检索结果-内蒙古大学图书馆

MambaMIM: Pre-training Mamba with state space token interpolation and its application to medical image segmentation

Medical image Analysis 2025年 103卷 103606页

作者： Tang, Fenghe Nian, Bingkun Li, Yingtai Jiang, Zihang Yang, Jie Liu, Wei 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 Suzhou Institute for Advanced Research USTC Jiangsu Suzhou215123 China Department of Automation Shanghai Jiao Tong University Shanghai China Institute of Image Processing and Pattern Recognition Shanghai China Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology Jiangsu Suzhou215123 China State Key Laboratory of Precision and Intelligent Chemistry University of Science and Technology of China Anhui Hefei230026 China

Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-supervised learning methods have not yet fully unleashed Mamba's potential for handling long-range dependencies because they overlook the inherent causal properties of state space sequences in masked modeling. To address this challenge, we propose a general-purpose pre-training framework called MambaMIM, a masked image modeling method based on a novel TOKen-Interpolation strategy (TOKI) for the selective structure state space sequence, which learns causal relationships of state space within the masked sequence. Further, MambaMIM introduces a bottom-up 3D hybrid masking strategy to maintain a masking consistency across different architectures and can be used on any single or hybrid Mamba architecture to enhance its multi-scale and long-range representation capability. We pre-train MambaMIM on a large-scale dataset of 6.8K CT scans and evaluate its performance across eight public medical segmentation benchmarks. Extensive downstream experiments reveal the feasibility and advancement of using Mamba for medical image pre-training. In particular, when we apply the MambaMIM to a customized architecture that hybridizes MedNeXt and Vision Mamba, we consistently obtain the state-of-the-art segmentation performance. The code is available at: https://***/FengheTan9/MambaMIM. © 2025

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Lightweight Human Pose Estimation Using Loss Weighted by Target Heatmap 26th

Lightweight Human Pose Estimation Using Loss Weighted by Ta...

引用

26th International Conference on Pattern Recognition, ICPR 2022

作者： Li, Shiqi Xiang, Xiang Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783031376597

Recent research on human pose estimation exploits complex structures to improve performance on benchmark datasets, ignoring the resource overhead and inference speed when the model is actually deployed. In this paper, we lighten the computation cost and parameters of the deconvolution head network in SimpleBaseline and introduce an attention mechanism that utilizes original, inter-level, and intra-level information to intensify the accuracy. Additionally, we propose a novel loss function called heatmap weighting loss, which generates weights for each pixel on the heatmap that makes the model more focused on keypoints. Experiments demonstrate our method achieves a balance between performance, resource volume, and inference speed. Specifically, our method can achieve 65.3 AP score on COCO test-dev, while the inference speed is 55 FPS and 18 FPS on the mobile GPU and CPU, respectively. © 2023, Springer Nature Switzerland AG.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Transmit aperture function for large depth focusing combined with phase coherence imaging for interference suppressing

Transmit aperture function for large depth focusing combined...

引用

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Xu, Mengling Chen, Yimin Yuchi, Ming Ding, Mingyue School of Life Science and Technology Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769546230

Dynamic focus and dynamic aperture applied on both transmit and receive aperture can provide the best possible quality of the B-mode ultrasound image, which is called a "gold standard" image. However, they are implemented only on the receive beam in most medical ultrasound systems because the application of dynamic focus on the transmit beam will reduce the frame rate severely, which has great medical importance especially when tissue motion needs to be considered. Recently, a specific transmit aperture function has been proposed to achieve uniform transmit energy distribution on the axis over a large depth without reducing the frame rate. Although it can maintain the uniformity of the transmit energy on the axis, the energy distribution off the axis of the transmit beam is not satisfactory, meaning a wider main lobe width and higher side lobe levels compared with some general aperture functions such as rectangular and hamming functions. To suppress the interference signals originating from the targets on the side and grating lobes, we processed the received echo signals using the phase coherence imaging method (PCI), which is an adaptive receive aperture weighting technique presented in the recent literatures. Experimental results show that the uniform sensitivity along the axis range has been achieved and image quality on spatial and contrast resolution improved when we use the transmit aperture function combined with PCI. © 2011 IEEE.

关键词： Ultrasonic applications

来源：评论

学校读者我要写书评

暂无评论

A three-dimensional transrectal ultrasound imaging system

A three-dimensional transrectal ultrasound imaging system

引用

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Chen, Yimin Qi, Jian Zhang, Xuming Ding, Mingyue School of Life Science and Technology Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769546230

A three dimensional transrectal ultrasound imaging system has been developed. The proposed system is aimed at monitoring for the prostate and providing three-dimensional ultrasound image for prostate biopsy and therapy. The device contains mechanical device and control circuit for the rotation of the probe. In addition, a two dimensional ultrasound machine for 2D ultrasound imaging is used and the software system for the reconstruction of three-dimensional ultrasound image based on PC is developed. Experiments are performed in phantom to validate our prototype. The 3D scan of the agar phantom produces minimal geometric distortion. In the future, our system will be tested on patients. © 2011 IEEE.

关键词： Phantoms

来源：评论

学校读者我要写书评

暂无评论

Robust Electric Vehicle Routing Problem with Time Windows under Demand Uncertainty and Weight-Related Energy Consumption

引用

Complex System Modeling and Simulation 2022年第1期2卷 18-34页

作者： Yindong Shen Leqin Yu Jingpeng Li Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhan 430074China Division of Computer Science and Mathematics University of StirlingStirlingFK94LAUK

Vehicle routing problem with time windows(VRPTW)is a core combinatorial optimization problem in distribution *** electric vehicle routing problem with time windows under demand uncertainty and weight-related energy consumption is an extension of the *** some researchers have studied either the electric VRPTW with nonlinear energy consumption model or the impact of the uncertain customer demand on the conventional vehicles,the literature on the integration of uncertain demand and energy consumption of electric vehicles is still ***,practically,it is usually not feasible to ignore the uncertainty of customer demand and the weight-related energy consumption of electronic vehicles(EVs)in actual ***,we propose the robust optimization model based on a route-related uncertain set to tackle this ***,adaptive large neighbourhood search heuristic has been developed to solve the problem due to the NP-hard nature of the *** effectiveness of the method is verified by experiments,and the influence of uncertain demand and uncertain parameters on the solution is further explored.

关键词： electric vehicle routing problem time windows uncertain demand energy consumption model robust optimization adaptive large neighbourhood search

来源：评论

学校读者我要写书评

暂无评论

Bagging and Boosting Fine-Tuning for Ensemble Learning

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1728-1742页

作者： Zhao, Changming Peng, Ruimin Wu, Dongrui Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074 China and alsowith the ShenzhenHuazhong University of Science and Technology Research Institute Shenzhen 518029 China

Ensemble learning aggregates outputs from multiple base learners for better performance. Bootstrap aggregating (bagging) and boosting are two popular such approaches. They are suitable for integrating unstable base learners with large variance and weak base learners with large bias, respectively, but not base learners with small variance and/or bias, e.g., support vector machine, regularized logistic regression, and ridge regression. This article proposes two novel ensemble-learning-based fine-tuning approaches, boosting fine-tuning (BF) and bagging and boosting fine-tuning (BBF), to fine-tune learners with small variance and/or bias for better performance. BF embeds boosting in a single hidden layer neural network. In each iteration, BF first uses the Newton's method to generate a temporary training set, and then trains a boosting learner on it. BBF combines BF and bagging. It first uses bootstrap to obtain multiple replicas of the training set, and then trains a BF learner on each replica. Extensive experiments on 46 real-world datasets demonstrated that BBF is flexible, robust, and effective, and can fine-tune many popular classifiers to achieve better generalization performance. © 2020 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

The application of support vector machines and improved particle swarm optimization

The application of support vector machines and improved part...

引用

2012 International Conference on Modelling, Identification and control, ICMIC 2012

作者： Zhang, Hu Wang, Min Huang, Xinhan Key Laboratory of Image Processing and Intelligent Control of Education Department of Control Science and Engineering Huazhong University of Science and Technology NO.1037 Luoyu Road 430074 Wuhan China

ISBN: (纸本)9780956715715

Parameters selection of support vector machine is the key issue that impacts its accurate performance. A method for support vector regression machine with standard particle swarm optimization (SPSO) algorithm is proposed in this paper. Furthermore, in order to improve the performance of the SPSO algorithm, the concept of the particles' average distance and fitness variance is proposed to make the efficiency of algorithm better. So, the improve algorithm was also applied in this paper. The two different models using SPSO and IPSO respectively were used to forecast the density of the acid-lead battery electrolyte. The experimental results indicate that both SPSO and IPSO have high prediction accuracy and efficiency. The time of the parametric searching by IPSO is obviously decreased to that of SPSO. The mean squared error (MSE) of the prediction model using SPSO is about 2.02056×10-4, Meanwhile, the MSE of the model using IPSO is only about 1.9324×10-4. So, the IPSO algorithm has more superior performance on convergence speed and global optimization. © 2012 Huazhong Univ of Sci & Tec.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

3D ultrasound data acqusition system based on back end scan mode

3D ultrasound data acqusition system based on back end scan ...

引用

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Qi, Jian Ding, Mingyue Yuchi, Ming Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China School of Life Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9780769546230

The data acquisition of 3D-Ultrasound includes array scan and mechanical scan, and the later one is more easy to realize. Currently, the traditional probe scanning mode is Front-end scanning. Under the above scanning mode, when it scans over the breast, 2D-Ultrasound probe slides through the surface of the patients' bodies, the image will be influenced strongly by the human *** this paper we propose a new scanning mode to solve the above problem: Back-End scan, the back end rotates while the front end contacts the patients' skin without slide. The device designed using dual stepper motors which are under the synchronization control. Experiment results show the effectiveness of the proposed device. © 2011 IEEE.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

A novel estimation strategy for the eye-in-hand depth-independent visual servoing

A novel estimation strategy for the eye-in-hand depth-indepe...

引用

2011 International Conference on Consumer Electronics, Communications and Networks, CECNet 2011

作者： Liang, Xinwu Huang, Xinhan Wang, Min Key Laboratory of Image Processing and Intelligent Control of Education Ministry of China Dept. of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 Hubei China

ISBN: (纸本)9781612844572

As we know, a novel adaptive visual servoing strategy has been proposed for the control of robot manipulators with an eye-in-hand configuration, where an adaptive law is used to estimate the unknown parameters determined by the products of the unknown 3D coordinates and the unknown camera parameters. From a practical point of view, in this paper, we propose a novel strategy for the estimation of these two types of unknown parameters. The new strategy is very useful in that it can reduce the number of the unknown parameters to be estimated. To demonstrate the feasibility of the proposed method, preliminary simulation results based on a two-link planar robot manipulator are presented in this paper. © 2011 IEEE.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Solving 0-1 planning problem based on self-assembly of dna tiles

Solving 0-1 planning problem based on self-assembly of dna t...

引用

作者： Huang, Yufang Cheng, Zhen Xu, Jin Shi, Xiaolong Zhou, Kang Key Laboratory of Image Processing and Intelligent Control Department of Control Science and Engineering Huazhong University of Science and Technology 430074 Wuhan China Ministry of Education 10087 Beijing China

DNA tile self-assembly has been proved to enable programmable manipulation of biological systems as a tool of molecular computation. It is mainly based on the property that is the spontaneous self-ordering of substructure into superstructure driven by annealing of Watson-Crick base-pairing DNA sequences. We take full advantage of the superiority of DNA tile self-assembly to construct a molecular computing system that implements a solution for the 0-1 planning problem. This algorithm can independently and simultaneously yield the data pool, containing all possible solutions when all basic operation tiles are designed beforehand. Then we can use some advanced bio-chemistry techniques to select the optimization solutions of the 0-1 planning problem. Our work has shown that it is possible to work with an exponential number of components to solve NP-complete problems. The method proposed here also can reduce the number of laboratory steps required for computation so that it can improve the computation speed. Copyright © 2010 American Scientific Publishers. All rights reserved.

关键词： Self assembly

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：