检索结果-内蒙古大学图书馆

DP-GAN+B: A lightweight generative adversarial network based on depthwise separable convolutions for generating CT volumes

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2024年 174卷 108393-108393页

作者： Xing, Xinlong Li, Xiaosen Wei, Chaoyi Zhang, Zhantian Liu, Ou Xie, Senmiao Chen, Haoman Quan, Shichao Wang, Cong Yang, Xin Jiang, Xiaoming Shuai, Jianwei Postgraduate Training Base Alliance of Wenzhou Medical University Zhejiang Wenzhou325000 China Wenzhou Institute University of Chinese Academy of Sciences Zhejiang Wenzhou325000 China School of Artificial Intelligence Guangxi Minzu University Nanning530006 China Department of Radiology The First Affiliated Hospital of Wenzhou Medical University Wenzhou325000 China Department of Big Data in Health Science The First Affiliated Hospital of Wenzhou Medical University China Department of Mathematics and Statistics Carleton College 300 N College St NorthfieldMN55057 United States School of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan114051 China

X-rays, commonly used in clinical settings, offer advantages such as low radiation and cost-efficiency. However, their limitation lies in the inability to distinctly visualize overlapping organs. In contrast, Computed Tomography (CT) scans provide a three-dimensional view, overcoming this drawback but at the expense of higher radiation doses and increased costs. Hence, from both the patient's and hospital's standpoints, there is substantial medical and practical value in attempting the reconstruction from two-dimensional X-ray images to three-dimensional CT images. In this paper, we introduce DP-GAN+B as a pioneering approach for transforming two-dimensional frontal and lateral lung X-rays into three-dimensional lung CT volumes. Our method innovatively employs depthwise separable convolutions instead of traditional convolutions and introduces vector and fusion loss for superior performance. Compared to prior models, DP-GAN+B significantly reduces the generator network parameters by 21.104 M and the discriminator network parameters by 10.82 M, resulting in a total reduction of 31.924 M (44.17%). Experimental results demonstrate that our network can effectively generate clinically relevant, high-quality CT images from X-ray data, presenting a promising solution for enhancing diagnostic imaging while mitigating cost and radiation concerns. © 2024 Elsevier Ltd

关键词： Convolution

Lung Nodule Segmentation and Uncertain Region Prediction with an Uncertainty-Aware Attention Mechanism

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Han Wang, Qiuli Zhang, Yue An, Zhulin Chen, Liu Zhang, Xiaohong 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 The Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Department of Radiology The First Affiliated Hospital of Army Medical University Chongqing400032 China School of Big Data & Software Engineering Chongqing University Chongqing401331 China Institute of Computing Technology Beijing100190 China

Radiologists possess diverse training and clinical experiences, leading to variations in the segmentation annotations of lung nodules and resulting in segmentation uncertainty. Conventional methods typically select a single annotation as the learning target or attempt to learn a latent space comprising multiple annotations. However, these approaches fail to leverage the valuable information inherent in the consensus and disagreements among the multiple annotations. In this paper, we propose an Uncertainty-Aware Attention Mechanism (UAAM) that utilizes consensus and disagreements among multiple annotations to facilitate better segmentation. To this end, we introduce the Multi-Confidence Mask (MCM), which combines a Low-Confidence (LC) Mask and a High-Confidence (HC) Mask. The LC mask indicates regions with low segmentation confidence, where radiologists may have different segmentation choices. Following UAAM, we further design an Uncertainty-Guide Multi-Confidence Segmentation Network (UGMCS-Net), which contains three modules: a Feature Extracting Module that captures a general feature of a lung nodule, an Uncertainty-Aware Module that produces three features for the annotations’ union, intersection, and annotation set, and an Intersection-Union Constraining Module that uses distances between the three features to balance the predictions of final segmentation and MCM. To comprehensively demonstrate the performance of our method, we propose a Complex Nodule Validation on LIDC-IDRI, which tests UGMCS-Net’s segmentation performance on lung nodules that are difficult to segment using common methods. Experimental results demonstrate that our method can significantly improve the segmentation performance on nodules that are difficult to segment using conventional methods. © 2023, CC BY-NC-ND.

关键词： Computerized tomography

Towards automated metamorphic test identification for ocean system models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hiremath, Dilip Jagadeeshwarswamy Claus, Martin Hasselbring, Wilhelm Rath, Willi MarDATA - Helmholtz School for Marine Data Science GEOMAR Helmholtz Centre for Ocean Research Kiel Kiel University Kiel Germany Software Engineering Group Computer Science Department Kiel University Kiel Germany Ocean Circulation and Climate Dynamics Department GEOMAR Helmholtz Centre for Ocean Research Kiel Kiel University Kiel Germany Ocean Circulation and Climate Dynamics Department GEOMAR Helmholtz Centre for Ocean Research Kiel Kiel Germany

Metamorphic testing seeks to verify software in the absence of test oracles. Our application domain is ocean system modeling, where test oracles rarely exist, but where symmetries of the simulated physical systems are known. The input data set is large owing to the requirements of the application domain. This paper presents work in progress for the automated generation of metamorphic test scenarios using machine learning. We extended our previously proposed method [1] to identify metamorphic relations with reduced computational complexity. Initially, we represent metamorphic relations as identity maps. We construct a cost function that minimizes for identifying a metamorphic relation orthogonal to previously found metamorphic relations and penalize for the identity map. A machine learning algorithm is used to identify all possible metamorphic relations minimizing the defined cost function. We propose applying dimensionality reduction techniques to identify attributes in the input which have high variance among the identified metamorphic relations. We apply mutation on these selected attributes to identify distinct metamorphic relations with reduced computational complexity. For experimental evaluation, we subject the two implementations of an ocean-modeling application to the proposed method to present the use of metamorphic relations to test the two implementations of this *** Codes J.2 © 2021, CC BY-SA.

关键词： Cost functions

Model-enhanced Vector Index

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hailin Wang, Yujing Chen, Qi Chang, Ruiheng Zhang, Ting Miao, Ziming Hou, Yingyan Ding, Yang Miao, Xupeng Wang, Haonan Pang, Bochen Zhan, Yuefeng Sun, Hao Deng, Weiwei Zhang, Qi Yang, Fan Xie, Xing Yang, Mao Cui, Bin School of Computer Science Key Lab of High Confidence Software Technologies Peking University China Microsoft United States Aerospace Information Research Institute Key Laboratory of Target Cognition and Application Technology Chinese Academy of Sciences China Institute of Information Engineering Chinese Academy of Sciences China Carnegie Mellon University United States National University of Singapore Singapore National Engineering Laboratory for Big Data Analysis and Applications Peking University China

Embedding-based retrieval methods construct vector indices to search for document representations that are most similar to the query representations. They are widely used in document retrieval due to low latency and decent recall performance. Recent research indicates that deep retrieval solutions offer better model quality, but are hindered by unacceptable serving latency and the inability to support document updates. In this paper, we aim to enhance the vector index with endto- end deep generative models, leveraging the differentiable advantages of deep retrieval models while maintaining desirable serving efficiency. We propose Modelenhanced Vector Index (MEVI), a differentiable model-enhanced index empowered by a twin-tower representation model. MEVI leverages a Residual Quantization (RQ) codebook to bridge the sequence-to-sequence deep retrieval and embeddingbased models. To substantially reduce the inference time, instead of decoding the unique document ids in long sequential steps, we first generate some semantic virtual cluster ids of candidate documents in a small number of steps, and then leverage the well-adapted embedding vectors to further perform a fine-grained search for the relevant documents in the candidate virtual clusters. We empirically show that our model achieves better performance on the commonly used academic benchmarks MSMARCO Passage and Natural Questions, with comparable serving latency to dense retrieval solutions. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

Optimization of Extraction Process of Valeriana officinalis L. Root Essential Oil and Study on Its Anti-Free Radical Activity

学校读者我要写书评

暂无评论

IOP Conference Series: Earth and Environmental science 2020年第1期526卷

作者： Tianlin Miao Hongjuan Zheng Xue Wang Ying Lan Yuehua Zhang Yujun Song Lan Li School of Life & Science Jiamusi University Jiamusi City Heilongjiang Province 154007 China School of Data Science and Software Engineering Wuzhou University Wuzhou City Guangxi Province 543000 China

Taking Valerianrhizome as raw material and the yield of volatile oil of Valerian as an index, the extraction process of valerian volatile oil was analyzed by microwave assisted steam distillation, and optimized by Box-Behnken response surface test. The effects of scavenging capacity of Li, DPPH and hydroxyl radicals on their antioxidant capacity were studied. The results showed that the optimal process conditions of microwave extraction of volatile oil of Valerian were 350W microwave power, extraction time 25min, liquid-to-material ratio 8.8mL: 1.0g, and the yield of volatile oil of Valerian extracted under this condition was 5.88%. Microwave-extracted volatile oil of Valerian has strong scavenging ability and high reducing power to DPPH free radicals and hydroxyl free radicals. Compared with steam distillation, it has obvious differences, which can provide reference for the development of antioxidant products of Valerian oil.

关键词：

Generative Adversarial Networks for Image Super-Resolution: A Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Chunwei Zhang, Xuanyu Zhu, Qi Zhang, Bob Lin, Jerry Chun-Wei School of Software Northwestern Polytechnical University the National Engineering Laboratory for Integrated Aero-space-Ground-Ocean Big Data Application Technology 1 Dongxiang Rd Shaanxi Xi’an710129 China School of Software Northwestern Polytechnical University 1 Dongxiang Rd Shaanxi Xi’an710129 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics 101 Section 2 Kuang-Fu Road Jiangsu Nanjing China PAMI Research Group University of Macau 101 Section 2 Kuang-Fu Road Macao999078 China Department of Computer Science Western Norway University of Applied Sciences Bergen Norway

Single image super-resolution (SISR) has played an important role in the field of image processing. Recent generative adversarial networks (GANs) can achieve excellent results on low-resolution images with small samples. However, there are little literatures summarizing different GANs in SISR. In this paper, we conduct a comparative study of GANs from different perspectives. We first take a look at developments of GANs. Second, we present popular architectures for GANs in big and small samples for image applications. Then, we analyze motivations, implementations and differences of GANs based optimization methods and discriminative learning for image super-resolution in terms of supervised, semi-supervised and unsupervised manners, where these GANs are analyzed via integrating different network architectures, prior knowledge, loss functions and multiple tasks. Next, we compare performance of these popular GANs on public datasets via quantitative and qualitative analysis in SISR. Finally, we highlight challenges of GANs and potential research points for SISR. © 2022, CC BY-NC-ND.

关键词： Generative adversarial networks

Is larger always better? Evaluating and prompting large language models for non-generative medical tasks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhu, Yinghao Gao, Junyi Wang, Zixiang Liao, Weibin Zheng, Xiaochen Liang, Lifang Wang, Yasha Pan, Chengwei Harrison, Ewen M. Ma, Liantao Institute of Artificial Intelligence Beihang University Beijing100191 China Centre for Medical Informatics University of Edinburgh EdinburghEH8 9YL United Kingdom Health Data Research UK United Kingdom School of Computer Science Peking University Beijing100871 China National Engineering Research Center for Software Engineering Peking University Beijing100871 China ETH Zürich Zürich8092 Switzerland

Background: The deployment of Large Language Models (LLMs) in medical fields is increasing, but few research evaluate their ability to manage both structured Electronic Health Record (EHR) data and unstructured clinical notes. This study provides a comprehensive benchmark of various models, including GPT-based LLMs, BERT-based language models, and conventional clinical predictive models to determine their efficacy in non-generative medical tasks using widely recognized datasets. Methods: We evaluated 14 language models (9 GPT-based and 5 BERT-based) alongside 7 conventional clinical predictive models on the MIMIC dataset, which encompasses comprehensive ICU patient records, and the TJH dataset, which includes EHR data from early COVID-19 patients. The performance of these models was assessed through a series of both supervised and unsupervised tasks, including mortality and readmission predictions, disease hierarchy reconstruction, and biomedical sentence matching. The study focused on comparing zero-shot prediction capabilities of LLMs with conventional models and the effectiveness of finetuned BERT-based models in handling clinical texts. Results: LLMs demonstrated promising zero-shot predictive abilities on structured EHR data when equipped with well-designed prompting strategies, often surpassing traditional models trained with limited datasets. However, in tasks involving unstructured medical texts, LLMs did not outperform existing BERT-based models. Both in supervised and unsupervised scenarios, the performance of finetuned BERT models was superior, suggesting that the additional cost and complexity of implementing LLMs might not be justifiable for non-generative tasks. Conclusion: While LLMs show significant potential in interpreting structured EHR data through zero-shot learning, their application in processing unstructured medical texts is less advantageous compared to finetuned BERT models. The findings underscore the importance of selecting appropriate mo

关键词： Clinical research

Hyperbolic geometric latent diffusion model for graph generation 24

学校读者我要写书评

暂无评论

Hyperbolic geometric latent diffusion model for graph genera...

Proceedings of the 41st International Conference on Machine Learning

作者： Xingcheng Fu Yisen Gao Yuecen Wei Qingyun Sun Hao Peng Jianxin Li Xianxian Li Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Institute of Artificial Intelligence Beihang University Beijing China and Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China School of Software Beihang University Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing School of Computer Science and Engineering Beihang University Beijing China

Diffusion models have made significant contributions to computer vision, sparking a growing interest in the community recently regarding the application of them to graph generation. Existing discrete graph diffusion models exhibit heightened computational complexity and diminished training efficiency. A preferable and natural way is to directly diffuse the graph within the latent space. However, due to the non-Euclidean structure of graphs is not isotropic in the latent space, the existing latent diffusion models effectively make it difficult to capture and preserve the topological information of graphs. To address the above challenges, we propose a novel geometrically latent diffusion framework HypDiff. Specifically, we first establish a geometrically latent space with interpretability measures based on hyperbolic geometry, to define anisotropic latent diffusion processes for graphs. Then, we propose a geometrically latent diffusion process that is constrained by both radial and angular geometric properties, thereby ensuring the preservation of the original topological properties in the generative graphs. Extensive experimental results demonstrate the superior effectiveness of HypDiff for graph generation with various topologies.

关键词：

A New Simple Stochastic Gradient Descent Type Algorithm With Lower Computational Complexity for Bilevel Optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huo, Haimei Liu, Risheng Su, Zhixun The School of Mathematical Sciences Dalian University of Technology Dalian116024 China The DUT-RU International School of Information Science and Engineering Dalian University of Technology China The Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian116024 China The State Key Laboratory of Structural Analysis for Industrial Equipment Dalian University of Technology Dalian116024 China The Key Laboratory for Computational Mathematics and Data Intelligence of Liaoning Province Dalian116024 China

Bilevel optimization has been widely used in many machine learning applications such as hyperparameter optimization and meta learning. Recently, many simple stochastic gradient descent(SGD) type algorithms(without using momentum and variance techniques) have been proposed to solve the bilevel optimization problems. However, all the existing simple SGD type algorithms estimate the hypergradient via stochastic estimation of Neumann series. In the paper, we propose to estimate the hypergradient via SGD-based Estimation(i.e., solving the linear system with SGD). By using warm start initialization strategy, a new simple SGD type algorithm SSGD based on SGD-based Estimation is proposed. We provide the convergence rate guarantee for SSGD and show that SSGD outperforms the best known computational complexity achieved by the existing simple SGD type algorithms. Our experiments validate our theoretical results and demonstrate the efficiency of our proposed algorithm SSGD in hyperparameter optimization applications. Copyright © 2023, The Authors. All rights reserved.

关键词： Linear systems