检索结果-内蒙古大学图书馆

High total variation-based method for sparse-view photoacoustic reconstruction

Chinese Optics Letters 2014年第11期12卷 81-85页

作者：张晨汪源源 Department of Electronic Engineering Fudan University Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention

We propose a novel method by combining the total variation（TV） with the high-degree TV（HDTV） to improve the reconstruction quality of sparse-view sampling photoacoustic imaging（PAI）. A weighing function is adaptively updated in an iterative way to combine the solutions of the TV and HDTV minimizations. The fast iterative shrinkage/thresholding algorithm is implemented to solve both the TV and the HDTV minimizations with better convergence rate. Numerical results demonstrate the superiority and efficiency of the proposed method on sparse-view PAI. In vitro experiments also illustrate that the method can be used in practical sparse-view PAI.

关键词： Digital television High definition television Numerical methods

来源：评论

学校读者我要写书评

暂无评论

Diffusion Model with Self-supervised Training for Subject-aware Photoplethysmography Recovery

Diffusion Model with Self-supervised Training for Subject-aw...

引用

2023 IEEE Biomedical Circuits and Systems Conference, BioCAS 2023

作者： Wang, Daomiao Hu, Qihan Feng, Xujian Yang, Cuiwei Fudan University Center for Biomedical Engineering School of Information Science and Technology Shanghai China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

ISBN: (纸本)9798350300260

Photoplethysmography (PPG) has emerged as a promising technology for wearable personal healthcare due to its non-invasive and cost-effective nature. However, owing to the vulnerability to various noise, the useful PPG signals are few and the usability of PPG-based systems are limited. In this paper, we address the challenge of recovering extremely corrupted PPG waveforms with severe distortions, which lead to missing data. Specifically, we propose a novel diffusion-based framework that incorporates remaining values and subject-aware embedding, along with a self-supervised generative training strategy. Extensive experiments were performed on two datasets under three missing rates and two missing patterns. Our proposed model achieves significant improvements of nearly 100% over existing imputation models on quantitative metrics, and together with the visualization, demonstrating its effectiveness for data distribution generation and corrupted PPG restoration. Our proposed method also provides a new perspective for PPG denoising. © 2023 IEEE.

关键词： Deep generative model Diffusion model Motion artifact Photoplethysmography Self-supervised training

来源：评论

学校读者我要写书评

暂无评论

Interoperative fundus image and report sharing in compliance with integrating the healthcare enterprise conformance and web access to digital imaging and communication in medicine persistent object protocol

引用

International Journal of Ophthalmology(English edition) 2013年第6期6卷 879-883页

作者： Hui-Qun Wu Zheng-Min Lv Xing-Yun Geng Kui Jiang Le-Min Tang Guo-Min Zhou Jian-Cheng Dong Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention(MICCAI) of Shanghai Department of Medical Informatics Medical School of Nantong University Department of Medical Image Engineering Medical School of Nantong University Department of Anatomy Histology and EmbryologySchool of Basic Medical Sciences

AIM:To address issues in interoperability between different fundus image systems,we proposed a web eyepicture archiving and communication system(PACS)framework in conformance with digital imaging and communication in medicine(DICOM)and health level 7(HL7)protocol to realize fundus images and reports sharing and communication through ***:Firstly,a telemedicine-based eye care work flow was established based on integrating the healthcare enterprise(IHE)Eye Care technical ***,a browser/server architecture eye-PACS system was established in conformance with the web access to DICOM persistent object(WADO)protocol,which contains three ***:In any client system installed with web browser,clinicians could log in the eye-PACS to observe fundus images and *** internet mail extensions(MIME)type of a structured report is saved as pdf/html with reference link to relevant fundus image using the WADO syntax could provide enough information for *** functions provided by open-source Oviyam could be used to query,zoom,move,measure,view OICOM fundus ***:Such web eye-PACS in compliance to WADO protocol could be used to store and communicate fundus images and reports,therefore is of great significance for teleophthalmology.

关键词： picture archiving and communication system teleophthalmology integrating the healthcare enterprise web access to DICOM persistent object

来源：评论

学校读者我要写书评

暂无评论

Research of an electromagnetic tracking method based on two electrically-controlled magnetic sources

Research of an electromagnetic tracking method based on two ...

引用

IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2015

作者： Sha, Min Wang, Yifeng Ding, Ning Fang, Zuxiang Wu, Xiaomei Department of Electronic Engineering Fudan University Shanghai China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai China

ISBN: (纸本)9781479919796

This paper presents an electromagnetic tracking method based on two electrically-controlled magnetic sources. Each source consists of three mutual orthogonal coils. The method can skillfully determine the rotation angles of the maximum magnetic flux density vector (MMFD V) generated by a magnetic source according to the Biot-Savart Law. Then the position of the sensor can be calculated with a noniterative geometrical algorithm in real time. Simulation results demonstrate a good performance of this method. © 2015 IEEE.

关键词： Finite element method

来源：评论

学校读者我要写书评

暂无评论

Automated brain tumor segmentation in magnetic resonance imaging based on sliding-window technique and symmetry analysis

引用

Chinese medical Journal 2014年第3期127卷 462-468页

作者： Lian Yanyun Song Zhijian Digital Medical Research Center Shanghai Medical School Fudan University Shanghai 200032 China Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention

Background Brain tumor segmentation from magnetic resonance imaging （MRI） is an important step toward surgical planning,treatment planning,monitoring of ***,manual tumor segmentation commonly used in clinic is time-consuming and challenging,and none of the existed automated methods are highly robust,reliable and efficient in clinic *** accurate and automated tumor segmentation method has been developed for brain tumor segmentation that will provide reproducible and objective results close to manual segmentation *** Based on the symmetry of human brain,we employed sliding-window technique and correlation coefficient to locate the tumor *** first,the image to be segmented was normalized,rotated,denoised,and ***,through vertical and horizontal sliding-windows technique in turn,that is,two windows in the left and the right part of brain image moving simultaneously pixel by pixel in two parts of brain image,along with calculating of correlation coefficient of two windows,two windows with minimal correlation coefficient were obtained,and the window with bigger average gray value is the location of tumor and the pixel with biggest gray value is the locating point of *** last,the segmentation threshold was decided by the average gray value of the pixels in the square with center at the locating point and 10 pixels of side length,and threshold segmentation and morphological operations were used to acquire the final tumor *** The method was evaluated on 3D FSPGR brain MR images of 10 *** a result,the average ratio of correct location was 93.4％ for 575 slices containing tumor,the average Dice similarity coefficient was 0.77 for one scan,and the average time spent on one scan was 40 *** An fully automated,simple and efficient segmentation method for brain tumor is proposed and promising for future clinic *** coefficient is a new and effective feature for tumor locati

关键词： segmentation magnetic resonance imaging brain tumor sliding-window correlation coefficient

来源：评论

学校读者我要写书评

暂无评论

The virtual endoscope of neurosurgery used for transnasal approach

引用

9th International Symposium on Linear Drives for Industry Applications, LDIA 2013

作者： Mo, Jun Cong Yao, De Min Digital Medical Research Center of Shanghai Medical College Fudan University Shanghai 200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032 China

ISBN: (纸本)9783037858639

This paper presents and implements an automatic roaming and fast virtual endoscopic neurosurgery system for transsexual approach, which can be compatible with the fiber-optic endoscopic transnasal approach in the skull base surgery, and accurately locate the position and their mutual relations among the lesions, tumors and surrounding vital anatomical structures. The system uses a multithreaded RayCasting volume-rendering algorithm based on the graphics processor (GPU). It reconstructs the nasal three-dimensional structure in the skull base surgery, and optimizes the centerline extraction that can be carried out automatically. In real-time display, it improves the translucent rendering optical model, taking into account lighting model important parameter-the image gradient translucent degree of non-linear effects, and can fully display the skull surface and internal implied the interface and internal details. © (2013) Trans Tech Publications, Switzerland.

关键词： Neurosurgery

来源：评论

学校读者我要写书评

暂无评论

A Feasible Way to Assess the Lower Extremity Motor Function of Stroke Patients - A Preliminary Study 15

A Feasible Way to Assess the Lower Extremity Motor Function ...

引用

15th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics, CISP-BMEI 2022

作者： Liu, Sen Xie, Hongyu Yuan, Han Tian, Jing Yang, Cuiwei Wu, Yi Center for Biomedical Engineering Fudan University Shanghai China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai China The Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

ISBN: (数字)9781665488877

ISBN: (纸本)9781665488877

Accurate assessment of the mobility of stroke patients is crucial to their rehabilitation management. In order to quantify the lower extremity motor function in stroke sufferers, two tasks, toe tapping and knee flexion and extension, were designed based on the Brunnstrom approach. In this work, five hemiplegic patients in Brunnstrom stage III or IV were recruited. Acceleration signals under different tasks were recorded using tri-axial accelerometers, which were placed at the arches of the feet. Various kinematic parameters were then calculated, and a statistical test was conveyed to investigate the correlations between Brunnstrom stages and the features. The results showed that in the toe tapping task, the dominant frequency of the y-axis and the proportion of signal power in specific frequency band of the x-axis were significantly higher in stage III than in stage IV. On the contrary, the standard deviation and the skewness of the y-axis were lower in stage III. Besides, there were also significant differences in the amplitude of knee flexion between cohorts at different Brunnstrom stages. It is expected that the findings of this study would be helpful for the monitoring and rehabilitation of stroke patients. © 2022 IEEE.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Intelligent Evaluation of the Course of Atrial Fibrillation Using Transfer Learning 15

Intelligent Evaluation of the Course of Atrial Fibrillation ...

引用

15th International Congress on Image and Signal Processing, Biomedical Engineering and Informatics, CISP-BMEI 2022

作者： Sun, Chen Li, Chunpu Huo, Hongye Zhong, Gaoyan Liu, Sen Wang, Aiguo Deng, Xintao Yang, Cuiwei Fudan University Center for Biomedical Engineering Shanghai China Xinghua City People's Hospital Department of Cardiology Jiangsu China The Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

ISBN: (数字)9781665488877

ISBN: (纸本)9781665488877

Atrial fibrillation (AF) is the most common chronic cardiovascular disease. As the disease progresses, AF could have various impact on the quality of life and the health of patients. The scientific management of AF depends on the development of targeted therapeutic measures according to the disease course. In view of the noninvasiveness and convenience of electrocardiogram (ECG), this study attempted to assess the course of AF based on standard 12-lead ECG. Therefore, based on transfer learning, we used MobileNetV2 to achieve automatic grading of AF treatment. By taking 12-lead ECG images of patients with mild and severe AF as network input, the pre-trained model was retrained to recognize different courses. The results show that our proposed method exhibits excellent performance with accuracy of 84.1 %, precision of 86.5%, recall of 83.1%, specificity of 85.3%, and F1-score of 84.8%. Our study provides a feasible way of assessing the course of AF and is of great significance to promote the graded diagnosis and treatment of AF. © 2022 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Forebrain excitatory neuron-specific loss of Brpf1 attenuates excitatory synaptic transmission and impairs spatial and fear memory

引用

Neural Regeneration Research 2024年第5期19卷 1133-1141页

作者： Baicheng Zhao Hang Zhang Ying Liu Gaoyu Zu Yuxiao Zhang Jiayi Hu Shuai Liu Linya You Department of Human Anatomy&Histoembryology School of Basic Medical SciencesFudan UniversityShanghaiChina Shanghai Key Laboratory of Brain Functional Genomics(Ministry of Education) Affiliated Mental Health Center(ECNU)School of Psychology and Cognitive ScienceEast China Normal UniversityShanghaiChina Shanghai Changning Mental Health Center ShanghaiChina NYU-ECNU Institute of Brain and Cognitive Science at NYU Shanghai ShanghaiChina Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai ShanghaiChina

Bromodomain and plant homeodomain(PHD)finger containing protein 1(Brpf1)is an activator and scaffold protein of a multiunit complex that includes other components involving lysine acetyltransferase(KAT)6A/6B/***1,KAT6A,and KAT6B mutations were identified as the causal genes of neurodevelopmental disorders leading to intellectual *** previous work revealed strong and specific expression of Brpf1 in both the postnatal and adult forebrain,especially the hippocampus,which has essential roles in learning and ***,we hypothesized that Brpf1 plays critical roles in the function of forebrain excitatory neurons,and that its deficiency leads to learning and memory *** test this,we knocked out Brpf1 in forebrain excitatory neurons using *** found that Brpf1 deficiency reduced the frequency of miniature excitatory postsynaptic currents and downregulated the expression of genes Pcdhgb1,Slc16a7,Robo3,and Rho,which are related to neural development,synapse function,and memory,thereby damaging spatial and fear memory in *** findings help explain the mechanisms of intellectual impairment in patients with BRPF1 mutation.

关键词： behavioral test Brpf1 CAMKIIa-Cre intellectual disability miniature excitatory postsynaptic current mRNA-Seq

来源：评论

学校读者我要写书评

暂无评论

Dual Attention Poser: Dual Path Body Tracking Based on Attention

Dual Attention Poser: Dual Path Body Tracking Based on Atten...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Di, Xinhan Dai, Xiaokun Zhang, Xinkang Chen, Xinrong Fudan Universiry Academy for Engineering&Technology China Deepearthgo Fudan University Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention China

ISBN: (纸本)9798350302493

Currently, mixed reality head-mounted displays tracking the full body of users is an important human-computer interaction mode through the pose of the head and the hands. Unfortunately, users' virtual representation and experience is limited due to high reconstruction error when simple transformer network architecture is applied. In this paper, we present a novel model, named Dual Attention Poser, which can learn the whole body reconstruction at a high accuracy. The proposed model consists of three key modules. Among them, dual-path attention encoder is designed to extract feature of the sparse signals. Cross attention mixer module enable the fusion of representation in the double path. Attention-gated-mlp decoder is applied to decode the hidden feature from the sparse input through attention gate. Test results on the AMASS dataset show that Dual Attention Poser can reduce the error by up to 18.2% in comparison with the state-of-the-art results. © 2023 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：