检索结果-内蒙古大学图书馆

IEEE International Conference on image Processing

作者： Liangjing Shao Benshuang Chen Xinrong Chen Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

In recent years, much achievement have been made in the field of 3D clothed human reconstruction. However, most of researches performed not well for reconstruction from in-the-wild images due to the domain gap between the synthetic images of training datasets and the in-the-wild images. In this study, a modular model, including clothes encoder, body encoder and cloth generator, is proposed to perform 3D clothed human reconstruction from one single-view in-the-wild RGB image. In particular, we introduce the adaptive aggregation of convolution and multi-head attention into the cloth encoder and apply the adjustment of the segmentation at the preprocessing stage. According to experiments on MSCOCO and 3DPW datasets, the proposed method achieves state-of-the-art performance on 3D clothed human reconstruction from in-the-wild images compared with previous works.

关键词： Training Solid modeling image segmentation Adaptation models Three-dimensional displays Convolution Data preprocessing

来源：评论

学校读者我要写书评

暂无评论

REMOTE: Real-time Ego-motion Tracking for Various Endoscopes via Multimodal Visual Feature Learning

arXiv

引用

arXiv 2025年

作者： Shao, Liangjing Chen, Benshuang Zhao, Shuting Chen, Xinrong Academy for Engineering & Technology Fudan University China Shanghai Key Laboratory of Medical Image Computing and Computer-Assisted Intervention Fudan University China

Real-time ego-motion tracking for endoscope is a significant task for efficient navigation and robotic automation of endoscopy. In this paper, a novel framework is proposed to perform real-time ego-motion tracking for endoscope. Firstly, a multi-modal visual feature learning network is proposed to perform relative pose prediction, in which the motion feature from the optical flow, the scene features and the joint feature from two adjacent observations are all extracted for prediction. Due to more correlation information in the channel dimension of the concatenated image, a novel feature extractor is designed based on an attention mechanism to integrate multi-dimensional information from the concatenation of two continuous frames. To extract more complete feature representation from the fused features, a novel pose decoder is proposed to predict the pose transformation from the concatenated feature map at the end of the framework. At last, the absolute pose of endoscope is calculated based on relative poses. The experiment is conducted on three datasets of various endoscopic scenes and the results demonstrate that the proposed method outperforms state-of-the-art methods. Besides, the inference speed of the proposed method is over 30 frames per second, which meets the real-time requirement. The project page is here: *** © 2025, CC BY.

关键词： Endoscopy

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

Exosome-Transmitted miR-224-5p Promotes Colorectal Cancer Cell Proliferation via Targeting ULK2 in p53-Dependent Manner

引用

Biomedical and Environmental Sciences 2024年第1期37卷 71-84页

作者： YANG Le Mei ZHENG Qi LIU Xiao Jia LI Xian Xian Veronica Lim CHEN Qi ZHAO Zhong Hua WANG Shu Yang Department of Pathology School of Basic MedicineFudan UniversityShanghai 200032China Department of Pathology Dunedin School of MedicineUniversity of OtagoDunedin 9054New Zealand Department of Pathology Huashan HospitalFudan UniversityShanghai 200040China Shanghai Cancer Institute Renji HospitalSchool of MedicineShanghai Jiao Tong UniversityShanghai 200127China Teladoc Health Inc Shanghai 200335China Shanghai Medical College Fudan UniversityShanghai 200032China Shanghai Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention Shanghai 200032China

Objective To investigate the role and molecular mechanism of exosomal miR-224-5p in colorectal cancer(CRC).Methods The miR-224-5p expression in CRC patient tissues and cell-derived exosomes was measured by laser capture microdissection and qRT-PCR,***-luciferase reporter gene assay was used to determine the target gene of *** protein expressions of p53 and unc-51 like kinase 2(ULK2)in CRC cells were detected by western *** cytometry was used to detect cell cycle and *** proliferation was measured by CCK8 and EdU *** The miR-224-5p expression was upregulated in CRC tissues and increased progressively with the rise of CRC *** cells secreted extracellular miR-224-5p mainly in an exosome-dependent manner,and then miR-224-5p could be transferred to surrounding tumor cells to regulate cell proliferation in the form of autocrine or ***,ULK2 was characterized as a direct target of miR-224-5p and was downregulated in CRC ***,ULK2 inhibited CRC cell proliferation in a p53-dependent ***,exosome-derived miR-224-5p partially reversed the proliferation regulation of ULK2 on CRC *** Our findings demonstrate that exosome-transmitted miR-224-5p promotes p53-dependent cell proliferation by targeting ULK2 in CRC,which may offer promising targets for CRC prevention and therapy.

关键词： miR-224-5p Exosome ULK2 p53 Cell proliferation Colorectal cancer

来源：评论

学校读者我要写书评

暂无评论

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide image Classification 38

FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Fu, Kexue Luo, Xiaoyuan Qu, Linhao Wang, Shuo Xiong, Ying Maglogiannis, Ilias Gao, Longxiang Wang, Manning Qilu University of Technology Shandong Academy of Sciences Jinan China Digital Medical Research Center School of Basic Medical Sciences Fudan University China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China Fudan University China University of Piraeus Greece Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China

The expensive fine-grained annotation and data scarcity have become the primary obstacles for the widespread adoption of deep learning-based Whole Slide images (WSI) classification algorithms in clinical practice. Unlike few-shot learning methods in natural images that can leverage the labels of each image, existing few-shot WSI classification methods only utilize a small number of fine-grained labels or weakly supervised slide labels for training in order to avoid expensive fine-grained annotation. They lack sufficient mining of available WSIs, severely limiting WSI classification performance. To address the above issues, we propose a novel and efficient dual-tier few-shot learning paradigm for WSI classification, named FAST. FAST consists of a dual-level annotation strategy and a dual-branch classification framework. Firstly, to avoid expensive fine-grained annotation, we collect a very small number of WSIs at the slide level, and annotate an extremely small number of patches. Then, to fully mining the available WSIs, we use all the patches and available patch labels to build a cache branch, which utilizes the labeled patches to learn the labels of unlabeled patches and through knowledge retrieval for patch classification. In addition to the cache branch, we also construct a prior branch that includes learnable prompt vectors, using the text encoder of visual-language models for patch classification. Finally, we integrate the results from both branches to achieve WSI classification. Extensive experiments on binary and multi-class datasets demonstrate that our proposed method significantly surpasses existing few-shot classification methods and approaches the accuracy of fully supervised methods with only 0.22% annotation costs. All codes and models will be publicly available on https://***/fukexue/FAST. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution

arXiv

引用

arXiv 2024年

作者： Duan, Minghong Qu, Linhao Liu, Shaolei Wang, Manning Digital Medical Research Center Fudan University Shanghai China Shanghai Key Lab of Medical Image Computing and Computer Assisted Intervention China

Implicit neural representations have recently demonstrated promising potential in arbitrary-scale Super-Resolution (SR) of images. Most existing methods predict the pixel in the SR image based on the queried coordinate and ensemble nearby features, overlooking the importance of incorporating high-frequency prior information in images, which results in limited performance in reconstructing high-frequency texture details in images. To address this issue, we propose the Local Implicit Wavelet Transformer (LIWT) to enhance the restoration of high-frequency texture details. Specifically, we decompose the features extracted by an encoder into four sub-bands containing different frequency information using Discrete Wavelet Transform (DWT). We then introduce the Wavelet Enhanced Residual Module (WERM) to transform these four sub-bands into high-frequency priors, followed by utilizing the Wavelet Mutual Projected Fusion (WMPF) and the Wavelet-aware Implicit Attention (WIA) to fully exploit the high-frequency prior information for recovering high-frequency details in images. We conducted extensive experiments on benchmark datasets to validate the effectiveness of LIWT. Both qualitative and quantitative results demonstrate that LIWT achieves promising performance in arbitrary-scale SR tasks, outperforming other state-of-the-art methods. The code is available at https://***/dmhdmhdmh/LIWT. Copyright © 2024, The Authors. All rights reserved.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Rethinking Multiple Instance Learning: Developing an Instance-Level Classifier via Weakly-Supervised Self-Training

arXiv

引用

arXiv 2024年

作者： Ma, Yingfan Luo, Xiaoyuan Yuan, Mingzhi Chen, Xinrong Wang, Manning The Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China The Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

Multiple instance learning (MIL) problem is currently solved from either bag-classification or instance-classification perspective, both of which ignore important information contained in some instances and result in limited performance. For example, existing methods often face difficulty in learning hard positive instances. In this paper, we formulate MIL as a semi-supervised instance classification problem, so that all the labeled and unlabeled instances can be fully utilized to train a better classifier. The difficulty in this formulation is that all the labeled instances are negative in MIL, and traditional self-training techniques used in semi-supervised learning tend to degenerate in generating pseudo labels for the unlabeled instances in this scenario. To resolve this problem, we propose a weakly-supervised self-training method, in which we utilize the positive bag labels to construct a global constraint and a local constraint on the pseudo labels to prevent them from degenerating and force the classifier to learn hard positive instances. It is worth noting that easy positive instances are instances are far from the decision boundary in the classification process, while hard positive instances are those close to the decision boundary. Through iterative optimization, the pseudo labels can gradually approach the true labels. Extensive experiments on two MNIST synthetic datasets, five traditional MIL benchmark datasets and two histopathology whole slide image datasets show that our method achieved new SOTA performance on all of them. The code will be publicly available. Impact Statement-MIL is a primary research field within weakly supervised learning and has numerous applications, such as histopathology analysis, video anomaly detection, and drug design. However, current mainstream methods in MIL predominantly rely on bag labels to train the network, consequently overlooking the potential of instance-level supervision information. In our paper, we highlight the

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Ddfp: Data-Dependent Frequency Prompt for Source Free Domain Adaptation of medical image Segmentation

SSRN

引用

SSRN 2024年

作者： Yin, Siqi Liu, Shaolei Wang, Manning Digital Medical Research Center School of Basic Medical Science Fudan University Shanghai200032 China Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention Shanghai200032 China

Domain adaptation aims to address model performance degradation problem under domain gap. In the typical setting of unsupervised domain adaptation, labeled data from source domain and unlabeled data from target domain are used to train a target model. However, access to source domain medical data can be restricted due to privacy policies, in which scenario, the research attention has shifted to source free domain adaptation (SFDA) which only requires a trained source domain model and unlabeled target domain data for adaptation. Existing SFDA methods often utilize domain-dependent image style translation and self-supervision techniques to reduce domain gap and train the target domain model. However, the quality of domain-dependent style translated images and pseudo labels still leaves room for improvement. Moreover, training the entire model during adaptation is suboptimal under limited supervision. In this paper, we propose a novel SFDA framework to overcome these limitations. Specifically, to effectively mitigate the impact of domain gap in the initial training phase, we introduce pre-adaptation to derive a pre-adapted model for target model initialization and generate quality enhanced pseudo labels without introducing additional parameters. Furthermore, we propose a data-dependent frequency prompt to better translate target domain images into a source-like style individually. Subsequently, the style-related layers fine-tuning strategy tailored for SFDA is used to train the target model using the prompted target domain images and pseudo labels. Extensive experiments on cross-modality abdominal and cardiac SFDA segmentation tasks demonstrated that our proposed method outperforms the state-of-the-art baselines. Our code is available online. © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Shape Estimation of Flexible Probe using Spatial-Attention FlexShapeNet

Shape Estimation of Flexible Probe using Spatial-Attention F...

引用

IEEE International Symposium on Applications of Ferroelectrics (ISAF)

作者： Xue Gao Lihong Huang Yuanyuan Wang Yi Guo Department of Electronic Engineering Fudan University Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai China

ISBN: (数字)9798350371901

ISBN: (纸本)9798350371918

Ultrasound imaging with flexible probes requires the knowledge of element array geometry, which is variable and unknown. Here, we propose a spatial-attention shape estimation model, named FlexShapeNet, to estimate accurate element array geometry of flexible probes from radio-frequency (RF) data. A spatial attention (SA) module is introduced to capture deformation information resulting from variations in the shape of the flexible probe, which effectively reduces the significant disparities in shape estimation accuracy among different imaging targets. The delay-and-sum (DAS) beamformer is then used to reconstruct ultrasound images with estimated shape and the raw RF data. Experimental results demonstrate that FlexShapeNet achieves the highest shape estimation accuracy for flexible probes without the need for multiple iterations of beamforming.

关键词： Radio frequency Geometry Accuracy Ultrasonic imaging Shape Deformation Estimation Imaging Arrays Probes

来源：评论

学校读者我要写书评

暂无评论

Chest-Diffusion: A Light-Weight Text-to-image Model for Report-to-CXR Generation

Chest-Diffusion: A Light-Weight Text-to-Image Model for Repo...

引用

IEEE International Symposium on Biomedical Imaging

作者： Peng Huang Xue Gao Lihong Huang Jing Jiao Xiaokang Li Yuanyuan Wang Yi Guo Department of Electronic Engineering Fudan University Shanghai China Key Laboratory of Medical Imaging Computing and Computer Assisted Intervention of Shanghai Shanghai China

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Text-to-image generation has important implications for generation of diverse and controllable images. Several attempts have been made to adapt Stable Diffusion (SD) to the medical domain. However, the large distribution difference between medical reports and natural texts, as well as high computational complexity in common stable diffusion limit the authenticity and feasibility of the generated medical images. To solve above problems, we propose a novel light-weight transformer-based diffusion model learning framework, Chest-Diffusion, for report-to-CXR generation. Chest-Diffusion employs a domain-specific text encoder to obtain accurate and expressive text features to guide image generation, improving the authenticity of the generated images. Meanwhile, we introduce a light-weight transformer architecture as the denoising model, reducing the computational complexity of the diffusion model. Experiments demonstrate that our Chest-Diffusion achieves the lowest FID score 24.456, under the computation budget of 118.918 GFLOPs, which is nearly one-third of the computational complexity of SD.

关键词： Accuracy Computational modeling Noise reduction Text to image computer architecture Transformers Diffusion models

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：