检索结果-内蒙古大学图书馆

A learnable self-supervised task for unsupervised domain adaptation on point cloud classification and segmentation

Frontiers of computer Science 2023年第6期17卷 147-149页

作者： Shaolei LIU Xiaoyuan LUO Kexue FU Manning WANG Zhijian SONG Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032China Digital Medical Research Center School of Basic Medical ScienceFudan UniversityShanghai 200032China

1 Introduction Deep neural networks have exhibited excellent performance in supervised tasks on point clouds,such as classification,segmentation[1]and registration[2].In supervised learning schemes,manual labeling of massive point clouds is needed for model ***,point clouds captured from different scenarios exist inevitable distribution discrepancy,and model trained from one domain always generalize badly in another *** reduce the doamin distribution discrepancy,many studies[3–6]have emerged for point cloud unsupervised domain adaptation(UDA)by learning domain-invariant features,where[5]proposed using adaptive nodes to align the local features between the source and the target domains[3,4],and[6]proposed utilizing self-supervised tasks to help capture highly transferable feature representations.

关键词： point cloud utilizing

来源：评论

学校读者我要写书评

暂无评论

SS-Pro:a simplified siamese contrastive learning approach for protein surface representation

引用

Frontiers of computer Science 2024年第5期18卷 243-245页

作者： Ao SHEN Mingzhi YUAN Yingfan MA Manning WANG Digital Medical Research Center School of Basic Medical ScienceFudan UniversityShanghai 200032China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032China

Protein surface serves as an important representation of protein structure,revealing how protein interacts with other biomolecules to perform its *** forms the basis for pharmaceutical and fundamental biological research[1].Datadriven deep learning methods in protein surface representation face challenges of label scarcity,since labeled data are typically obtained through wet lab experiments.

关键词： revealing representation simplified

来源：评论

学校读者我要写书评

暂无评论

PLTN: Noisy label learning in long-tailed medical images with adaptive prototypes

引用

Neurocomputing 2025年 645卷

作者： Zhiqing He Jie Xu Peng Huang Qin Wang Yuanyuan Wang Yi Guo Department of Biomedical Engineering School of Information Science and Technology Fudan University Shanghai China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

Label noise poses a significant challenge in medical image classification, particularly for minority diseases in long-tailed distribution. Most Noisy Label Learning methods rely on clean sample selection to learn representative patterns. However, the imbalanced data distribution and intra-class variability cause model bias towards head classes at the inter-class level and dominant patterns at the intra-class level. Existing methods show limited performance in handling these biases simultaneously, causing inefficient clean sample selection and hindering minority class training. Thus, we propose PLTN, named P rototype-guided L ong- T ail N oisy Learning, a novel approach that selects comprehensive clean samples from each class and enhances minority class training to improve diagnostic accuracy of rare disease in long tailed medical data. First, Adaptive Multi-Prototype Learning (AMPL) module is designed to enable precise selection of clean samples, especially for minority classes. It achieves this by capturing diverse feature patterns through a dynamic prototype learning approach. The clean samples are then treated as labeled data while the noisy samples are used as unlabeled data in a semi-supervised learning paradigm. Second, we introduce Sharpness-aware Distributional Mixup (SDM) to enhance minority class training. SDM employs distributional mixup to enrich tail classes representations, simultaneously minimizing loss landscape sharpness to enhance model generalization for all classes, benefiting tail classes. Experiments on three typical medical datasets demonstrate that our method outperforms state-of-the-art methods. On HAM10000 dataset with 20 % label noise, we achieve an 80.34 % Macro-F1 score, with notable gains in tail class performance while maintaining head class performance, showing potential for real-world clinical applications.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Evaluation of uncertainty estimation methods in medical image segmentation: Exploring the usage of uncertainty in clinical deployment

引用

computerized medical Imaging and Graphics 2025年 124卷

作者： Shiman Li Mingzhi Yuan Xiaokun Dai Chenxi Zhang Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai 200032 China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention Shanghai 200032 China Digital Medical Research Center Academy for Engineering and Technology Fudan University Shanghai 200032 China

Uncertainty estimation methods are essential for the application of artificial intelligence (AI) models in medical image segmentation, particularly in addressing reliability and feasibility challenges in clinical deployment. Despite their significance, the adoption of uncertainty estimation methods in clinical practice remains limited due to the lack of a comprehensive evaluation framework tailored to their clinical usage. To address this gap, a simulation of uncertainty-assisted clinical workflows is conducted, highlighting the roles of uncertainty in model selection, sample screening, and risk visualization. Furthermore, uncertainty evaluation is extended to pixel, sample, and model levels to enable a more thorough assessment. At the pixel level, the Uncertainty Confusion Metric (UCM) is proposed, utilizing density curves to improve robustness against variability in uncertainty distributions and to assess the ability of pixel uncertainty to identify potential errors. At the sample level, the Expected Segmentation Calibration Error (ESCE) is introduced to provide more accurate calibration aligned with Dice, enabling more effective identification of low-quality samples. At the model level, the Harmonic Dice (HDice) metric is developed to integrate uncertainty and accuracy, mitigating the influence of dataset biases and offering a more robust evaluation of model performance on unseen data. Using this systematic evaluation framework, five mainstream uncertainty estimation methods are compared on organ and tumor datasets, providing new insights into their clinical applicability. Extensive experimental analyses validated the practicality and effectiveness of the proposed metrics. This study offers clear guidance for selecting appropriate uncertainty estimation methods in clinical settings, facilitating their integration into clinical workflows and ultimately improving diagnostic efficiency and patient outcomes.

关键词：

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

Typicality-and instance-dependent label noise-combating:a novel framework for simulating and combating real-world noisy labels for endoscopic polyp classification

引用

Visual computing for Industry,Biomedicine,and Art 2024年第1期7卷 300-315页

作者： Yun Gao Junhu Fu Yuanyuan Wang Yi Guo School of Information Science and Technology Fudan UniversityShanghai 200433China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai 200433China

Learning with noisy labels aims to train neural networks with noisy *** models handle instance-inde-pendent label noise(IIN)well;however,they fall short with real-world *** medical image classification,atypical samples frequently receive incorrect labels,rendering instance-dependent label noise(IDN)an accurate representa-tion of real-world ***,the current IDN approaches fail to consider the typicality of samples,which hampers their ability to address real-world label noise *** alleviate the issues,we introduce typicality-and instance-dependent label noise(TIDN)to simulate real-world noise and establish a TIDN-combating framework to combat label ***,we use the sample’s distance to decision boundaries in the feature space to repre-sent *** TIDN is then generated according to *** establish a TIDN-attention module to combat label noise and learn the transition matrix from latent ground truth to the observed noisy labels.A recursive algorithm that enables the network to make correct predictions with corrections from the learned transition matrix is *** experiments demonstrate that the TIDN simulates real-world noise more closely than the existing IIN and ***,the TIDN-combating framework demonstrates superior classification performance when training with simulated TIDN and actual real-world noise.

关键词： Noisy label Instance-dependent label noise Noisy label simulation Real-world label noise Polyp classification

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

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

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

Surface-based automatic coarse registration of head scans

Surface-based automatic coarse registration of head scans

引用

作者： Li, Fang Song, Zhijian Digital Medical Research Center Fudan University Shanghai200032 China Key Laboratory of Medical Imaging Computing Computer Assisted Intervention of Shanghai Shanghai200032 China

Surface registration is widely used in image-guided neurosurgery to achieve spatial registration between the patient space and the image space. Coarse registration, followed by fine registration, is an important premise to ensure the robustness and efficiency of surface registration. In this paper, a coarse registration algorithm based on the principal axes is proposed to achieve this goal. The extraction of the principal axes relies on the approximated surface with an adaptive Gaussian kernel, the width of which is consistent with neighborhood relation so that it is applicable for various scanning data. Determining the corresponding centers of translation is another problem for aligning different scanning data, which is solved through heuristics. Six pairs of points on two surfaces with the farthest projections on the principal axes were regarded as the candidates of translation centers, and then through tentative alignments of local regions around them, a pair of candidates with the minimum registration error was selected as the optimal translation centers. Automatic registration of two scans of a head phantom is presented in this paper. Experimental results confirmed the robustness of the algorithm and its feasibility in clinical applications. © 2014 - IOS Press and the authors.

关键词： Neurosurgery

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：