检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Lai, Haoran Jiang, Zihang Yao, Qingsong Wang, Rongsheng He, Zhiyang Tao, Xiaodong Wei, Wei Lv, Weifu Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China Stanford University Palo AltoCA94305 United States Medical Business Department iFlytek Co.Ltd. Anhui Hefei230088 China The First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230001 China Department of Radiology The First Affiliated Hospital of USTC Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230001 China Suzhou Institute for Advance Research USTC Jiangsu Suzhou215123 China State Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China Anhui Hefei230026 China Institute of Computing Technology CAS Beijing100190 China

3D medical images such as Computed tomography (CT) are widely used in clinical practice, offering a great potential for automatic diagnosis. Supervised learning-based approaches have achieved significant progress but rely heavily on extensive manual annotations, limited by the availability of training data and the diversity of abnormality types. Vision-language alignment (VLA) offers a promising alternative by enabling zero-shot learning without additional annotations. However, we empirically discover that the visual and textural embeddings after alignment endeavors from existing VLA methods form two well-separated clusters, presenting a wide gap to be bridged. To bridge this gap, we propose a Bridged Semantic Alignment (BrgSA) framework. First, we utilize a large language model to perform semantic summarization of reports, extracting high-level semantic information. Second, we design a Cross-Modal Knowledge Interaction (CMKI) module that leverages a cross-modal knowledge bank as a semantic bridge, facilitating interaction between the two modalities, narrowing the gap, and improving their alignment. To comprehensively evaluate our method, we construct a benchmark dataset that includes 15 underrepresented abnormalities as well as utilize two existing benchmark datasets. Experimental results demonstrate that BrgSA achieves state-of-the-art performances on both public benchmark datasets and our custom-labeled dataset, with significant improvements in zero-shot diagnosis of underrepresented abnormalities. © 2025, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Cdunet: A U-Shaped Encoder-Decoder Network with Channel Attention Block and Dynamic Feature Extraction Block for Ldct Denoising

SSRN

引用

SSRN 2024年

作者： Li, Minghao Teng, Yueyang Zhou, Jie Li, Mingrui Zhu, Ruiming Wang, Haoran College of Medicine and Biological Information Engineering Northeastern University Shenyang110169 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110169 China

Background and Objective: Computer tomography (CT) has become an important tool of clinical diagnosis. However, X-ray radiation related to CT can cause harm to patients. Low-dose CT (LDCT) can reduce radiation, however it can bring noise. How to remove noise from LDCT is a worthwhile research topic. In recent years, deep learning has shown outstanding performance in the field of LDCT ***: This article proposes a U-shaped encoder-decoder network CDUNet with channel attention block (CAB) and dynamic feature extraction block (DFEB). The CAB assigns different weights to feature maps to better utilize multi-channel information. The DFEB uses CondConv, which is able to respond differently to different inputs. When processing CT images, DEFB can perform targeted processing on different CT slices and different parts within each slice to achieve better feature extraction. At the same time, we also use the Sobel operator to calculate the gradient of the image, combining gradient loss with Mean Square Error (MAE) loss to alleviate the smoothing problem and restore the structural information of the image ***: The experiments on the 2016 NIH-AAPM-Mayo Clinic LDCT Grand Challenge show that our method has better results compared with state-of-the-art (SOTA) methods. Specifically, our method not only has the best visual effects, but also outperforms other algorithms in terms of evaluation ***: Experiments shows that our method is reasonable and effective. The code is available at https://***/xxxxxxmmmmmm/CDUNet. © 2024, The Authors. All rights reserved.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

An application of circumscribed circle filter in the multi-stencils fast marching method 12

An application of circumscribed circle filter in the multi-s...

引用

27th Annual ACM Symposium on Applied computing, SAC 2012

作者： Liu, Hong Hung, Chih-Cheng Hu, Huaifei Yu, Mali Song, Enmin School of Computer Science Huazhong University of Science and Technology Wuhan China Key Laboratory of Education Ministry for Image Processing and Intelligent Control Wuhan Hubei 430074 China School of Computing and Software Engineering Southern Polytechnic State University Marietta GA 30060 United States

ISBN: (纸本)9781450308571

We develop an effective method for improving the segmentation result based on the Multi-Stencils Fast Marching method (MSFM). In MSFM, the gradient information of the image plays a vital role for calculating edges. It is straightforward to obtain the edge of good quality images;however, MSFM may not have robust edge maps available for images with spurious edges. Thus, a special multi-direction circumscribed circle filter is proposed to calculate the image gradient information which is then used in the MSFM. Using the new gradient information, better image contours can be obtained with MSFM. The size of the radius used in our circle filter is constant even the standard deviation of zero-mean Gaussian noise changes while the parameters of mean filter and Canny filter for gradient computation have to be correctly selected according to different noisy images. Our proposed method shows that it is effective through the experiments of image segmentation. © 2012 ACM.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

The Effect of The Number of Sensor Coils on Sensitivity in Electromagnetic Tomography 2020

The Effect of The Number of Sensor Coils on Sensitivity in E...

引用

The Fourth International Symposium on image computing and Digital Medicine

作者： Siqi Xu Qian Zhao Liu Li Nan Li Wenjun Tan Shenyang Normal University China Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education China

ISBN: (纸本)9781450389686

Electromagnetic tomography (EMT) is a process tomography based on the principle of electromagnetic induction. It has the advantages of non-intrusive, non-contact and low harm. In the process of image reconstruction, the sensitivity matrix reflects the influence of tiny disturbance on the measured value, which is an important index of image quality. Base on the traditional "O" sensor array structure in this article, Comsol Multiphysics finite element simulation software is used to divide the measured field into several tiny elements. A simulated perturbation method is used to investigate the effect of the number of EMT sensors' midline coils on sensitivity. The sensitivity matrix of sensor arrays with 4 coils ,8 coils ,12 coils ,16 coils and 20 coils is compared by using the method of separation variables. The sensitivity matrix of different coils is imaged by Matlab software. Through comparative analysis, it is concluded that the sensitivity band shape of the coil in the same position is same in different models. All of them are distributed along the arc type between the excitation and detection coils, which presents the middle strong and gradually weakens to the outside. With the increase of the number of coils, the sensitivity band is widened, but the sensitivity value of the central part is slightly weakened. According to this characteristic, it lays a foundation for the practical application of EMT technology and image reconstruction.

关键词： electromagnetic tomography sensitivity sensor coil finite element

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Rotation Learning for 3D Segmentation on Nasopharyngeal Carcinoma MRI images

Self-Supervised Rotation Learning for 3D Segmentation on Nas...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Li, Changtai Jiang, Ruohui Yin, Shihua Yang, Jinzhu Ban, Xiaojuan University of Science and Technology Beijing Beijing Advanced Innovation Center for Materials Genome Engineering School of Intelligence Science and Technology Beijing China University of Science and Technology Beijing School of Intelligence Science and Technology Beijing China Second Affiliated Hospital of Guangxi Medical University Nanning China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang China

ISBN: (纸本)9798350337488

Segmenting the tumors of nasopharyngeal carcinoma (NPC) in Magnetic Resonance Imaging (MRI) images is critical for its diagnosis and treatment. In medical image segmentation, it is vital to exploit the rich information contained in 3D sliced images. However, the precise identification and location of lesion regions often require plenty of labels. To alleviate this situation, in this article, we propose 3DRotNPC, a framework based on a tailored Self-Supervised Learning (SSL) strategy, to accurately segment tumor regions for NPC under the circumstance of label limitation. To learn the rich 3D spatial and geometric nature of MRI images in a Self-Supervised way, the proxy task of randomly selecting and rotating images in consecutively sliced data is designed. After the SSL pre-training stage, the learned parameters of the Convolutional Neural Networks (CNNs) based model are transferred to adapt the downstream segmentation task. We verify the capability of 3DRotNPC on the NPC tumor dataset which is collected and curated from the clinical treatment in the representative hospital. Extensive experiments demonstrate that our approach delivers considerable gains in downstream 3D voxel segmentation, especially with a 10% to 50% number of labels. © 2023 IEEE.

关键词： 3D tumor segmentation MRI image nasopharyngeal carcinoma Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Measure optimized cost-sensitive neural network ensemble for multiclass imbalance data learning

Measure optimized cost-sensitive neural network ensemble for...

引用

International Conference on Hybrid intelligent Systems (HIS)

作者： Peng Cao Dazhe Zhao Osmar Zaiane Key Laboratory of Medical Image Computing of Ministry of Education Northeastern University Shenyang China Computing Science University of Alberta Edmonton Canada

The performance of traditional classification algorithms can be limited on imbalanced datasets. In recent years, the imbalanced data learning problem has drawn significant interest. In this work, we focus on designing modifications to neural network, in order to appropriately tackle the problem of multiclass imbalance. We propose a hybrid method that combines two ideas: diverse random subspace ensemble learning with evolutionary search, to improve the performance of neural network on multiclass imbalanced data. An evolutionary search technique is utilized to optimize the misclassification cost under the guidance of imbalanced data measures. Moreover, the diverse random subspace ensemble employs the minimum overlapping mechanism to provide diversity so as to improve the performance of the learning and optimization of neural network. We have demonstrated experimentally using UCI datasets that our approach can achieve better result than state-of-the-art methods for imbalanced data.

关键词： Artificial neural networks Annealing Glass Testing Radio frequency

来源：评论

学校读者我要写书评

暂无评论

Generating Post-healing images of Skin Diseases Based on an Adversarial Self-coding Generator 2nd

Generating Post-healing Images of Skin Diseases Based on an ...

引用

2nd International Conference on image, Vision and intelligent Systems, ICIVIS 2022

作者： Li, Yaning Chen, Yiqiang Yang, Xiaodong Cai, Hong University of Jinan Shandong Jinan250024 China Shandong Academy of Intelligent Computing Technology Shandong Jinan250102 China Beijing Key Laboratory of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Science Beijing100086 China Department of Dermatology Air Force Medical Center PLA Beijing100142 China

ISBN: (纸本)9789819909223

Goal: In recent years, the rapid development of computer vision and deep learning has driven the improvement of new technologies in medical imaging, while applications in various aspects have emerged. Regarding dermatology, which is an important branch of medical imaging technology, the techniques surrounding it are currently focused on lesion segmentation, identification, and classification of benign and malignant cells in pathological sections. we explore a post-healing image generation method based on dermatological diseases to fill the current situation where the field is relatively under-researched in terms of post-healing. Methods: In this work, the ISIC 2018 dataset is used as our object to be recovered, and the U-net neural network is used as the network model of the segmentation module to segment the healthy skin cell region and the focal cell region by setting the threshold region. The erosion module is used to obtain the area to be filled for this lesion, thus simulating the different stages of healing. Finally, images are generated by a VAE/GAN-based adversarial autoencoder. Conclusion: Our proposed method can generate more realistic post-healing images of skin diseases compared with the VAE and GAN methods. Significance: This work explores the application of AI-aided diagnosis in the generation of post-healing images in medical imaging, which can help doctors and patients understand the healing process after surgery to a certain extent. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Research of medical image non-rigid registration based on TPS-SEMISURF algorithm

引用

2013 3rd International Symposium on Chemical Engineering and Material Properties, ISCEMP 2013

作者： Dong, Ao Shuang Yang, Ben Qiang Zhao, Dan Yang He, Bao Chun Zhang, Li Bo Yang, Guang Ming Tong, Qiang Gao, Tian Han Jiang, Hui Yan Software College Northeastern University Shenyang 110819 China Radioactive Branch PLA General Hospital of Shenyang Military Region Shenyang 110016 China Key Laboratory of Medical Image Computing Northeastern University Ministry of Education Shenyang 110819 China

ISBN: (纸本)9783037858363

Aiming at avoiding misregistration in complicated medical image registration based on SURF (Speed-Up Robust Features)-TPS (Thin-Plate Spline), we propose a novel algorithm. This method is based on SURF and human interaction method for feature extraction. Then we improve SURF-TPS and propose an algorithm named TPS-SEMISURF which obtains the deformation field by calculating the Thin-plate spline of the feature points, and finally does the medical image non-rigid registration according to the parameters. Experimental results showed that the proposed method can register medical images effectively. It has a good robustness and owns better precision and rate than traditional algorithm. © (2013) Trans Tech Publications, Switzerland.

关键词： image registration

来源：评论

学校读者我要写书评

暂无评论

Collaborative learning of graph generation, clustering and classification for brain networks diagnosis

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022年 219卷 106772-106772页

作者： Yang, Wenju Wen, Guangqi Cao, Peng Yang, Jinzhu Zaiane, Osmar R. [a]College of Computer Science and Engineering Northeastern University Shenyang China [b]Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China [c]Alberta Machine Intelligence Institute University of Alberta Edmonton Canada

Purpose: Accurate diagnosis of autism spectrum disorder (ASD) plays a key role in improving the condition and quality of life for patients. In this study, we mainly focus on ASD diagnosis with functional brain networks (FBNs). The major challenge for brain networks modeling is the high dimensional connectivity in brain networks and limited number of subjects, which hinders the classification capability of graph convolutional networks (GCNs). Method: To alleviate the influence of the limited data and high dimensional connectivity, we introduce a unified three-stage graph learning framework for brain network classification, involving multi-graph clustering, graph generation and graph classification. The framework combining Graph Generation, Clustering and Classification Networks (GraphCGC-Net) enhances the critical connections by multi-graph clustering (MGC) with a supervision scheme, and generates realistic brain networks by simultaneously preserving the global consistent distribution and local topology properties. Results: To demonstrate the effectiveness of our approach, we evaluate the performance of the proposed method on the Autism Brain Imaging Data Exchange (ABIDE) dataset and conduct extensive experiments on the ASD classification problem. Our proposed method achieves an average accuracy of 70.45% and an AUC of 72.76% on ABIDE. Compared with the traditional GCN model, the proposed GraphCGC-Net obtains 9.3%, and 10.64% improvement in terms of accuracy and AUC metrics, respectively. Conclusion: The comprehensive experiments demonstrate that our GraphCGC-Net is effective for graph classification in brain disorders diagnosis. Moreover, we find that MGC can generate biologically meaningful subnetworks, which is highly consistent with the previous neuroimaging-derived biomarker evidence of ASD. More importantly, the promising results suggest that applying generative adversarial networks (GANs) in brain networks to improve the classification performance is worth fur

关键词： Autism spectrum disorder Functional brain networks Multi-graph clustering Generative adversarial networks Graph convolutional networks

来源：评论

学校读者我要写书评

暂无评论

Improved Hessian multiscale enhancement filter

Improved Hessian multiscale enhancement filter

引用

作者： Yang, Jinzhu Ma, Shuang Sun, Qi Tan, Wenjun Xu, Mengjia Chen, Nan Zhao, Dazhe Key Laboratory of Medical Image Computing of Northeastern University Ministry of Education Shenyang110819 China College of Information Science and Engineering Northeastern University Shenyang110004 China Neusoft Shenyang110819 China Department of Radiology Xuanwu Hospital Capital Medical University Beijing China

Traditional Hessian multiscale filter consider only the local geometric feature but not the global grayscale information. In medical image analysis, Hessian filter is usually used to enhance the blood vessels. However, it also produces some pseudo vascular structures or some isolate noise points, such as the nasal soft tissues that have the similar shape with the vessels in MRA data, which will increase the difficulty of cerebrovascular segmentation. To resolve this issue, an improved Hessian multiscale filter is proposed in this paper. An image grayscale factor is added to the vascular similarity function computed by Hessian matrix eigenvalue. This method is experimented on brain MRA data and lung CTA data. Experimental results show that this method can enhance vascular structures, and simultaneously reduce the appearance of the pseudo vascular structures and the isolated noise points. © 2014 - IOS Press and the authors.

关键词： Blood vessels

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：