检索结果-内蒙古大学图书馆

Enhancing polyp detection in endoscopy with cross-channel self-attention fusion

Smart Health 2025年 36卷

作者： Liang, Xiaolong Chen, Shuijiao Shu, Linfeng Wang, Dechun Chen, Qilei Cao, Yu Liu, Benyuan Zhang, Honggang Liu, Xiaowei Department of Gastroenterology National Clinical Research Center for Geriatric Disorders Xiangya Hospital of Central South University and Hunan International Scientific and Technological Cooperation Base of Artificial Intelligence Computer Aided Diagnosis and Treatment for Digestive Disease Hunan Changsha 410008 China Miner School of Computer & Information Sciences University of Massachusetts Lowell Lowell 01854 MA United States School of Computer Science and Technology Huazhong University of Science and Technology Hubei Wuhan 430074 China Department of Engineering University of Massachusetts Boston Boston 02125 MA United States

Colorectal cancer (CRC) poses a significant global health challenge, ranking as a leading cause of cancer-related mortality. Colonoscopy, the most effective means of preventing CRC, is utilized for early detection and removal of precancerous growths. However, while there have been many efforts that utilize deep learning based approaches for automatic polyp detection, false positive rates in polyp detection during colonoscopy remain high due to the diverse characteristics of polyps and the presence of various artifacts. This paper introduces an innovative technique aimed at improving polyp detection accuracy in colonoscopy video frames. The proposed method introduces a novel framework incorporating a cross-channel self-attention fusion unit, aimed at enhancing polyp detection accuracy in endoscopic procedures. The integration of this unit proves to play an important role in refining prediction quality, resulting in more precise detection outcomes in complex medical imaging scenarios. To substantiate the effectiveness of our framework, we create an extensive private dataset comprising complete endoscopy videos, captured from diverse equipment from different manufacturers. This dataset represents realistic and intricate application scenarios, offering an authentic and effective foundation for both training and evaluating our framework. Thorough experiments and ablation studies are conducted to assess the performance of our proposed approach. The results demonstrate that our framework, featuring key technical innovations, significantly reduces false detections and achieves a higher recall rate. This underscores the remarkable effectiveness of our framework in upgrading polyp detection accuracy in real-world endoscopy procedures. © 2025 Elsevier Inc.

关键词： Colonoscopy computer vision Convolutional neural network Deep learning Polyp detection

来源：评论

学校读者我要写书评

暂无评论

Improving Brain MRI Image Segmentation Quality: A Hybrid Technique for Intensity Inhomogeneity Correction

Improving Brain MRI Image Segmentation Quality: A Hybrid Tec...

引用

Open Innovations Association (FRUCT), Conference of

作者： Samah Abdel Aziz Ammar Hawbani Xingfu Wang Talaat Abdelhamid Ismail Y. Maolood Saeed Alsamhi A. S. Ismail School of Computer Science and Technology University of Science and Technology of China Hefei China Faculty of Electronic Engineering Menoufia University Menoufia Egypt Ministry of Higher Education and Scientific Research Information and Communication Technology Center (ICTC)-System Information Erbil Kurdistan Region Iraq Insight Centre for Data Analytics National University of Ireland Galway Ireland

Intensity inhomogeneity is a significant issue in magnetic resonance imaging (MRI), where the presence of bias field causes distortions in pixel values, resulting in inconsistent and erroneous intensities across the image. This artifact not only hampers accurate diagnosis by radiologists but also negatively impacts the performance of computer-aided diagnosis algorithms, particularly in tasks like segmentation. In our proposed approach, we use a hybrid technique called KIFCM, which integrates K-means and Fuzzy C-means to enhance brain tumor segmentation. K-means provides computational efficiency, while Fuzzy C-means improves accuracy by detecting missed tumor cells. We employ a bias correction method based on the level set framework, removing noise with a median filter and applying the hybrid KIFCM technique for optimal segmentation. Our method effectively addresses intensity variation challenges, ensuring precise brain tumor region segmentation. We compare our results with DFCM and MFFLs, and the comparison shows the efficiency of our proposed method by highlighting the superior quality and accuracy of 81% achieved, requiring less computational time. Consequently, our results demonstrate KIFCM's potential to boost both accuracy and speed in MRI-based brain tumor detection through computer-aided diagnosis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interplay between Federated Learning and Explainable Artificial Intelligence: a Scoping Review

arXiv

引用

arXiv 2024年

作者： Lopez-Ramos, Luis M. Leiser, Florian Rastogi, Aditya Hicks, Steven Strümke, Inga Madai, Vince I. Budig, Tobias Sunyaev, Ali Hilbert, Adam Holistic Systems department Simula Metropolitan Center for Digital Engineering Oslo Norway Department of Economics and Management Karlsruhe Institute of Technology Germany Department of Neuroradiology University Hospital Bonn Germany Department of Computer Science Faculty of Informatics Norwegian University of Science and Technology Trondheim Norway QUEST Center for Responsible Research Charité - Universitätsmedizin Berlin Berlin Germany School of Computing and Digital Technology Birmingham City University Birmingham United Kingdom ETH Zurich Switzerland School of Computation Information and Technology Technical University of Munich Germany Charité - Universitätsmedizin Berlin Germany

The joint implementation of Federated learning (FL) and Explainable artificial intelligence (XAI) will allow training models from distributed data and explaining their inner workings while preserving important aspects of privacy. Towards establishing the benefits and tensions associated with their interplay, this scoping review maps those publications that jointly deal with FL and XAI, focusing on publications where an interplay between FL and model interpretability or post-hoc explanations was found. In total, 37 studies met our criteria, with more papers focusing on explanation methods (mainly feature relevance) than on interpretability (mainly algorithmic transparency). Most works used simulated horizontal FL setups involving 10 or fewer data centers. Only one study explicitly and quantitatively analyzed the influence of FL on model explanations, revealing a significant research gap. Aggregation of interpretability metrics across FL nodes created generalized global insights at the expense of node-specific patterns being diluted. 8 papers addressed the benefits of incorporating explanation methods as a component of the FL algorithm. Studies using established FL libraries or following reporting guidelines are a minority. More quantitative research and structured, transparent practices are needed to fully understand their mutual impact and under which conditions it happens. © 2024, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain for Finance: A Survey

arXiv

引用

arXiv 2024年

作者： Wu, Hanjie Yao, Qian Liu, Zhenguang Huang, Butian Zhuang, Yuan Tang, Huayun Liu, Erwu School of Cyber Science and Technology Zhejiang University Hangzhou China ZJU-Hangzhou Global Scientific and Technological Innovation Center Hangzhou China China Securities Regulatory Commission China Hangzhou Yunphant Network Technology Co. Ltd. Hangzhou China College of Computer Science and Technology Harbin Engineering University Harbin China Institute of Chinese Finance Studies Southwestern University of Finance and Economics Chengdu China College of Electronics and Information Engineering Tongji University Shanghai China

As an innovative technology for enhancing authenticity, security, and risk management, blockchain is being widely adopted in trade and finance systems. The unique capabilities of blockchain, such as immutability and transparency, enable new business models of distributed data storage, point-to-point transactions, and decentralized autonomous organizations. In this paper, we focus on blockchain-based securities trading, in which blockchain technology plays a vital role in financial services as it ultimately lifts trust and frees the need for third-party verification by using consensus-based verification. We investigate the 12 most popular blockchain platforms and elaborate on 6 platforms that are related to finance, seeking to provide a panorama of securities trading practices. Meanwhile, this survey provides a comprehensive summary of blockchain-based securities trading applications. We gather numerous practical applications of blockchain-based securities trading and categorize them into four distinct categories. For each category, we introduce a typical example and explain how blockchain contributes to solving the key problems faced by FinTech companies and researchers. Finally, we provide interesting observations ranging from mainstream blockchain-based financial institutions to security issues of decentralized finance applications, aiming to picture the current blockchain ecosystem in finance. Copyright © 2024, The Authors. All rights reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

arXiv

引用

arXiv 2024年

作者： Bassi, Pedro R.A.S. Li, Wenxuan Tang, Yucheng Isensee, Fabian Wang, Zifu Chen, Jieneng Chou, Yu-Cheng Roy, Saikat Kirchhoff, Yannick Rokuss, Maximilian Huang, Ziyan Ye, Jin He, Junjun Wald, Tassilo Ulrich, Constantin Baumgartner, Michael Maier-Hein, Klaus H. Jaeger, Paul Ye, Yiwen Xie, Yutong Zhang, Jianpeng Chen, Ziyang Xia, Yong Xing, Zhaohu Zhu, Lei Sadegheih, Yousef Bozorgpour, Afshin Kumari, Pratibha Azad, Reza Merhof, Dorit Shi, Pengcheng Ma, Ting Du, Yuxin Bai, Fan Huang, Tiejun Zhao, Bo Wang, Haonan Li, Xiaomeng Gu, Hanxue Dong, Haoyu Yang, Jichen Mazurowski, Maciej A. Gupta, Saumya Wu, Linshan Zhuang, Jiaxin Chen, Hao Roth, Holger Xu, Daguang Blaschko, Matthew B. Decherchi, Sergio Cavalli, Andrea Yuille, Alan L. Zhou, Zongwei Department of Computer Science Johns Hopkins University United States Department of Pharmacy and Biotechnology University of Bologna Italy Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Italy NVIDIA United States Germany Germany ESAT-PSI KU Leuven Belgium Faculty of Mathematics and Computer Science Heidelberg University Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Germany Shanghai Jiao Tong University China Shanghai Artificial Intelligence Laboratory China Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Germany DKFZ Germany School of Computer Science and Engineering Northwestern Polytechnical University China Australian Institute for Machine Learning The University of Adelaide Australia College of Computer Science and Technology Zhejiang University China Hong Kong University of Science and Technology Guangzhou China Hong Kong University of Science and Technology Hong Kong Faculty of Informatics and Data Science University of Regensburg Germany Faculty of Electrical Engineering and Information Technology RWTH Aachen University Germany Fraunhofer Institute for Digital Medicine MEVIS Germany Electronic & Information Engineering School Harbin Institute of Technology Shenzhen China China The Chinese University of Hong Kong Hong Kong Peking University China Department of Electrical and Computer Engineering Duke University United States Stony Brook University United States Department of Computer Science and Engineering Department of Chemical and Biological Engineering Division of Life Science Hong Kong University of Science and Technology Hong Kong Data Science and Computation Facility Fondazione Istituto Italiano di Tecnologia Italy Ecole Polytechnique Fédérale de Lausanne Switzerland

How can we test AI performance? This question seems trivial, but it isn’t. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain. Copyright © 2024, The Authors. All rights reserved.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

A Study and Recognition of Alzheimer’s Disease Using Machine Learning

A Study and Recognition of Alzheimer’s Disease Using Machin...

引用

International Conference for Convergence of Technology (I2CT)

作者： SK Masthan Basha Ashalatha G Srisailapu D Vara Prasad Mazin R. Al-Hameed Sajad Ali Zearah K Saikumar ECE Department Vignan's Institute of Management and Technology for Women Hyderabad India Department of Computer Science-CS-DS&AI&DS VNR Vignana Jyothi Institute of Engineering and Technology Hyderabad Telangana India Computer Science and Engineering School of Technology GITAM Deemed to be University Hyderabad Telangana Department of Medical Device Industry Engineering College of Engineering Technology National University of Science and Technology Dhi Qar Iraq Scientific Research Center Al-Ayen University Thi-Qar Iraq Koneru Lakshmaiah Education Foundation Andhra Pradesh India

Nowadays, Alzheimer's disease is one of the most severe threats to people of all ages and socioeconomic backgrounds. Their everyday activities may measure this disorder, and how they speak about it shows how concerned they are about it. The way we live today is different from how it was in the past because of our working environment and the lack of opportunities to interact with people. WHO estimates that about 10 billion individuals perish each year due to Alzheimer's disease since not been appropriately diagnosed and treated. An advanced Machine Learning-based recognition system design performs in this research work. The proposed model has been designed based on the human being EEG dataset(testing) and the Kaggle Alzheimer dataset (training). The developed intelligent system will be updated with data collection and pre-processing through the Random Forest machine model to locate our health condition and recognize daily routine changes. Only by developing a machine-based approach will we be able to discover Alzheimer's patients who previously had no idea that they had the illness and are now unable to reverse the progression of their condition. The designed application has attained a sensitivity of 93.01%, an accuracy of 91.32%, a recall of 97.28%, and a detection rate of 98.91%. The implemented application is beneficial to investigators and surgeons for easy treatment. The proposed RFO Machine learning design competes with present technology and outperforms methodology.

关键词： Training Sensitivity Surgery Organizations Data collection Brain modeling Data models

来源：评论

学校读者我要写书评

暂无评论

DR-GAN: Distribution Regularization for Text-to-Image Generation

arXiv

引用

arXiv 2022年

作者： Tan, Hongchen Liu, Xiuping Yin, Baocai Li, Xin Artificial Intelligence Research Institute Beijing University of Technology Beijing100124 China School of Electrical Engineering & Computer Science Center for Computation & Technology Louisiana State University Baton RougeLA70808 United States School of Mathematical Sciences Dalian University of Technology Dalian116024 China

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two novel modules: a Semantic Disentangling Module (SDM) and a Distribution Normalization Module (DNM). SDM combines the spatial self-attention mechanism and a new Semantic Disentangling Loss (SDL) to help the generator distill key semantic information for the image generation. DNM uses a Variational Auto-Encoder (VAE) to normalize and denoise the image latent distribution, which can help the discriminator better distinguish synthesized images from real images. DNM also adopts a Distribution Adversarial Loss (DAL) to guide the generator to align with normalized real image distributions in the latent space. Extensive experiments on two public datasets demonstrated that our DR-GAN achieved a competitive performance in the Text-to-Image task. The code link: https://***/Tan-H-C/DR-GAN-Distribution-Regularization-for-Text-to-Image-Generation. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Quantum Optics Applications of Hexagonal Boron Nitride Defects

arXiv

引用

arXiv 2024年

作者： Çakan, Aslı Cholsuk, Chanaprom Gale, Angus Kianinia, Mehran Paçal, Serkan Ateş, Serkan Aharonovich, Igor Toth, Milos Vogl, Tobias Department of Computer Engineering TUM School of Computation Information and Technology Technical University of Munich Munich80333 Germany Munich80799 Germany Abbe Center of Photonics Institute of Applied Physics Friedrich Schiller University Jena Jena07745 Germany School of Mathematical and Physical Sciences Faculty of Science University of Technology Sydney UltimoNSW2007 Australia University of Technology Sydney UltimoNSW2007 Australia Department of Physics Izmir Institute of Technology Izmir35430 Turkey

Hexagonal boron nitride (hBN) has emerged as a compelling platform for both classical and quantum technologies. In particular, the past decade has witnessed a surge of novel ideas and developments, which may be overwhelming for newcomers to the field. This review provides an overview of the fundamental concepts and key applications of hBN, including quantum sensing, quantum key distribution, quantum computing, and quantum memory. Additionally, we highlight critical experimental and theoretical advances that have expanded the capabilities of hBN, in a cohesive and accessible manner. The objective is to equip readers with a comprehensive understanding of the diverse applications of hBN, and provide insights into ongoing research efforts. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

The SWAP Imposter: Bidirectional Quantum Teleportation and its Performance

arXiv

引用

arXiv 2022年

作者： Siddiqui, Aliza U. Wilde, Mark M. Division of Computer Science and Engineering Louisiana State University Baton RougeLA70803 United States Hearne Institute for Theoretical Physics Department of Physics and Astronomy Center for Computation and Technology Louisiana State University Baton RougeLA70803 United States School of Electrical and Computer Engineering Cornell University IthacaNY14850 United States

Bidirectional quantum teleportation is a fundamental protocol for exchanging quantum information between two parties. Specifically, the two individuals make use of a shared resource state as well as local operations and classical communication (LOCC) to swap quantum states. In this work, we concisely highlight the contributions of our companion paper [Siddiqui and Wilde, arXiv:2010.07905]. We develop two different ways of quantifying the error of nonideal bidirectional teleportation by means of the normalized diamond distance and the channel infidelity. We then establish that the values given by both metrics are equal for this task. Additionally, by relaxing the set of operations allowed from LOCC to those that completely preserve the positivity of the partial transpose, we obtain semidefinite programming lower bounds on the error of nonideal bidirectional teleportation. We evaluate these bounds for some key examples-isotropic states and when there is no resource state at all. In both cases, we find an analytical solution. The second example establishes a benchmark for classical versus quantum bidirectional teleportation. Another example that we investigate consists of two Bell states that have been sent through a generalized amplitude damping channel (GADC). For this scenario, we find an analytical expression for the error, as well as a numerical solution that agrees with the former up to numerical precision. Copyright © 2022, The Authors. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Correction: Modeling of concrete-filled PVC tube columns confined with CFRP strips under uniaxial eccentric compression: machine learning and finite element approaches

引用

Journal of Big Data 2025年第1期12卷 1-2页

作者： Wang, Yan Elmeligy, Mohamed A. Isleem, Haytham F. Hamed, Asmaa Y. Qader, Diyar N. Sharaf, Mohamed Jangir, Pradeep Arpita Tejani, Ghanshyam G. School of Mechanical and Electrical Engineering Guilin University of Electronic Technology Guilin China Advanced Manufacturing Institute King Saud University Riyadh Saudi Arabia Jadara University Research Center Jadara University Irbid Jordan Department of Computer Science University of York York UK Construction and Building Department The Higher Institute of Engineering and Technology Luxor Luxor Egypt Civil Engineering Department University of Kirkuk Kirkuk Iraq Industrial Engineering Department College of Engineering King Saud University Riyadh Saudi Arabia University Centre for Research and Development Chandigarh University Gharuan Mohali India Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan Department of CSE Graphic Era Hill University Dehradun India Graphic Era Deemed Department of CSE To Be University Dehradun India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Industrial Engineering and Management Yuan Ze University Taoyuan Taiwan Applied Science Research Center Applied Science Private University Amman Jordan

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：