检索结果-内蒙古大学图书馆

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

Decoupled deep hough voting for point cloud registration

引用

Frontiers of computer Science 2024年第2期18卷 147-155页

作者： Mingzhi YUAN Kexue FU Zhihao LI Manning WANG Digital Medical Research Center School of Basic Medical SciencesFudan UniversityShanghai 200032China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032China

Estimating rigid transformation using noisy correspondences is critical to feature-based point cloud ***,a series of studies have attempted to combine traditional robust model fitting with deep *** them,DHVR proposed a hough voting-based method,achieving new state-of-the-art ***,we find voting on rotation and translation simultaneously hinders achieving better ***,we proposed a new hough voting-based method,which decouples rotation and translation ***,we first utilize hough voting and a neural network to estimate *** based on good initialization on rotation,we can easily obtain accurate rigid *** experiments on 3DMatch and 3DLoMatch datasets show that our method achieves comparable performances over the state-of-the-art *** further demonstrate the generalization of our method by experimenting on KITTI dataset.

关键词： point cloud registration robust model fitting deep learning hough voting

来源：评论

学校读者我要写书评

暂无评论

VesselMamba: 3D vessel segmentation in CTA images using Mamba with enhanced Spatial-Channel Attention

引用

Biomedical Signal Processing and Control 2025年 110卷

作者： Ziyue Xie Xiaoquan Huang Shiyao Chen Yonghong Shi Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai 200032 China Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention Shanghai 200032 China Department of Gastroenterology and Hepatology Zhongshan Hospital Fudan University Shanghai 200032 China

3D vessel segmentation in Computed Tomography Angiography (CTA) is crucial yet challenging due to the complex, multi-scale, and elongated branching structure of human vasculature. Accurate modeling requires capturing both long-range dependencies and multi-scale information inherent in vascular networks. While deep neural networks like CNNs and Vision Transformers (ViTs) have demonstrated progress, they often face challenges balancing global receptive field capture with computational efficiency. To address these limitations, we propose VesselMamba, a novel 3D vessel segmentation framework based on Mamba, an approach for modeling long-range dependencies with linear complexity. VesselMamba integrates parallel Mamba blocks in the encoder to efficiently capture vascular continuity and long-range dependencies. Additionally, the encoder is enhanced with a Spatial-Channel Attention with Spatial Pyramid Pooling (SCASPP) module to effectively model multi-scale information and optimize the integration of global and local features, significantly improving segmentation precision. Furthermore, a composite loss function that combines the clDice loss with traditional cross-entropy and Dice losses is employed to improve the connectivity of segmented vessels. This reduces fragmentation and artifacts, leading to more reliable segmentations. Comprehensive ablation studies on private and public datasets demonstrate the complementary nature and effectiveness of the proposed modules. Experimental results show that VesselMamba achieves state-of-the-art performance in CTA vessel segmentation tasks, outperforming existing methods and providing a robust tool for clinical diagnosis and research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ultrasonic Backscatter Instrument for Cancellous Bone Evaluation in Neonates

引用

Engineering 2015年第3期1卷 336-343页

作者： Chengcheng Liu Rong Zhang Ying Li Feng Xu Dean Ta Weiqi Wang Department of Electronic Engineering Fudan University Department of Neonatology Children’s Hospital of Fudan University Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention (MICCAI) of Shanghai

Ultrasonic backscatter technique has shown promise as a noninvasive cancellous bone assessment tool. A novel ultrasonic backscatter bone diagnostic （UBBD） instrument and an in vivo application for neonatal bone evaluation are introduced in this study. The UBBD provides several advantages, including noninvasiveness, non- ionizing radiation, portability, and simplicity. In this study, the backscatter signal could be measured within 5 s using the UBBD. Ultrasonic backscatter measurements were performed on 467 neonates （268 males and 199 females） at the left calcaneus. The backscatter signal was measured at a central frequency of 3.5 MHz. The delay （-/-1） and duration （7-2） of the backscatter signal of interest （SOl） were varied, and the apparent integrated backscatter （AIB）, frequency slope of apparent backscatter （FSAB）, zero frequency intercept of apparent backscatter （FIAB）, and spectral centroid shift （SCS） were calculated. The results showed that the SOl selection had a direct influence on cancellous bone evaluation. The AIB and FIAB were positively correlated with the gestational age （｜R｜ up to 0.45, P 〈 0.001） when -/-1 was short （〈 8 μS）, while negative correlations （｜R｜ up to 0.56, P 〈 0.001） were commonly observed for T1 〉 10 IJS. Moderate positive correlations （IRI up to 0.45, P 〈 0.001） were observed for FSAB and SCS with gestational age when 71 was long （〉 10 μs）. The 7-2 mainly introduced fluctuations in the observed correlation coefficients. The moderate correlations observed with UBBD demonstrate the feasibility of using the backscatter signal to evaluate neonatal bone status. This study also proposes an explicit standard for in vivo SOl selection and neonatal cancellous bone assessment.

关键词： ultrasonic backscatter cancellous bone evaluation signal of interest （SOI） backscatter instrument neonatal bone status

来源：评论

学校读者我要写书评

暂无评论

An efficient dual-branch framework via implicit self-texture enhancement for arbitrary-scale histopathology image super-resolution

引用

Scientific Reports 2025年第1期15卷 1-18页

作者： Minghong Duan Linhao Qu Manning Wang Chenxi Zhang Zhijian Song Zhiwei Yang Digital Medical Research Center School of Basic Medical Sciences Fudan University Shanghai 200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai 200032 China Academy for Engineering and Technology Fudan University Shanghai 200433 China

High-quality whole-slide scanning is expensive, complex, and time-consuming, thus limiting the acquisition and utilization of high-resolution histopathology images in daily clinical work. Deep learning-based single-image super-resolution (SISR) techniques provide an effective way to solve this problem. However, the existing SISR models applied in histopathology images can only work in fixed integer scaling factors, decreasing their applicability. Though methods based on implicit neural representation (INR) have shown promising results in arbitrary-scale super-resolution (SR) of natural images, applying them directly to histopathology images is inadequate because they have unique fine-grained image textures different from natural images. Thus, we propose an Implicit Self-Texture Enhancement-based dual-branch framework (ISTE) for arbitrary-scale SR of histopathology images to address this challenge. The proposed ISTE contains a feature aggregation branch and a texture learning branch. We employ the feature aggregation branch to enhance the learning of the local details for SR images while utilizing the texture learning branch to enhance the learning of high-frequency texture details. Then, we design a two-stage texture enhancement strategy to fuse the features from the two branches to obtain the SR images. Experiments on publicly available datasets, including TMA, HistoSR, and the TCGA lung cancer datasets, demonstrate that ISTE outperforms existing fixed-scale and arbitrary-scale SR algorithms across various scaling factors. Additionally, extensive experiments have shown that the histopathology images reconstructed by the proposed ISTE are applicable to downstream pathology image analysis tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

STCA-Net: Multi-channel ECG Space-Time-Channel Attention Model for Noninvasive Prediction of Catheter Ablation in Atrial Fibrillation 3

STCA-Net: Multi-channel ECG Space-Time-Channel Attention Mod...

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Zhong, Gaoyan Liu, Sen Wang, Yueyi Yang, Cuiwei Fudan University Center for Biomedical Engineering Shanghai China The Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Atrial Fibrillation (AF) remains a high recurrence rate after Catheter Ablation (CA). It is of certain clinical significance to predict the recurrence of AF before CA using preoperative electrocardiogram (ECG) signals. The Body Surface Potential Mapping Signals (BSPMs) can be processed into Three-dimensional (3D) video frame signals using isopotential map. By applying space, time and channel attention to emphasize meaningful features, we proposed the space-time-channel attention module (STCA-Net) for large-scale supervised learning. Compare with C3D-Net, the experiment of 14 patients collected in the clinic shows that C3D-Net with space-time-channel attention (STCA) can achieve better performance, and can achieve 0.858 accuracy for the experiment of identifying patients' recurrence. The experimental results show that STCA-Net contributes to a good prediction of CA in AF. © 2022 IEEE.

关键词： Electrocardiograms

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

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

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：