检索结果-内蒙古大学图书馆

Enhancing medical vision-language contrastive learning via inter-matching relation modelling

IEEE Transactions on Medical imaging 2025年第6期44卷 2463-2476页

作者： Li, Mingjian Meng, Mingyuan Fulham, Michael Feng, David Dagan Bi, Lei Kim, Jinman University of Sydney Biomedical data analysis and visualization lab School of Computer Science NSW Australia Royal Prince Alfred Hospital Department of Molecular Imaging NSW Australia Shanghai Jiao Tong University Institute of Translational Medicine Shanghai China

Medical image representations can be learned through medical vision-language contrastive learning (mVLCL) where medical imaging reports are used as weak supervision through image-text alignment. These learned image representations can be transferred to and benefit various downstream medical vision tasks such as disease classification and segmentation. Recent mVLCL methods attempt to align image sub-regions and the report keywords as local-matchings. However, these methods aggregate all local-matchings via simple pooling operations while ignoring the inherent relations between them. These methods therefore fail to reason between local-matchings that are semantically related, e.g., local-matchings that correspond to the disease word and the location word (semantic-relations), and also fail to differentiate such clinically important local-matchings from others that correspond to less meaningful words, e.g., conjunction words (importance-relations). Hence, we propose a mVLCL method that models the inter-matching relations between local-matchings via a relation-enhanced contrastive learning framework (RECLF). In RECLF, we introduce a semantic-relation reasoning module (SRM) and an importance-relation reasoning module (IRM) to enable more fine-grained report supervision for image representation learning. We evaluated our method using six public benchmark datasets on four downstream tasks, including segmentation, zero-shot classification, linear classification, and cross-modal retrieval. Our results demonstrated the superiority of our RECLF over the state-of-the-art mVLCL methods with consistent improvements across single-modal and cross-modal tasks. These results suggest that our RECLF, by modelling the inter-matching relations, can learn improved medical image representations with better generalization capabilities. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of Color Laparoscopic Super-Resolution Image Quality Based on Generative Adversarial Networks 1

Optimal Design of Color Laparoscopic Super-Resolution Image ...

引用

1st International Conference on Computer Graphics and Image Processing, CGIP 2023

作者： Kawabata, Norifumi Nakaguchi, Toshiya Hokkaido University Education and Research Center for Mathematical and Data Science Sapporo Japan Computational Imaging Lab Research Division of Computational Imaging Sapporo Japan Chiba University Center for Frontier Medical Engineering Chiba Japan

ISBN: (纸本)9798350333183

The Generative Adversarial Networks (GAN) is unsupervised learning enabled to transform according to data characteristics, though this generate unreal data by learning characteristics from data. As past our study, we discussed from the viewpoint of image quality for super-resolution of color laparoscopic image including SRCNN (Super-Resolution Convolutional Neural Network). However, it was not enough to compare to other neural network methods in our discussion. We consider that it is possible to support the medical image diagnosis by measuring whether the difference of both neural network method and image contents is affected or not for image quality. In this paper, first we carried out the objective image quality assessment by designing optimally of color laparoscopic super-resolution image using Generative Adversarial Networks (GAN). And then, we discussed for performance between methods comparing to result of SRCNN. On the other hand, from a view of information science, we consider that we need to verify experimentally for affect between network learning effect and generated image, and then to improve method. Therefore, we also discussed relationship between image quality and learning effect in color laparoscopic image generation using SRGAN. © 2023 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

3D CG Image Region of Interest Estimation and Visual Attention Based on Saliency Map 29

3D CG Image Region of Interest Estimation and Visual Attenti...

引用

29th International Display Workshops, IDW 2022

作者： Kawabata, Norifumi Education and Research Center for Mathematical and Data Science Hokkaido University Sapporo Japan Research Division of Computational Imaging Computational Imaging Lab Sapporo Japan

In this paper, we estimated that there is the region of interest (ROI) in which object or background region of 3D CG image from the view of stochastic model for saliency map, and then we evaluated and discussed quanti... 详细信息

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

A Pilot Study on Video-based Eye Movement Assessment of the NeuroEye Examination

A Pilot Study on Video-based Eye Movement Assessment of the ...

引用

2021 IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2021

作者： Hassan, Mohamed Abul Yin, Xuwang Zhuang, Yan Aldridge, Chad M. McMurry, Timothy Southerland, Andrew M. Rohde, Gustavo K. Imaging and Data Science Lab Department of Biomedical Engineering University of Virginia VA22903 United States Imaging and Data Science Lab Department of Electrical and Computer Engineering University of Virginia VA22903 United States The Department of Neurology University of Virginia VA22903 United States

ISBN: (纸本)9781665403580

The ability to perform automated neurological assessment could enhance diagnosis and treatment in the pre-hospital setting such as during telemedicine or emergency medical services (EMS) encounters. In this pilot study we present the preliminary analysis of a video-based eye movement assessment workflow (NeuroGaze) for neurological eye examinations. Our workflow uses a pupil detector to detect the center of the pupil for both eyes for a given video and determine the conjugacy of eye movement. The study evaluated the proposed workflow on 18 healthy volunteers while performing a digitally adapted neurological eye examination (NeuroEye) to assess conjugacy of gaze in all cardinal positions. The NeuroGaze performance was compared to the COTS eye tracker. The video-based eye movement assessment workflow reported an average Pearson correlation coefficient of 0.84, compared to the COTS eye tracker with an average of 0.95. The preliminary analysis indicates that NeuroGaze can be used to determine the individuals ability to perform conjugate eye movements. Future study will assess the performance of NeuroGaze in patients with pathological eye movements. © 2021 IEEE

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

SFPGCL: Specificity-preserving federated population graph contrastive learning for multi-site ASD identification using rs-fMRI data

引用

Computerized Medical imaging and Graphics 2025年 124卷 102558页

作者： Ren, Yudan Ma, Zihan Ding, Zhenqing Yang, Ruonan Li, Xiao He, Xiaowei Liu, Tianming School of Information Science & Technology Northwest University Xi'an China School of Network and Data Center Northwest University Xi'an China Cortical Architecture Imaging and Discovery Lab School of Computing University of Georgia United States

Autism spectrum disorder (ASD) is a severe neurodevelopmental disorder that affects people's social communication and daily routine. Most existing imaging studies on ASD use single site resting-state functional magnetic resonance imaging (rs-fMRI) data, which may suffer from limited samples and geographic bias. Improving the generalization ability of the diagnostic models often necessitates a large-scale dataset from multiple imaging sites. However, centralizing multi-site data generally faces inherent challenges related to privacy, security, and storage burden. Federated learning (FL) can address these issues by enabling collaborative model training without centralizing data. Nevertheless, multi-site rs-fMRI data introduces site variations, causing unfavorable data heterogeneity. This negatively impacts biomarker identification and diagnostic decision. Moreover, previous FL approaches for fMRI analysis often ignore site-specific demographic information, such as age, gender, and full intelligence quotient (FIQ), providing useful information as non-imaging features. On the other hand, Graph Neural Networks (GNNs) are gaining popularity in fMRI representation learning due to their powerful graph representation capabilities. However, existing methods often focus on extracting subject-specific connectivity patterns and overlook inter-subject relationships in brain functional topology. In this study, we propose a specificity-preserving federated population graph contrastive learning (SFPGCL) framework for rs-fMRI analysis and multi-site ASD identification, including a server and multiple clients/sites for federated model aggregation. At each client, our model consists of a shared branch and a personalized branch, where parameters of the shared branch are sent to the sever, while those of the personalized branch remain local. This setup facilitates invariant knowledge sharing among sites and also helps preserve site specificity. In the shared branch, we employ a spatio-te

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

TagGAN: A Generative Model for data Tagging

arXiv

引用

arXiv 2025年

作者： Nawaz, Muhammad Nasir, Basma Zia, Tehseen Hussain, Zawar Moreira, Catarina Data Science Institute University of Technology Sydney Australia COMSATS University Islamabad Pakistan Medical Imaging and Diagnostics Lab National Center of Artificial Intelligence Pakistan Macquarie University Sydney Australia

Precise identification and localization of disease-specific features at the pixel-level are particularly important for early diagnosis, disease progression monitoring, and effective treatment in medical image analysis. However, conventional diagnostic AI systems lack decision transparency and cannot operate well in environments where there is a lack of pixel-level annotations. In this study, we propose a novel Generative Adversarial Networks (GANs)-based framework, TagGAN, which is tailored for weakly-supervised fine-grained disease map generation from purely image-level labeled data. TagGAN generates a pixel-level disease map during domain translation from an abnormal image to a normal representation. Later, this map is subtracted from the input abnormal image to convert it into its normal counterpart while preserving all the critical anatomical details. Our method is first to generate fine-grained disease maps to visualize disease lesions in a weekly supervised setting without requiring pixel-level annotations. This development enhances the interpretability of diagnostic AI by providing precise visualizations of disease-specific regions. It also introduces automated binary mask generation to assist radiologists. Empirical evaluations carried out on the benchmark datasets, CheXpert, TBX11K, and COVID-19, demonstrate the capability of TagGAN to outperform current top models in accurately identifying disease-specific pixels. This outcome highlights the capability of the proposed model to tag medical images, significantly reducing the workload for radiologists by eliminating the need for binary masks during training. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

AirShot: Efficient Few-Shot Detection for Autonomous Exploration

AirShot: Efficient Few-Shot Detection for Autonomous Explora...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Zihan Wang Bowen Li Chen Wang Sebastian Scherer Institute for Imaging Data and Communications School of Engineering The University of Edinburgh UK AirLab Robotics Institute Carnegie Mellon University Pittsburgh PA USA Department of Computer Science and Engineering Spatial AI & Robotics (SAIR) Lab Institute for Artificial Intelligence and Data Science University at Buffalo NY USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Few-shot object detection has drawn increasing attention in the field of robotic exploration, where robots are required to find unseen objects with a few online provided examples. Despite recent efforts have been made to yield online processing capabilities, slow inference speeds of low-powered robots fail to meet the demands of real-time detection-making them impractical for autonomous exploration. Existing methods still face performance and efficiency challenges, mainly due to unreliable features and exhaustive class loops. In this work, we propose a new paradigm AirShot, and discover that, by fully exploiting the valuable correlation map, AirShot can result in a more robust and faster few-shot object detection system, which is more applicable to robotics community. The core module Top Prediction Filter (TPF) can operate on multi-scale correlation maps in both the training and inference stages. During training, TPF supervises the generation of a more representative correlation map, while during inference, it reduces looping iterations by selecting top-ranked classes, thus cutting down on computational costs with better performance. Surprisingly, this dual functionality exhibits general effectiveness and efficiency on various off-the-shelf models. Exhaustive experiments on COCO2017, VOC2014, and SubT datasets demonstrate that TPF can significantly boost the efficacy and efficiency of most off-the-shelf models, achieving up to 36.4% precision improvements along with 56.3% faster inference speed. Code and data are at: https://***/ImNotPrepared/AirShot.

关键词： Training Correlation Codes Computational modeling Atmospheric modeling Object detection Real-time systems Computational efficiency Intelligent robots Faces

来源：评论

学校读者我要写书评

暂无评论

AirShot: Efficient Few-Shot Detection for Autonomous Exploration

arXiv

引用

arXiv 2024年

作者： Wang, Zihan Li, Bowen Wang, Chen Scherer, Sebastian Institute for Imaging Data and Communications School of Engineering The University of Edinburgh United Kingdom AirLab Robotics Institute Carnegie Mellon University PittsburghPA15213 United States Lab Institute for Artificial Intelligence and Data Science Department of Computer Science and Engineering University at Buffalo NY14260 United States

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Optimal Design of Color Laparoscopic Super-Resolution Image Quality Based on Generative Adversarial Networks

Optimal Design of Color Laparoscopic Super-Resolution Image ...

引用

Computer Graphics and Image Processing (CGIP), International Conference on

作者： Norifumi Kawabata Toshiya Nakaguchi Education and Research Center for Mathematical and Data Science Hokkaido University Sapporo Japan Research Division of Computational Imaging Computational Imaging Lab Sapporo Japan Center for Frontier Medical Engineering Chiba University Chiba Japan

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Digital Camera-based Eye Movement Assessment Method for NeuroEye Examination

TechRxiv

引用

TechRxiv 2022年

作者： Hassan, Mohamed Abul Yin, Xuwang Zhuang, Yan Aldridge, Chad M. McMurry, Timothy Southerland, Andrew M. Rohde, Gustavo K. The Imaging and Data Science Lab Department of Biomedical Engineering University of Virginia VA22903 United States The Imaging and Data Science Lab Department of Electrical and Computer Engineering University of Virginia VA22903 United States The Department of Neurology University of Virginia VA22903 United States

The ability to perform quantitative and automated neurological assessment could enhance diagnosis and treatment in the pre-hospital setting, such as during telemedicine or emergency medical services (EMS) encounters. Such a tool could be developed by adapting clinically significant information such as symmetry of eye movement or conjugate eye movement. Here we describe a digital camera-based eye tracking method "NeuroGaze" to capture the symmetry of eye movement while performing neurological eye examination. The proposed method was developed based on detecting the center of the pupil for both eyes from a given video and measuring eye conjugacy by transforming the pupil center coordinates to relative gaze. The method was tested on 18 healthy volunteers while performing three neurological eye examinations1. We also compared our proposed approach to state-of-the-art digital camera-based eyetracking methods and commercial off-the-shelf (COTS) eye trackers. NeuroGaze outperformed digital camera-based eye tracking methods by reporting a mean Spearman rank-order correlation coefficient of 0.85 for the H-test, 0.85 for the Dot-test, and 0.5 for the OKN-Test, and shows similarity in trends for the relative gaze trajectories with a noticeable offset in the scale of the relative gaze angle compared to COTS eye tracker (see Fig. 1). The study demonstrates that by using a pupil-center-based eyetracking method, a digital camera can measure clinically relevant information regarding eye movement. © 2022-12-22, CC BY.

关键词： Eye tracking

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：