, Shi; Qiu, Zhilang; Luo, Chao; Shi, Caiyun; Wan, Liwen; Zhu, Yanjie; Li, Ye; Liu, Xin; Zheng, Hairong; Liang, Dong; Wang, Haifeng;

摘要：The Wave Controlled Aliasing In Parallel Imaging (Wave-CAIPI) technique manifests great potential to highly accelerate three-dimensional (3D) balanced steady- state free precession (bSSFP) through substantially reducing the geometric factor (g-factor) and aliasing artifacts of image reconstruction. However, severe banding artifacts appear in bSSFP imaging due to unbalanced gradients with nonzero 0th moment applied by the conventional Wave-CAIPI technique. In this study, we propose a 3DWave-bSSFP scheme that adopts truncated wave gradients with zero 0th moment to avoid introducing additional banding artifacts and to maintain the advantages of wave encoding. The simulation results indicate that the number of wave cycles that are truncated and different options of applying wave gradients affect both the g-factor reduction and image quality, but the influence is limited. In phantom experiments, the proposed technique shows similar acceleration performance as the conventional Wave-CAIPI technique and effectively eliminates its introduced banding artifacts. Additionally, Wave-bSSFP obtains up to 12x retrospective acceleration at 0.8 mm isotropic resolution in in vivo 3D brain experiments and is superior to the state-of-the-art Controlled Aliasing In Parallel Imaging Results IN Higher Acceleration ( CAIPIRINHA) technique, according to both visual validation and quantitative analysis. Moreover, in vivo 3D spine and abdomen imaging demonstrate the potential clinical applications of Wave-bSSFP with fast acquisition speed, improved isotropic resolution and fine image quality.…展开更多>>

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY，2223-4292，2021，11(1)，57-66

Zhu, Tingting; Ren, Lijie; Zhang, Lei; Shao, Yinghui; Wan, Liwen; Li, Ye; Liang, Dong; Zheng, Hairong; Liu, Xin; Zhang, Na;

摘要：Background: The characteristics of plaque that ultimately lead to different subcortical infarctions remain unclear. We explored the differences in pla que characteristics between patients with small subcortical infarction (SSI) and large subcortical infarction (LSI) of the middle cerebral artery (MCA) using high resolution magnetic resonance vessel wall imaging (HR-MRVWI).…展开更多>>

APPLIED INTELLIGENCE，0924-669X，2021，51(5)，2838-2849

Huang, Zhenxing; Liu, Xinfeng; Wang, Rongpin; Zhang, Mudan; Zeng, Xianchun; Liu, Jun; Yang, Yongfeng; Liu, Xin; Zheng, Hairong; Liang, Dong; Hu, Zhanli;

摘要：The novel coronavirus (COVID-19) pneumonia has become a serious health challenge in countries worldwide. Many radiological findings have shown that X- ray and CT imaging scans are an effective solution to assess disease severity during the early stage of COVID-19. Many artificial intelligence (AI)-assisted diagnosis works have rapidly been proposed to focus on solving this classification problem and determine whether a patient is infected with COVID-19. Most of these works have designed networks and applied a single CT image to perform classification; however, this approach ignores prior information such as the patient's clinical symptoms. Second, making a more specific diagnosis of clinical severity, such as slight or severe, is worthy of attention and is conducive to determining better follow-up treatments. In this paper, we propose a deep learning (DL) based dual-tasks network, named FaNet, that can perform rapid both diagnosis and severity assessments for COVID-19 based on the combination of 3D CT imaging and clinical symptoms. Generally, 3D CT image sequences provide more spatial information than do single CT images. In addition, the clinical symptoms can be considered as prior information to improve the assessment accuracy; these symptoms are typically quickly and easily accessible to radiologists. Therefore, we designed a network that considers both CT image information and existing clinical symptom information and conducted experiments on 416 patient data, including 207 normal chest CT cases and 209 COVID-19 confirmed ones. The experimental results demonstrate the effectiveness of the additional symptom prior information as well as the network architecture designing. The proposed FaNet achieved an accuracy of 98.28% on diagnosis assessment and 94.83% on severity assessment for test datasets. In the future, we will collect more covid-CT patient data and seek further improvement.…展开更多>>

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY，2223-4292，2021，11(6)，2415-U87

Zhou, Hui; Liu, Yang; Long, Xiaojing; Qiao, Yangzi; Lee, Jo; Liu, Xin; Zheng, Hairong; Zou, Chao;

摘要：Background: Opening the blood-brain barrier (BBB) with focused ultrasound and microbubbles (MBs) has potential use in non-invasive targeted therapy fo r central nervous system (CNS) diseases. Rapid short-pulse (RaSP) ultrasound with a microsecond sequence has been proposed as a minimally disruptive and efficient method for opening the BBB. This work aimed to test the feasibility and safety of BBB opening in a nonhuman primate model using combined RaSP ultrasound sequence and MBs.…展开更多>>

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY，2223-4292，2021，11(2)，749-762

Xue, Hengzhi; Zhang, Qiyang; Zou, Sijuan; Zhang, Weiguang; Zhou, Chao; Tie, Changjun; Wan, Qian; Teng, Yueyang; Li, Yongchang; Liang, Dong; Liu, Xin; Yang, Yongfeng; Zheng, Hairong; Zhu, Xiaohua; Hu, Zhanli; …展开更多>>

摘要：Background: Reducing the radiation tracer dose and scanning time during positron emission tomography (PET) imaging can reduce the cost of the tracer, reduce motion artifacts, and increase the efficiency of the scanner. However, the reconstructed images to be noisy. It is very important to reconstruct high-quality images with low-count (LC) data. Therefore, we propose a deep learning method called LCPR-Net, which is used for directly reconstructing full-count (FC) PET images from corresponding LC sinogram data.…展开更多>>

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY，2223-4292，2021，11(1)，276-289

Mao, Huan; Guan, Xiuhong; Peng, Kewen; Cai, Yanjun; Yang, Jing; He, Xueping; Chen, Hanwei; Zhang, Xiaoyong; Bi, Xiaoming; Liu, Xin; Li, Debiao; Fan, Zhaoyang; Deng, Zhixian; Xie, Guoxi; …展开更多>>

摘要：Background: Black-blood thrombus imaging (BTI) has shown to be advantageous for the diagnosis of deep vein thrombosis (DVT). However, previous techniq ues using fast spin echo have a high specific absorption rate. As DANTE (delay alternating with nutation for tailored excitation) black-blood preparation can suppress blood flows over a broad range of velocities, we hypothesized that a DANTE black-blood preparation combined with a fast low-angle shot (FLASH) gradient-echo readout-DANTE-FLASH could be used to diagnose DVT.…展开更多>>

PHYSICS IN MEDICINE AND BIOLOGY，0031-9155，2021，66(1)，

Huang, Zhenxing; Chen, Zixiang; Chen, Jincai; Lu, Ping; Quan, Guotao; Du, Yanfeng; Li, Chenwei; Gu, Zheng; Yang, Yongfeng; Liu, Xin; Zheng, Hairong; Liang, Dong; Hu, Zhanli; …展开更多>>

摘要：Many deep learning (DL)-based image restoration methods for low-dose CT (LDCT) problems directly employ the end-to-end networks on low-dose training d ata without considering dose differences. However, the radiation dose difference has a great impact on the ultimate results, and lower doses increase the difficulty of restoration. Moreover, there is increasing demand to design and estimate acceptable scanning doses for patients in clinical practice, necessitating dose-aware networks embedded with adaptive dose estimation. In this paper, we consider these dose differences of input LDCT images and propose an adaptive dose-aware network. First, considering a large dose distribution range for simulation convenience, we coarsely define five dose levels in advance as lowest, lower, mild, higher and highest radiation dose levels. Instead of directly building the end-to-end mapping function between LDCT images and high-dose CT counterparts, the dose level is primarily estimated in the first stage. In the second stage, the adaptively learned low-dose level is used to guide the image restoration process as the pattern of prior information through the channel feature transform. We conduct experiments on a simulated dataset based on original high dose parts of American Association of Physicists in Medicine challenge datasets from the Mayo Clinic. Ablation studies validate the effectiveness of the dose-level estimation, and the experimental results show that our method is superior to several other DL-based methods. Specifically, our method provides obviously better performance in terms of the peak signal-to-noise ratio and visual quality reflected in subjective scores. Due to the dual-stage process, our method may suffer limitations under more parameters and coarse dose-level definitions, and thus, further improvements in clinical practical applications with different CT equipment vendors are planned in future work.…展开更多>>

NEUROCOMPUTING，0925-2312，2021，428，104-115

Huang, Zhenxing; Liu, Xinfeng; Wang, Rongpin; Chen, Jincai; Lu, Ping; Zhang, Qiyang; Jiang, Changhui; Yang, Yongfeng; Liu, Xin; Zheng, Hairong; Liang, Dong; Hu, Zhanli; …展开更多>>

摘要：Currently, many deep learning (DL)-based low-dose CT image postprocessing technologies fail to consider the anatomical differences in training data am ong different human body sites, such as the cranium, lung and pelvis. In addition, we can observe evident anatomical similarities at the same site among individuals. However, these anatomical differences and similarities are ignored in the current DL-based methods during the network training process. In this paper, we propose a deep network trained by introducing anatomical site labels, termed attributes for training data. Then, the network can adaptively learn to obtain the optimal weight for each anatomical site. By doing so, the proposed network can take full advantage of anatomical prior information to estimate high-resolution CT images. Furthermore, we employ a Wasserstein generative adversarial network (WGAN) augmented with attributes to preserve more structural details. Compared with the traditional networks that do not consider the anatomical prior and whose weights are consequently the same for each anatomical site, the proposed network achieves better performance by adaptively adjusting to the anatomical prior information. (c) 2020 Elsevier B.V. All rights reserved.…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：郑海荣; 刘新; 邹超; 帖长军; 孟德; 乔阳紫; 文剑洪;

申请日：2019-12-14

公开(公告)日：2024-02-09

摘要：本申请涉及一种周期性运动物体测温方法、系统及电子设备。包括：步骤a：在治疗开始前，采集n幅患者自由呼吸状态下的腹部图像，得到参考图集A；步骤b：提取所述参考图集的特征向量，生成特征图；步骤c：开始治疗时，将扫描生成的患者腹部图像B与所述特征图进行最小二乘法拟合，得到拟合值Wgt;；步骤d：根据所述拟合值W…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：史彩云; 王海峰; 梁栋; 程静; 刘新; 郑海荣;

申请日：2022-12-26

公开(公告)日：2024-06-28

摘要：本发明公开了一基于深度学习的正对比磁共振三维成像方法及装置，涉及医学领域，其中该方法包括：获取测试数据，并对所述测试数据进行相位解卷绕获得局部场图；将所述局部场图及对应的极化核，幅值图和掩膜矩阵输入预先创建的卷积神经网络模型，获得磁化率正对比图，其中，所述卷积神经网络模型是将零值磁化率图输入至预先建立的正则化模型及CNN网络并进行多次循环后得到的。本发明可以通过三维快速可变翻转角的正对比成像技术采集真实磁化率图数据，采用拟合的训练数据实现对卷积神经网络模型的训练，实现正对比图像实时的在线重建和可视化，定位也更准确。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：李印生; 梁栋; 刘新; 郑海荣;

申请日：2022-08-25

公开(公告)日：2024-03-15

摘要：本发明实施例公开了一种C臂CT心脏图像处理方法、装置、计算机设备及存储介质，该方法包括：获取测量投影数据对应的初始图像序列，测量投影数据对应心脏的舒张期或收缩期；将初始图像序列输入已训练的图像处理模型以得到重构图像序列；其中，已训练的图像处理模型用于确定初始图像序列对应的初始特征序列；在时间维度上对初始特征序列进行重采样以得到期望特征序列；确定期望特征序列对应的重构图像序列，期望特征序列包括初始特征与重采样特征，重采样特征对应的目标时刻分布在相应初始特征对应的目标时刻的时间邻域内，时间邻域小于或等于对应的舒张期时长或收缩期时长。解决了现有技术存在无法提高C臂CT图像时间分辨率的问题。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院,南方科技大学

发明（设计）人：朱燕杰; 曹晨涛; 梁栋; 崔卓须; 朱庆永; 刘新; 郑海荣;

申请日：2022-10-31

公开(公告)日：2024-04-30

摘要：本发明涉及一种基于部分可分函数自适应动态磁共振快速成像方法及装置。该方法及装置基于动态磁共振的低秩先验和稀疏先验构建动态磁共振重建模型，动态磁共振重建模型首先将输入的低秩通过图像域的湮没关系转化为对图像滤波器零空间的刻画，动态磁共振重建模型再利用Hankel矩阵乘积与卷积的等价关系，将低秩用卷积网络表达，并将其迭代求解展开到卷积网络中。本发明提出的神经网络可以到达更高的磁共振重建加速倍数，达到更好的重建效果，对动态帧的捕捉更为准确。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：张娜; 郑海荣; 刘新; 梁栋; 胡战利; 李烨; 邹超; 钟裕祥;

申请日：2023-12-08

公开(公告)日：2024-03-19

摘要：本申请实施例提供了一种高分辨率图像重构方法和装置、计算机设备及存储介质，属于图像处理技术领域。该方法包括：获取低分辨率图像；其中，所述低分辨率图像由高分辨率的目标图像降低分辨率得到；将低分辨率图像输入至少两个阶段的图像重构网络；通过图像重构网络对低分辨率图像进行高分辨率重构，得到初步重构图像；根据初步重构图像和目标图像对下一阶段的图像重构网络进行参数调整；通过调整后的图像重构网络对低分辨率图像进行高分辨率重构得到更新重构图像；根据更新重构图像和目标图像对下下阶段的图像重构网络进行参数调整，直至最后阶段的图像重构网络输出高分辨率图像。本申请实施例能够有效利用先验信息提高高分辨率图像的重建效果。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：吴垠; 郑海荣; 刘新;

申请日：2020-12-07

公开(公告)日：2024-03-08

摘要：本申请公开了用于磁共振的化学交换饱和转移定量方法、装置及介质，属于生物医学工程领域。本申请的定量方法包括：获取水的纵向弛豫率；预设基于非稳态实验条件下计算水的自旋锁弛豫率的变形公式，变形公式的至少一个变形参数为非稳态实验条件下的饱和信号与无饱和参考信号的比值；获取非稳态实验条件下的多项参数，并根据上述参数计算变形公式，获取水的自旋锁弛豫率；基于水的纵向弛豫率与水的自旋锁弛豫率，获取稳态实验条件下的磁共振化学交换饱和转移信号；基于该信号获取稳态实验条件下的磁共振化学交换饱和转移效应。本申请能够基于非稳态CEST信号计算获取稳态CEST信号，移除了成像参数对CEST定量结果的影响，提高了CEST定量的准确性。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：葛永帅; 梁栋; 朱炯滔; 刘新; 郑海荣;

申请日：2019-09-30

公开(公告)日：2024-02-27

摘要：本发明公开了一种CT成像方法、装置、存储设备及医学成像系统。其中CT成像方法包括：获取目标对象的投影数据，其中，所述投影数据为基于预设剂量的X射线光子对所述目标对象进行检测时采集得到，所述预设剂量小于CT标准剂量；将所述投影数据发送至预先训练的成像模型，将所述成像模型的输出图像确定为所述目标对象的C T图像，其中，所述成像模型由标准剂量的CT图像和包含噪声的样本投影数据训练得到。通过设置三个子网络模块，分别对投影域数据和CT域数据进行去噪处理，实现在图像重建过程中的双重去噪，提高了去噪效果，使得在低剂量X射线光子进行检测时，得到高质量的CT图像。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：葛永帅; 梁栋; 刘新; 郑海荣;

申请日：2020-11-05

公开(公告)日：2024-11-08

摘要：本发明实施例公开了一种乳腺体模生成方法、装置、设备和介质，其中，方法包括：基于基础乳腺体模生成包含乳腺组织分区的初始三维乳腺体模，其中，所述基础乳腺体模是预设半椭球形状模型；在所述初始三维乳腺体模内部叠加二值化噪声信号，并将叠加噪声信号后的初始三维乳腺体模调整到目标体模尺寸；根据乳腺组织对X射线的衰减系数计算目标尺寸的三维乳腺体模中各组织的像素值并进行赋值，得到目标三维乳腺体模。本发明实施例的技术方案实现了通过数值计算的方式生成任意外部轮廓的大小和形状的三维乳腺体模，可以任意设置腺体组织以及腺体的分布状态，增加了数据的多样性。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：王珊珊; 荣楚誉; 郑海荣; 刘新;

申请日：2021-03-26

公开(公告)日：2024-05-03

摘要：本申请属于计算机技术领域，尤其涉及一种磁共振氧十七代谢成像方法、装置、计算机可读存储介质及终端设备。所述方法包括：获取磁共振氧十七代谢的黄金角径向采样数据，并按照预设的频率分区将所述径向采样数据划分为若干个分区域径向采样数据；使用不同的径向插值网络分别对各个分区域径向采样数据进行处理，得到填补后的径向采样数据；对所述填补后的径向采样数据进行成像处理，得到目标图像。通过本申请，引入不同的径向插值网络分别在各个频率分区上对采样数据进行填补，有效提高了最终的成像精度。…展开更多>>

申请（专利权）人：中国科学院深圳先进技术研究院

发明（设计）人：段君毅; 刘新; 邹超; 万倩; 阳冈汗;

申请日：2024-03-13

公开(公告)日：2024-06-11

摘要：本发明公开了一种氘代蛋氨酸的制备方法。所述制备方法包括：以DL‑同型半胱氨酸硫内酯盐酸盐为底物进行水解反应，得到DL‑同型半胱氨酸；利用所述DL‑同型半胱氨酸与氘代碘甲烷进行氘代反应，得到所述氘代蛋氨酸；所述氘代蛋氨酸的结构式如式I所示。本发明设计全新的两步法合成路线，能够有效降低成本，同时避免了D L‑同型半胱氨酸保存中被氧化的问题；以氘代碘甲烷作为氘源进行氘代反应，大大简化了反应过程步骤，无需昂贵催化剂、还原剂等，且对合成环境的要求大大降低，有利于提高氘代蛋氨酸生产效能，推动氘代蛋氨酸的应用，并证明氘代蛋氨酸可进一步开发诊断脑胶质瘤的磁共振造影剂。…展开更多>>

负责人：刘新

项目开始时间：2019-1-1

项目结束时间：2023-12-1

承担机构：中国科学院深圳先进技术研究院,深圳先进技术研究院,中国科学院深圳市先进技术研究院,现代服务业,中科院深圳先进技术研究院,Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences,SIAT, CAS,South China Sea Institute Oceanology,Chinese Acad Sci, Shenzhen Inst Adv Technol,Shenzhen Institute of Advanced Technology, CAS

基金来源：中国国家自然科学基金委

负责人：刘新

项目开始时间：2016-1-1

项目结束时间：2018-12-31

基金来源：全国哲学社会科学规划办公室

负责人：刘新

项目开始时间：2014-01-01

项目结束时间：2018-12-30

基金来源：中国国家自然科学基金委

负责人：刘新

项目开始时间：2012-01-01

项目结束时间：2016-12-30

基金来源：中国国家自然科学基金委

负责人：刘新

项目开始时间：2011-01-01

项目结束时间：2013-12-30

基金来源：中国国家自然科学基金委

项目申请摘要：针对基于血流散相（FSD）和稳态自由进动（SSFP）技术的非增强磁共振血管成像在图像稳定性、个体化成像方案以及显示迂曲血管存在的问题，本项目探讨SSFP序列因磁场梯度一阶矩（m1）随时间变化所导致的稳态信号减弱、m1值对血流信号抑制程度的影响、以及FSD多方向去相位梯度对复杂血流信号的抑制特性。建立 SSFP序列流动补偿的优化方案、不同个体搜寻最佳m1值的方法以及多方向施加去相位梯度的成像方案。验证基于FSD和SSFP血管成像的临床有效性。本项目的开展，不仅可以显著提高外周血管非增强成像的稳定性和实用性，实现手部和足部动脉的无创性血管成像，而且为进一步发展磁共振血管壁成像提供理论和实验依据。…展开更多>>

D-Val22 containing human big endothelin-1 analog, [D-Val22]Big ET-1⎜-38], inhibits the endothelin converting enzyme.

时间: 2017年12月1日

出处: 5卷7期

被引: 1234

Bovine embryonic stem cells are of potentially big value in transgenic research and studies of lineage commitment and development. Nevertheless, key aspects of the establishment of bovine embryonic stem cells such as the identification of specific pluripotency

研究领域: 生物物理;高分子;生物质能源; …展开更多>>

D-Val22 containing human big endothelin-1 analog, [D-Val22]Big ET-1⎜-38], inhibits the endothelin converting enzyme.

时间: 2017年12月1日

出处: 5卷7期

被引: 1234

研究领域: 生物物理;高分子;生物质能源; …展开更多>>