检索结果-内蒙古大学图书馆

SYSTEMS AND SOFT COMPUTING 2025年 7卷

作者： Alia, Osama Moh'd Univ Tabuk Fac Comp & Informat Technol Dept Comp Sci POB 741 Tabuk 71491 Saudi Arabia

image segmentation is a fundamental component of image analysis. While numerous algorithms exist for this task, thresholding is one of the most widely used methods. Multilevel thresholding, which involves dividing an image into multiple segments, is computationally intensive due to its need to search for optimal thresholds. This paper presents a solution to this optimization problem by exploring the New Caledonian crow learning algorithm (NCCLA). Inspired by nature, the NCCLA algorithm draws from the behaviors of New Caledonian crows, which use tools from Pandanus trees to obtain food. To improve the algorithm's capacity to discover optimal thresholds while balancing the exploitation and exploration processes, this paper introduces a modification inspired by the pitch adjustment rate portion of the harmony search algorithm. The performance of this modified NCCLA algorithm was evaluated on benchmark images, and a comparative analysis was conducted against other metaheuristic-based algorithms including particle swarm optimization, harmony search, bacterial foraging, and genetic algorithms;the experimental results demonstrate the effectiveness of the proposed algorithm, which was further statistically validated using a t-test.

关键词： New Caledonian crow learning algorithm image segmentation Multilevel thresholding Otsu method Kapur method

来源：评论

学校读者我要写书评

暂无评论

Prompt Once, Segment Everything: Leveraging SAM 2 Potential for Infinite Medical image segmentation with a Single Prompt

引用

ALGORITHMS 2025年第4期18卷

作者： Gutierrez, Juan D. Delgado, Emilio Breuer, Carlos Conejero, Jose M. Rodriguez-Echeverria, Roberto Univ Santiago Compostela Dept Elect & Comp Sci Rua Benigno Ledo Lugo 27002 Spain Univ Extremadura Inst Invest Tecnol Informat Aplicadas INTIA Ave Univ S-N Caceres 10003 Spain

Semantic segmentation of medical images holds significant potential for enhancing diagnostic and surgical procedures. Radiology specialists can benefit from automated segmentation tools that facilitate identifying and isolating regions of interest in medical scans. Nevertheless, to obtain precise results, sophisticated deep learning models tailored to this specific task must be developed and trained, a capability not universally accessible. Segment Anything Model (SAM) 2 is a foundational model designed for image and video segmentation tasks, built on its predecessor, SAM. This paper introduces a novel approach leveraging SAM 2's video segmentation capabilities to reduce the prompts required to segment an entire volume of medical images. The study first compares SAM and SAM 2's performance in medical image segmentation. Evaluation metrics such as the Jaccard index and Dice score are used to measure precision and segmentation quality. Then, our novel approach is introduced. Statistical tests include comparing precision gains and computational efficiency, focusing on the trade-off between resource use and segmentation time. The results show that SAM 2 achieves an average improvement of 1.76% in the Jaccard index and 1.49% in the Dice score compared to SAM, albeit with a ten-fold increase in segmentation time. Our novel approach to segmentation reduces the number of prompts needed to segment a volume of medical images by 99.95%. We demonstrate that it is possible to segment all the slices of a volume and, even more, of a whole dataset, with a single prompt, achieving results comparable to those obtained by state-of-the-art models explicitly trained for this task. Our approach simplifies the segmentation process, allowing specialists to devote more time to other tasks. The hardware and personnel requirements to obtain these results are much lower than those needed to train a deep learning model from scratch or to modify the behavior of an existing one using model modifi

关键词： image segmentation deep learning zero-shot learning medical imaging foundation models

来源：评论

学校读者我要写书评

暂无评论

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

引用

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimized image segmentation using an improved reptile search algorithm with Gbest operator for multi-level thresholding

引用

SCIENTIFIC REPORTS 2025年第1期15卷 1-45页

作者： Abualigah, Laith Al-Okbi, Nada Khalil Alomari, Saleh Ali Almomani, Mohammad H. Moneam, Sahar Yousif, Maryam A. Snasel, Vaclav Saleem, Kashif Smerat, Aseel Ezugwu, Absalom E. Al Al Bayt Univ Comp Sci Dept Mafraq 25113 Jordan Univ Baghdad Coll Sci Women Dept Comp Sci Baghdad Iraq Jadara Univ Fac Informat Technol Irbid 21110 Jordan VSB Tech Univ Ostrava Fac Elect Engn & Comp Sci Poruba Ostrava 70800 Czech Republic King Saud Univ Coll Appl Studies & Community Serv Dept Comp Sci & Engn Riyadh 11362 Saudi Arabia Al Ahliyya Amman Univ Fac Educ Sci Amman 19328 Jordan Chitkara Univ Inst Engn & Technol Ctr Res Impact & Outcome Rajpura 140401 Punjab India North West Univ Unit Data Sci & Comp 11 Hofman St ZA-2520 Potchefstroom South Africa Hashemite Univ Dept Math Fac Sci POB 330127 Zarqa 13133 Jordan Mazaya Univ Coll Comp Technol Engn Nasiriyah Iraq

image segmentation using bi-level thresholds works well for straightforward scenarios;however, dealing with complex images that contain multiple objects or colors presents considerable computational difficulties. Multi-level thresholding is crucial for these situations, but it also introduces a challenging optimization problem. This paper presents an improved Reptile Search Algorithm (RSA) that includes a Gbest operator to enhance its performance. The proposed method determines optimal threshold values for both grayscale and color images, utilizing entropy-based objective functions derived from the Otsu and Kapur techniques. Experiments were carried out on 16 benchmark images, which included COVID-19 scans along with standard color and grayscale images. A thorough evaluation was conducted using metrics such as the fitness function, peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and the Friedman ranking test. The results indicate that the proposed algorithm seems to surpass existing state-of-the-art methods, demonstrating its effectiveness and robustness in multi-level thresholding tasks.

关键词： Medical images image segmentation Multi-level threshold Reptile search algorithm Otsu method, Kapur method

来源：评论

学校读者我要写书评

暂无评论

A Novel iDAGUNet-Assisted QSM Method to Enhance image segmentation for Quantitative Assessment of Magnetic Hydrogel Evolution in Rat Vagus Nerve

引用

SENSING AND IMAGING 2025年第1期26卷 1-23页

作者： Wang, Peng Zhu, Chenzhuo Lv, Pin Li, Zheng Bao, Siyuan Mai, Xiaoli Gu, Jiayu Sun, Jianfei Southeast Univ Sch Biol Sci & Med Engn State Key Lab Bioelect Jiangsu Key Lab Biomat & Devices Nanjing 210009 Peoples R China Nanjing Univ Nanjing Drum Tower Hosp Med Sch State Key Lab Pharmaceut BiotechnolDept Sports Me Nanjing 210008 Peoples R China Nanjing Univ Nanjing Drum Tower Hosp Affiliated Hosp Dept RadiolMed Sch Nanjing 210008 Peoples R China Jiangsu Inst Metrol Nanjing 210023 Peoples R China

Quantitative susceptibility mapping (QSM) is considered as a valuable technique to assess the evolution of iron oxide nanoparticles (IONPs)-based biomaterials by deconvolving the magnetic field through the combination of magnitude and phase map information of magnetic resonance imaging (MRI). However, issues may arise during QSM processing, particularly in tissues with irregular boundaries, where signal loss can occur. In this work, we developed an improved dilated attention gate U-Net (iDAGUNet) network, an augmentation of the U-Net segmentation framework that incorporates attention mechanisms and dilated convolutional structures. Enhancement in segmentation ability is evident in iDAGUNet model with an average intersection-over-union (IoU) of 0.931. Notably, iDAGUNet-assisted QSM could effectively resolve the signal loss issue associated with irregular boundaries as evidenced by comparison with manually labeled masks, affirming their accuracy and reliability (R-2=0.996). Finally, long-term residence capabilities of IONPs-incorporated hydrogels in rat vagus nerve were monitored by iDAGUNet-assisted QSM with only 41% degradation within 16 weeks. This technology exhibits substantial promise in advancing quantitative assessment of IONPs-based biomaterials evolution for preclinical evaluations and the translation of IONPs-based biomaterials into practical applications.

关键词： Improved dilated attention gate U-Net Magnetic resonance imaging Quantitative susceptibility mapping Iron oxide nanoparticles image segmentation

来源：评论

学校读者我要写书评

暂无评论

Near-infrared vascular image segmentation using multi-stage enhancement and TAU-Net

引用

INFRARED PHYSICS & TECHNOLOGY 2025年 148卷

作者： Tian, Zhen Liu, Haoting Ji, Qianru Wang, Song Li, Qing Yi, Dewei Liu, Xintao Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing Engn Res Ctr Ind Spectrum Imaging Beijing 100083 Peoples R China Peking Univ Third Hosp Dept Nephrol Beijing 100191 Peoples R China Univ Aberdeen Dept Comp Sci Aberdeen AB24 3UE Scotland Hong Kong Polytech Univ Dept Land Surveying & Geoinformat Hong Kong 999077 Peoples R China

Near-infrared optical imaging technology provides a non-invasive solution for visualization and monitoring of subcutaneous vascular structures. In order to solve the problems of low vascular image quality and inefficient and inaccurate manual segmentation, we propose a complete set of image processing methods. First, the blood vessel images are preprocessed by the background removal, Gaussian filtering, and contrast stretching. Then the image details are enhanced by a multi-stage enhancement method, which combines the Residual Convolutional AutoEncoder (RCAE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) to effectively improve the contrast between vascular region and other tissue regions. Finally, the images are segmented by our Triplet Attention U-Net (TAU-Net) model, which improves the efficiency and performance of attention mechanism. The TAU-Net introduces a triple attention module in U-Net for the first time, which strengthens the computational ability of spatial and channel attention models. The main segmentation head and auxiliary segmentation head are combined to improve the gradient information, promote the multi-scale learning of network. Numerous experimental results show that our model can flexibly process blood vessel images of various quality levels and distribution forms, and effectively segment their contours well.

关键词： U -Net Triplet attention Near infrared vascular images image segmentation

来源：评论

学校读者我要写书评

暂无评论

A multi-strategy enhanced circle search algorithm based on adaptive evolutionary framework and its application in image segmentation

引用

Cluster Computing 2025年第5期28卷 1-46页

作者： Wang, Wei Lu, Yinan Wang, Shengsheng College of Computer Science and Technology Jilin University Jilin Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Jilin Changchun130012 China

Circle search algorithm (CSA) is a meta-heuristic optimization algorithm based on the characteristics of circle geometry. In order to overcome the shortcomings of the original CSA in the optimization process, such as low convergence accuracy and easily falling into local optimal, this paper proposed a multi-strategy enhanced CSA named APRDCSA. Firstly, a mutation strategy guided by multiple superior solutions is proposed, which increases the diversity of the population and the global exploration ability of the algorithm. Secondly, random replacement strategy is introduced in the late iteration to avoid falling into local optima. Finally, a population evolution state assessment framework with adaptive parameter (APSE) based on improvement rate is proposed to improve the probability of finding a better solution. A series of comparative experiments on IEEE CEC 2014 demonstrate the superior convergence speed and solution quality of APRDCSA, as well as its enhanced reliability in avoiding local optima. In addition, to further illustrate the improved performance of APRDCSA and its ability to solve practical applications, we apply it to the multi-thresholding image segmentation (MIS) method based on non-local mean two-dimensional histogram and Kapur entropy. Experimental results show that the proposed method achieves better segmentation results at both low and high threshold levels. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Extracting Learning Data From Handwritten Notes: A New Approach to Educational Data Analysis Based on image segmentation and Generative AI

引用

IEEE ACCESS 2025年 13卷 74563-74576页

作者： Zhou, Yunyu Tang, Cheng Shimada, Atsushi Kyushu Univ Fac Informat Sci & Elect Engn Fukuoka 8190395 Japan

While handwritten notes offer valuable insights into students' knowledge retention, traditional analysis methods are often time-consuming and limited in scope. This study introduces an efficient approach for educational data analysis by combining image segmentation with generative AI to extract learning insights from students' handwritten notes. Leveraging the Attention Multi-task U-Net for accurate segmentation and GPT-4o for content analysis, our method precisely identifies and categorizes text, charts, and formulas within notes. The extracted data provides educators with a detailed view of students' knowledge retention, highlights the areas students focus on, and identifies critical knowledge points that may be missing from notes. Our experiments on student notes from a Digital Signal Processing course demonstrate the method's high accuracy and significant efficiency improvements in teachers' review of student notes. This research contributes to educational technology and data mining by introducing an automated, scalable method that supports more personalized and effective educational strategies.

关键词： image segmentation Accuracy Multitasking Generative AI Natural language processing Data mining Data models Analytical models Handwriting recognition Optical character recognition Attention multi-task U-Net GPT-4o handwritten notes image segmentation knowledge extraction natural language processing

来源：评论

学校读者我要写书评

暂无评论

UniAda: Domain Unifying and Adapting Network for Generalizable Medical image segmentation

引用

IEEE TRANSACTIONS ON MEDICAL IMAGING 2025年第5期44卷 1988-2001页

作者： Zhang, Zhongzhou Chen, Yingyu Yu, Hui Wang, Zhiwen Wang, Shanshan Fan, Fenglei Shan, Hongming Zhang, Yi Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Univ Minist Educ Key Lab Data Protect & Intelligent Management Chengdu 610207 Peoples R China Anhui Univ Minist Educ Inst Phys Sci & Informat Technol Key Lab Intelligent Comp & Signal Proc Hefei 230601 Peoples R China Chinese Univ Hong Kong Dept Math Hong Kong Peoples R China Fudan Univ MOE Frontiers Ctr Brain Sci Inst Sci & Technol Brain Inspired Intelligence Shanghai 200433 Peoples R China Fudan Univ Key Lab Computat Neurosci & Brain Inspired Intelli Shanghai 200433 Peoples R China Shanghai Ctr Brain Sci & Brain Inspired Technol Shanghai 201210 Peoples R China Sichuan Univ Sch Cyber Sci & Engn Chengdu 610207 Peoples R China

Learning a generalizable medical image segmentation model is an important but challenging task since the unseen (testing) domains may have significant discrepancies from seen (training) domains due to different vendors and scanning protocols. Existing segmentation methods, typically built upon domain generalization (DG), aim to learn multi-source domain-invariant features through data or feature augmentation techniques, but the resulting models either fail to characterize global domains during training or cannot sense unseen domain information during testing. To tackle these challenges, we propose a domain Unifying and Adapting network (UniAda) for generalizable medical image segmentation, a novel "unifying while training, adapting while testing" paradigm that can learn a domain-aware base model during training and dynamically adapt it to unseen target domains during testing. First, we propose to unify the multi-source domains into a global inter-source domain via a novel feature statistics update mechanism, which can sample new features for the unseen domains, facilitating the training of a domain base model. Second, we leverage the uncertainty map to guide the adaptation of the trained model for each testing sample, considering the specific target domain may be outside the global inter-source domain. Extensive experimental results on two public cross-domain medical datasets and one in-house cross-domain dataset demonstrate the strong generalization capacity of the proposed UniAda over state-of-the-art DG methods. The source code of our UniAda is available at https://***/ZhouZhang233/UniAda.

关键词： Adaptation models Training image segmentation Testing Data models Uncertainty Perturbation methods Medical diagnostic imaging Metalearning Representation learning Domain generalization medical image segmentation base model unifying and adapting

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Driven Edge Prompt Generation Network for Medical image segmentation

引用

IEEE Transactions on Medical Imaging 2025年第5期44卷 2218-2229页

作者： Zhao, Junyong Sun, Liang Fan, Dingwei Wang, Kun Si, Haipeng Fu, Huazhu Zhang, Daoqiang Ministry of Education College of Artificial Intelligence Nanjing University of Aeronautics and Astronautics The Key Laboratory of Brain-Machine Intelligence Technology Nanjing211106 China Nanjing University of Aeronautics and Astronautics Shenzhen Research Institute China Shandong University Cheeloo College of Medicine Department of Orthopedics Qilu Hospital Jinan250012 China 138632 Singapore

Segment Anything Model (SAM) is a foundational image segmentation model, which shows superior performance for natural image segmentation tasks. Several SAM-based medical image segmentations have been proposed. However, these SAM-based medical image segmentation methods heavily depend on prior manual guidance involving points, boxes, and coarse-grained masks, which lack adaptability and flexibility. Moreover, the inherent challenge of edge blurring in medical images is critical, as it directly affects the quality of segmentation. To address these challenges, we propose an uncertainty-driven edge prompt generation network for medical image segmentation, called UDEG-Net. Specifically, to better adapt to medical image segmentation, we fine-tune the encoder by using Low-Rank Adaptation (LoRA) technology to enhance the encoder's learning capability and capture enriched medical image features. Furthermore, to overcome the limitations of interactive prompts, we develop an auto edge prompt generator to generate edge prompt information and further enhance the structural representation. Finally, to focus on the high-uncertainty edge areas, we introduce an evidence-based uncertainty estimation and a progressive uncertainty-driven loss to drive the auto edge prompt generator to yield robust edge prompt information and reliable segmentation results. Experimental results on three public datasets and one private dataset show that our UDEG-Net outperforms the state-of-the-art medical image segmentation methods. © 2025 IEEE.

关键词： image segmentation

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：