检索结果-内蒙古大学图书馆

1st MICCAI Challenge Comprehensive Analysis and Computing of Real-World Medical images, CARE 2024 Held in Conjunction with 27th International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Huang, Jinlong Sun, Xiao Wang, Lisheng Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783031870088

Revolutionizing medical image analysis, the Segment Anything Model (SAM) stands out among emerging foundation models, yet its potential in accurately segmenting small, irregular ROIs from multi-center, diverse datasets remains untapped in real-world scenarios. Our study harnesses SAM’s capabilities to address the segmentation intricacies of clinically crucial, yet challenging, features in complex medical imaging. To bridge this gap, we embark on a comprehensive exploration anchored in Foundation models including SegVol and MedSAM, targeting three pivotal challenges: 1) enhancing the generalization of models across diverse medical image modalities and sequences, 2) reinforcing the stability of interactive segmentation, and 3) overcoming the segmentation hurdles posed by minuscule, atypical ROIs. We employ a coarse-to-fine segmentation strategy, using the CARE24 dataset alongside a meticulously publicly available dataset to fine-tune these models for enhanced real-world performance. To boost the stability and precision of interactive segmentation, we devise a retest mechanism, ensuring consistent outcomes in user-guided processes. Furthermore, recognizing the potential of multimodal data, we introduce a fusion strategy, capitalizing on complementary information to improve overall segmentation accuracy and adaptability. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Complicated ROIs Foundation model Multi-center Segment Anything Model (SAM)

来源：评论

学校读者我要写书评

暂无评论

Applications of artificial intelligence to lipid nanoparticle delivery

引用

Particuology 2024年第7期90卷 88-97页

作者： Ye Yuan Yuqi Wu Jiabei Cheng Kaiyuan Yang Yilin Xia Hongguang Wu Xiaoyong Pan Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong UniversityKey Laboratory of System Control and Information ProcessingMinistry of Education of ChinaChina Songjiang Research Institute Songjiang District Central HospitalShanghai Jiao Tong University School of MedicineShanghaiChina

Lipid nanoparticles(LNPs)are nanocarriers composed of four lipid components and can be used for gene therapy,protein replacement,and vaccine ***,LNPs also face several challenges,such as toxicity,immune activation,and low delivery *** overcome these challenges,artificial intelligence can be used to optimize the design and formulation of LNPs,as well as to predict their properties and ***,antibody-targeted conjugation can be used to enhance the specificity and selectivity of LNPs by attaching an antibody that recognizes a specific antigen on the cell surface to LNPs.

关键词： Artificial intelligence Lipid nanoparticles Antibody Targeted conjugation

来源：评论

学校读者我要写书评

暂无评论

Inferior Alveolar Nerve Segmentation in CBCT images Using Connectivity-Based Selective Re-training 2nd

Inferior Alveolar Nerve Segmentation in CBCT Images Using C...

引用

2nd International ToothFairy2: Multi-Structure Segmentation in CBCT Volumes, ToothFairy 2024, 3D Teeth Landmarks Detection Challenge, 3DTeethLand 2024, Semi-supervised Teeth Segmentation, STS 2024 held in conjunction with the 27th International Conference on Medical image Computing and Computer-Assisted Intervention, MICCAI 2024

作者： Liu, Yusheng Xin, Rui Yang, Tao Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783031889769

Inferior Alveolar Nerve (IAN) canal detection in CBCT is an important step in many dental and maxillofacial surgery applications to prevent irreversible damage to the nerve during the procedure. The ToothFairy2023 Challenge aims to establish a 3D maxillofacial dataset comprising both sparse and partially dense labels, with the goal of improving the accuracy of automatic IAN segmentation. In this work, in order to avoid the negative impact brought by sparse labeling, we transform the mixed supervised problem into a semi-supervised problem. Inspired by self-training via pseudo labeling, we propose a selective re-training framework based on IAN connectivity. Our method is quantitatively evaluated on the ToothFairy verification cases, achieving the dice similarity coefficient (DSC) of 0.7956, and 95% hausdorff distance (HD95) of 4.4905, and wining the champion in the competition. Code is available at https://***/GaryNico517/SSL-IAN-Retraining. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Two-Stage Semi-supervised nnU-Net Model for Automated Tooth Segmentation in Panoramic X-Ray images 2nd

A Two-Stage Semi-supervised nnU-Net Model for Automated Too...

引用

作者： Ji, Changkai Liu, Yusheng He, Lanshan Jiang, Yuxian Huang, Chuanyi Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783031889769

Automatic tooth segmentation in 2D panoramic X-ray images is crucial for various applications. Task 1 of the MICCAI STS 2024 Challenge aims to advance automated tooth segmentation techniques by providing datasets comprising labeled and unlabeled panoramic X-ray images. This paper addresses the challenge of limited labeled data by framing the problem as a semi-supervised learning task. We propose a two-stage deep learning model based on nnU-Net. The method first performs quadrant segmentation using one nnU-Net, followed by fine tooth segmentation using another nnU-Net within each quadrant. To effectively utilize unlabeled data, we implement a selective stability-based retraining strategy to generate reliable pseudo-labels. We further enhance model performance through post-processing methods such as connected domain analysis. Quantitative evaluation on the STS 2024 validation set demonstrates that our method achieves strong performance across several metrics (Dice_instance = 79.82%, Dice_image = 94.02%). In the competition’s validation phase, the method was awarded second place, validating its efficacy in automated dental segmentation of panoramic X-ray images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Semi-supervised nnU-Net Framework for Tooth Segmentation in CBCT images 2nd

Two-Stage Semi-supervised nnU-Net Framework for Tooth Segme...

引用

ISBN: (纸本)9783031889769

Automated tooth segmentation in Cone-Beam Computed Tomography (CBCT) images is crucial for various dental applications, including treatment planning and computer-assisted dental prosthesis design. The MICCAI STS 2024 Challenge Task 2 aims to enhance automated tooth segmentation by providing a dataset comprising both labeled and unlabeled CBCT images. This paper addresses the challenge of limited labeled data by reformulating the problem as a semi-supervised learning task. We propose a two-stage deep learning model based on nnU-Net. Our approach initially employs a low-resolution nnU-Net for quadrant segmentation, followed by a full-resolution nnU-Net for fine tooth segmentation within each quadrant. To efficiently utilize unlabeled data, we implement a selective stability-based retraining strategy to generate reliable pseudo-labels. Our method is quantitatively evaluated on the STS 2024 validation set, achieving good performance across various metrics (Dice_instance = 90.74%, Dice_image = 97.70%). The proposed approach achieved one of the highest rankings in the competition’s validation phase, demonstrating its efficacy in automatically segmenting teeth from CBCT images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Revisiting the Benefits of Knowledge Distillation against Adversarial Examples 6

Revisiting the Benefits of Knowledge Distillation against Ad...

引用

6th International Conference on Data Science and Information Technology, DSIT 2023

作者： Li, Jiawen Yang, Jie Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798350304442

Deep neural networks (DNNs) have always been a popular base model in many image classification tasks. However, some recent works suggest that there are some man made images will easily lead DNNs give wrong predictions. These images are generated by adding some invisible perturbations into clean images, which are the so-called adversarial examples. Since they are almost similar to original data but can fool DNNs, adversarial examples can bring the insecurity to many life-critical applications. Adversarial knowledge distillation is a positive defense method to attach improved robustness to the target DNNs against adversarial examples. In distillation, student models are trained by soft labels coming from robust pre-trained teacher networks. However, it is hard for researchers to ensure that supervised information comes from a better teacher model. In this paper, We focus on four potential factors of the teacher that may have an effect to the distillation performance of student model, and investigate whether and when they can boost the model robustness against adversarial attacks. Multiple quantitative experiment illustrate that these factors have impact on the distillation process and these results can be considered to choose a better teacher model. Further studies can focus on the combination of adversarial knowledge distillation and other defense schemes. Empirical results in this paper may also help select proper teacher in new complex distillation tasks. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

A Coarse-to-Fine Ensembling Framework for Head and Neck Tumor and Lymph Segmentation in CT and PET images 1

引用

3rd 3D Head and Neck Tumor Segmentation in PET/CT Challenge, HECKTOR 2022, held in Conjunction with the 25th International Conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2022

作者： Sun, Xiao An, Chengyang Wang, Lisheng Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9783031274206

ISBN: (纸本)9783031274190

Head and neck (H &N) cancer is one of the most prevalent cancers [1]. In its treatment and prognosis analysis, tumors and metastatic lymph nodes may play an important role but their manual segmentations are time-consuming and laborious. In this paper, we propose a coarse-to-fine ensembling framework to segment the H &N tumor and metastatic lymph nodes automatically from Positron Emission Tomography (PET) and Computed Tomography (CT) images. The framework consists of three steps. The first step is to locate the head region in CT images. The second step is a coarse segmentation, to locate the tumor and lymph region of interest (ROI) from the head region. The last step is a fine segmentation, to get the final precise predictions of tumors and metastatic lymph nodes, where we proposed a ensembling refinement model. This framework is evaluated quantitatively with aggregated Dice Similarity Coefficient (DSC) of 0.77782 in the task 1 of the HECKTOR 2022 challenge[2, 3] as team SJTU426. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-structure Segmentation in CBCT images with Adaptive Structure Optimization 2nd

Enhanced Multi-structure Segmentation in CBCT Images with ...

引用

作者： Jiang, Yuxian Liu, Yusheng Ji, Changkai Wang, Lisheng Institute of Image Processing and Pattern Recognition Department of Automation Shanghai Jiao Tong University Shanghai200240 China

ISBN: (纸本)9783031889769

Oral structure segmentation plays a crucial role in facilitating computer-aided orthodontic treatment. While numerous studies have concentrated on specific categories of structures, such as the inferior alveolar nerves, jawbones, and teeth, a comprehensive method for segmenting all structures within the oral cavity has been lacking. The MICCAI ToothFairy2 Challenge seeks to enhance the development of deep learning frameworks and expand the availability of publicly accessible 3D-annotated CBCT datasets. In response to this challenging task, we employed a segmentation network to segment multiple oral structures. Subsequently, we introduced an Adaptive Structure Optimization technique to mitigate the trade-off between missed and false segmentations. Our method was rigorously evaluated on the ToothFairy2 test dataset, yielding a Dice Similarity Coefficient (DSC) of 0.9167 and a 95% Hausdorff Distance (HD95) of 17.5809 mm, winning second place in the competition. Code is available at Oculins/Multi_Oral_Structure. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Multiple oral structures segmentation network structure optimization

来源：评论

学校读者我要写书评

暂无评论

ClusVPR: Efficient Visual Place recognition With Clustering-Based Weighted Transformer

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 1038-1049页

作者： Xu, Yifan Shamsolmoali, Pourya Zareapoor, Masoume Yang, Jie Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai200240 China East China Normal University School of Communication Shanghai200240 China University of York YorkYO10 5DD United Kingdom

Visual place recognition (VPR) is a highly challenging task that has a wide range of applications, including robot navigation and self-driving vehicles. VPR is a difficult task due to duplicate regions and insufficient attention to small objects in complex scenes, resulting in recognition deviations. In this article, we present ClusVPR, a novel approach that tackles the specific issues of redundant information in duplicate regions and representations of small objects. Different from existing methods that rely on convolutional neural networks (CNNs) for feature map generation, ClusVPR introduces a unique paradigm called clustering-based weighted transformer network (CWTNet). CWTNet uses the power of clustering-based weighted feature maps and integrates global dependencies to effectively address visual deviations encountered in large-scale VPR problems. We also introduce the optimized-VLAD (OptLAD) layer, which significantly reduces the number of parameters and enhances model efficiency. This layer is specifically designed to aggregate the information obtained from scale-wise image patches. Additionally, our pyramid self-supervised strategy focuses on extracting representative and diverse features from scale-wise image patches rather than from entire images. This approach is essential for capturing a broader range of information required for robust VPR. Extensive experiments on four VPR datasets show our model's superior performance compared to existing models while being less complex. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A matching-score-based template reconstruction attack

A matching-score-based template reconstruction attack

引用

2024 International Conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2024

作者： Liao, Fengxiang Leng, Lu Guo, Guodong Jiangxi Provincial Key Laboratory of Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang330063 China Ningbo Institute of Digital Twin Eastern Institute of Technology Ningbo315000 China

ISBN: (纸本)9781510689275

Biometric systems, even with high accuracies, commonly suffer from various attacks. In practical applications, some systems directly display the matching scores, or attackers can obtain the matching scores. This paper proposes a novel matching-score-based template reconstruction attack, which reveals that matching scores can leak the spatial neighborhood range of the attacked template, resulting in some potential security and privacy risks. The dissimilarity (matching score) between two real-number templates is measured by the Euclidean distance. A small number of match scores can be obtained by matching the attacked template with a few randomly selected or generated fake templates. An equation set can be established based on the formulae of the matching scores. However, it is difficult to directly solve the quadratic equation set. We skillfully simplify the quadratic equation set into a linear equation set, which obviously reduces the complexity, especially for large-size templates. This novel attack can be extended to other algorithms, and used to evaluate the security and privacy of the related algorithms. © 2025 SPIE.

关键词： Template matching

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：