检索结果-内蒙古大学图书馆

3D medical image segmentation using the serial-parallel convolutional neural network and transformer based on cross-window self-attention

引用

CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY 2025年第2期10卷 337-348页

作者： Yu, Bin Zhou, Quan Yuan, Li Liang, Huageng Shcherbakov, Pavel Zhang, Xuming Huazhong Univ Sci & Technol Coll Life Sci & Technol Dept Biomed Engn Wuhan Peoples R China Huazhong Univ Sci & Technol Wuhan Childrens Hosp Wuhan Maternal & Child Healthcare Hosp Tongji Med CollDept Ultrasound Imaging Wuhan Peoples R China Huazhong Univ Sci & Technol Union Hosp Tongji Med Coll Dept Urol Wuhan Peoples R China Russian Acad Sci Inst Control Sci Moscow Russia

Convolutional neural network (CNN) with the encoder-decoder structure is popular in medical image segmentation due to its excellent local feature extraction ability but it faces limitations in capturing the global feature. The transformer can extract the global information well but adapting it to small medical datasets is challenging and its computational complexity can be heavy. In this work, a serial and parallel network is proposed for the accurate 3D medical image segmentation by combining CNN and transformer and promoting feature interactions across various semantic levels. The core components of the proposed method include the cross window self-attention based transformer (CWST) and multi-scale local enhanced (MLE) modules. The CWST module enhances the global context understanding by partitioning 3D images into non-overlapping windows and calculating sparse global attention between windows. The MLE module selectively fuses features by computing the voxel attention between different branch features, and uses convolution to strengthen the dense local information. The experiments on the prostate, atrium, and pancreas MR/CT image datasets consistently demonstrate the advantage of the proposed method over six popular segmentation models in both qualitative evaluation and quantitative indexes such as dice similarity coefficient, Intersection over Union, 95% Hausdorff distance and average symmetric surface distance.

关键词： artificial intelligence image segmentation medical image processing

来源：评论

学校读者我要写书评

暂无评论

Tea Disease Recognition Based on image segmentation and Data Augmentation

引用

IEEE ACCESS 2025年 13卷 19664-19677页

作者： Li, Ji Liao, Chenyi Hunan Agr Univ Coll Biosci & Biotechnol Changsha 410128 Peoples R China Foshan Univ Sch Environm & Chem Engn Foshan 528000 Peoples R China

Accurate identification of tea leaf diseases is crucial for intelligent tea cultivation and monitoring. However, the complex environment of tea plantations-affected by weather variations and uneven lighting-poses significant challenges for building effective disease recognition models using raw field-captured images. To address this, we propose a method that combines two-stage image segmentation with an improved conditional generative adversarial network (IC-GAN). The two-stage segmentation approach, integrating graph cuts and support vector machines (SVM), effectively isolates disease regions from complex backgrounds. The IC-GAN augments the dataset by generating high-quality synthetic disease images for model training. Finally, an Inception Embedded Pooling Convolutional Neural Network (IDCNN) is developed for disease recognition. Experimental results demonstrate that the segmentation method improves recognition accuracy from 53.36% to 75.63%, while the IC-GAN increases the dataset size. The IDCNN achieves 97.66% accuracy, 97.36% recall, and a 96.98% F1 score across three types of tea diseases. Comparative evaluations on two additional datasets further confirm the method's robustness and accuracy, offering a practical solution to reduce tea production losses and improve quality.

关键词： Diseases image segmentation Accuracy Feature extraction Support vector machines Data augmentation Lesions Plant diseases Object recognition Generative adversarial networks Conditional generative adversarial network disease recognition deep learning image generation

来源：评论

学校读者我要写书评

暂无评论

Fast Recognition of Bright Spot Structures in Divertor Region Based on Improved DeepLabv3+ image segmentation on EAST

引用

PROCESSES 2025年第3期13卷 899-899页

作者： Wu, Yahao Ye, Yang Yang, Jianhua Tan, Mingsheng Zhong, Fubin Qu, Chengming Wang, Xiaopeng Wang, Chao Kong, Defeng Anhui Univ Sci & Technol Sch Mat Sci & Engn Huainan 232001 Peoples R China Hefei Comprehens Natl Sci Ctr Anhui Energy Lab Inst Energy Hefei 230031 Peoples R China Chinese Acad Sci Hefei Inst Phys Sci Inst Plasma Phys Hefei 230031 Peoples R China

The presence of a bright spot structure in the divertor region during the discharge process, indicative of localized overheating, has been observed through multi-band and high-speed endoscope diagnostic on the Experimental Advanced Superconducting Tokamak (EAST). This localized deposition of hyperthermal heat flux can lead to erosion and melting of the target plate material, thereby posing a significant risk to the safe operation of the device. Moreover, it may introduce impurities into the main plasma, negatively impacting plasma performance. Therefore, real-time monitoring of the divertor and rapid identification of localized overheating regions during experiments are crucial. In this context, this paper proposes an improved DeepLabv3+-based highlight structure image-segmentation algorithm, which uses minimum value, image difference method, and Prewitt operator for dataset preprocessing. In order to realize the rapid identification of local overheated regions, this paper introduces the application of the improved DeepLabv3+ neural network algorithm based on MobileNetV2 as the backbone network in the bright spot structure segmentation task for the first time. The results show that the algorithm achieves a 65.36% average crosslinking rate (mIoU), 78.75% accuracy, 0.78 s per-iteration processing time, and 22.4 MB parameter size. This provides substantial advantages in terms of reduced computing and memory resources and real-time detection performance. Ultimately, the method proposed in this paper enables the rapid identification of the bright spot structure in the localized overheating region of the divertor on the EAST;it identifies areas of overheating and prevents damage to the divertor or other critical components due to overheating, ensuring safe operation of the device.

关键词： EAST tokamak bright spot DeepLabv3+ image segmentation MobileNetV2 computational efficiency safety protection

来源：评论

学校读者我要写书评

暂无评论

Laser rapid scanning strategy for bitmaps via image segmentation utilizing grey wolf optimizer

引用

OPTICS AND LASER TECHNOLOGY 2025年 181卷

作者： Zhang, Tian Rong, Youmin Liu, Xiufeng Cao, Siyang Liang, Yufeng Wu, Congyi Zhang, Guojun Huang, Yu Huazhong Univ Sci & Technol State Key Lab Digital Mfg Equipment & Technol Wuhan Peoples R China Huazhong Univ Sci & Technol Sch Mech Sci & Engn Wuhan Peoples R China Hubei Univ Educ Sch Phys & Electromech Engn Wuhan Peoples R China HGLaser Engn Co Ltd Wuhan 430223 Peoples R China

A novel laser scanning processing methodology is introduced for bitmap aimed at reducing time losses associated with multiple galvanometer scanning cycles. The Multi-threshold Otsu method, resolved via the Grey Wolf optimizer (GWO), effectively segments the target image into background and target regions. To handle the resulting threshold distribution, four mapping functions with distinct growth trends are to adjust pixel gray values within specified regions, thereby modulating scanning input powers accordingly. An experimental investigation was conducted utilizing a galvanometer scanner and a set of sample images. A comparative analysis of the image segmentation outcomes demonstrates that the GWO consistently delivers robust segmentation results and superior solution stability compared to other methodologies. Furthermore, when combined with the adaptive power mapping functions, this new approach shows remarkable adaptability to a range of graphical representations. Ultimately, the scanning process duration is reduced by as much as 89 % when contrasted with traditional point carving and layer-by-layer scanning. This discovery signifies that this approach holds significant promise for enhancing productivity in laser processing applications.

关键词： Laser marking image segmentation Grey wolf optimization Galvanometer scanner

来源：评论

学校读者我要写书评

暂无评论

CAML-PSPNet: A Medical image segmentation Network Based on Coordinate Attention and a Mixed Loss Function

引用

SENSORS 2025年第4期25卷 1117-1117页

作者： Li, Yuxia Li, Peng Wang, Hailing Gong, Xiaomei Fang, Zhijun Shanghai Univ Engn Sci Sch Elect & Elect Engn Shanghai 201620 Peoples R China Tongji Univ Sch Med Shanghai Pulm Hosp Dept Radiat Oncol Shanghai 200433 Peoples R China

The problems of missed segmentation with fuzzy boundaries of segmented regions and small regions are common in segmentation tasks, and greatly decrease the accuracy of clinicians' diagnosis. For this, a new network based on PSPNet, using a coordinate attention mechanism and a mixed loss function for segmentation (CAML-PSPNet), is proposed. Firstly, the coordinate attention module splits the input feature map into horizontal and vertical directions to locate the edge position of the segmentation target. Then, a Mixed Loss function (MLF) is introduced in the model training stage to solve the problem of the low accuracy of small-target tumor segmentation. Finally, the lightweight MobilenetV2 is utilized in backbone feature extraction, which largely reduces the model's parameter count and enhances computation speed. Three datasets-PrivateLT, Kvasir-SEG and ISIC 2017-are selected for the experimental part, and the experimental results demonstrate significant enhancements in both visual effects and evaluation metrics for the segmentation achieved by CAML-PSPNet. Compared with Deeplabv3, HrNet, U-Net and PSPNet networks, the average intersection rates of CAML-PSPNet are increased by 2.84%, 3.1%, 5.4% and 3.08% on lung cancer data, 7.54%, 3.1%, 5.91% and 8.78% on Kvasir-SEG data, and 1.97%, 0.71%, 3.83% and 0.78% on ISIC 2017 data, respectively. When compared to other methods, CAML-PSPNet has the greatest similarity with the gold standard in boundary segmentation, and effectively enhances the segmentation accuracy for small targets.

关键词： lung tumor PSPNet attention mechanism mixed loss image segmentation

来源：评论

学校读者我要写书评

暂无评论

Wasserstein distance-based fuzzy C-means clustering in Riemannian manifold feature space for image segmentation

引用

SIGNAL image AND VIDEO PROCESSING 2025年第1期19卷 1-14页

作者： Wu, Chengmao Zheng, Jia Xian Univ Posts & Telecommun Sch Elect Engn Xian 710121 Peoples R China

To ensure the accuracy of image segmentation, selecting appropriate image features is crucial. The existing image segmentation methods mainly utilize spectral features of images to achieve image segmentation, which have low segmentation accuracy and weak robustness, and are difficult to adapt to the needs of complex image segmentation. Therefore, this paper proposes a new robust fuzzy clustering image segmentation based on Wasserstein distance in the Riemannian manifold feature space. At first, the spectral features of pixels in the neighborhood window around the current pixel are constructed into a Gaussian normal distribution structure model, and the original image is mapped to the Riemannian manifold feature space to achieve Riemannian manifold feature modeling of image feature information. Secondly, the Wasserstein distance is used to measure the difference between two Gaussian Riemannian manifolds, and a robust fuzzy clustering method for image segmentation is proposed in Riemannian manifold feature space. Finally, the local convergence of the algorithm is proved using the Zangwill theorem and bordered Hessian matrix. The experimental results demonstrate that the proposed algorithm has good segmentation performance and strong noise resistance. Compared with existing segmentation algorithms based on spectral feature space and Riemannian manifold feature space, this proposed algorithm is more effective and robust in segmenting images with or without noise.

关键词： image segmentation Riemannian manifold Gaussian distribution Fuzzy C-means clustering Wasserstein distance Robustness

来源：评论

学校读者我要写书评

暂无评论

Pre-trained SAM as data augmentation for image segmentation

引用

CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY 2025年第1期10卷 268-282页

作者： Wu, Junjun Rao, Yunbo Zeng, Shaoning Zhang, Bob Univ Elect Sci & Technol China Yangtze Delta Reg Inst Huzhou Huzhou Peoples R China Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu Peoples R China Univ Macau Dept Comp & Informat Sci Pattern Anal & Machine Intelligence Res Grp Macau Peoples R China

Data augmentation plays an important role in training deep neural model by expanding the size and diversity of the dataset. Initially, data augmentation mainly involved some simple transformations of images. Later, in order to increase the diversity and complexity of data, more advanced methods appeared and evolved to sophisticated generative models. However, these methods required a mass of computation of training or searching. In this paper, a novel training-free method that utilises the Pre-Trained Segment Anything Model (SAM) model as a data augmentation tool (PTSAM-DA) is proposed to generate the augmented annotations for images. Without the need for training, it obtains prompt boxes from the original annotations and then feeds the boxes to the pre-trained SAM to generate diverse and improved annotations. In this way, annotations are augmented more ingenious than simple manipulations without incurring huge computation for training a data augmentation model. Multiple comparative experiments on three datasets are conducted, including an in-house dataset, ADE20K and COCO2017. On this in-house dataset, namely Agricultural Plot segmentation Dataset, maximum improvements of 3.77% and 8.92% are gained in two mainstream metrics, mIoU and mAcc, respectively. Consequently, large vision models like SAM are proven to be promising not only in image segmentation but also in data augmentation.

关键词： data augmentation image segmentation large model segment anything model

来源：评论

学校读者我要写书评

暂无评论

Tongue-LiteSAM: A Lightweight Model for Tongue image segmentation With Zero-Shot

引用

IEEE ACCESS 2025年 13卷 11689-11703页

作者： Tan, Daiqing Zang, Hao Zhang, Xinyue Gao, Han Wang, Ji Wang, Zaijian Zhai, Xing Li, Huixia Tang, Yan Han, Aiqing Beijing Univ Chinese Med Sch Management Beijing 100029 Peoples R China Beijing Univ Chinese Med Sch Nursing Beijing 100029 Peoples R China Beijing Univ Chinese Med Sch Humanities Beijing 100029 Peoples R China Beijing Univ Chinese Med Natl Inst TCM Constitut & Prevent Med Beijing 100029 Peoples R China Beijing Univ Chinese Med Affiliated Hosp 3 Beijing 100029 Peoples R China

Objective: Tongue image segmentation is a crucial step in the intelligent recognition of tongue diagnosis in Traditional Chinese Medicine (TCM). Existing deep learning-based tongue image segmentation models face issues such as poor versatility and insufficient expressiveness in zero-shot tasks. This study aims to construct an efficient model with zero-shot suitable for tongue image segmentation in TCM. Methods: We developed the Tongue-LiteSAM model by improving the SAM (Segment Anything Model) framework to suit tongue segmentation. Based on the basic SAM model, the improvement involved modifying the image encoder by integrating two lightweight ViT-Tiny image encoders, effectively reducing the model's parameter count. Additionally, data perturbation techniques were employed to enhance the zero-shot segmentation capability of the model and ensure robust performance across different data sources. Results: Experiments conducted on six distinct tongue image datasets demonstrated that the Tongue-LiteSAM model outperformed traditional convolutional neural network-based models and transformers, the original SAM model, and other related improved models in tongue image segmentation tasks. Conclusion: The Tongue-LiteSAM model provides a more objective and consistent solution for tongue diagnosis, and has better zero-shot segmentation capabilities. By optimizing the model structure and data processing strategies, the accuracy and practicality of tongue diagnosis models are effectively improved, offering new technical support for the modernization and precision of TCM tongue diagnosis.

关键词： image segmentation Tongue Training Data models Computational modeling Accuracy Medical diagnostic imaging Transformers Deep learning Feature extraction Segment anything model tongue image segmentation traditional Chinese medicine

来源：评论

学校读者我要写书评

暂无评论

A hybrid approach for MRI brain image segmentation using KIFECM-IPSO algorithm

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 268卷

作者： Verma, Deepa Verma, Hanuman Tiwari, Pawan Kumar Inst Engn & Technol Comp Sci & Engn Dept Lucknow 226021 Uttar Pradesh India Bareilly Coll Dept Math Bareilly 243005 Uttar Pradesh India Dr APJ Abdul Kalam Tech Univ Fac Engn & Technol Lucknow 226031 Uttar Pradesh India

A hybrid approach for brain magnetic resonance imaging (MRI) image segmentation is proposed, that combines the intuitionistic particle swarm optimization (IPSO) algorithm and the kernel intuitionistic fuzzy entropy cmeans (KIFECM) to overcome the local minima trapping problem of KIFECM. In terms of intuitionistic fuzzification, intuitionistic PSO (IPSO) is a global optimization technique that investigates random search with candidate solution. The hybrid KIFECM-IPSO technique combines the best aspects of IPSO and KIFECM algorithms to improve clustering outcomes and prevent the local minima entrapment issue. The performance of the algorithm can be evaluated using various measures such as the similarity measure, average similarity measure, jaccard coefficient, false negative ratio and false positive ratio on the real brain data and simulated brain data. The results have been compared with KIFECM, PSO-KIFCM, FEC, PSO and FCM-PSO algorithms to determine the effectiveness of the proposed algorithm and the experimental results shows that the proposed KIFECM-IPSO perform better. Friedman's statistical test is also carried out to demonstrate that the performance of the proposed algorithm is not only better but the performance difference is statistically significant also.

关键词： image segmentation Intuitionistic fuzzy sets Kernel intuitionistic fuzzy entropy c -means algorithm Kernel methods Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Constrained multi-scale dense connections for biomedical image segmentation

引用

PATTERN RECOGNITION 2025年 158卷

作者： Zhang, Jiawei Zhang, Yanchun Qiu, Hailong Wang, Tianchen Li, Xiaomeng Zhu, Shanfeng Huang, Meiping Zhuang, Jian Shi, Yiyu Xu, Xiaowei Pengcheng Lab Dept New Network Shenzhen Guangdong Peoples R China Southern Med Univ Guangdong Prov Peoples Hosp Guangdong Cardiovasc Inst Guangdong Acad Med SciGuangdong Prov Key Lab Sout Guangzhou 510080 Peoples R China Zhejiang Normal Univ Sch Comp Sci Jinhua Peoples R China Univ Notre Dame Dept Comp Sci & Engn Notre Dame IN USA Victoria Univ Coll Engn & Sci Melbourne Australia Fudan Univ Inst Sci & Technol Brain Inspired Intelligence Shanghai Peoples R China Fudan Univ MOE Frontiers Ctr Brain Sci Shanghai Peoples R China Fudan Univ Key Lab Computat Neurosci & Brain Inspired Intelli Minist Educ Shanghai Peoples R China Shanghai Key Lab Intelligent Informat Proc Shanghai Peoples R China Shanghai Inst Artificial Intelligence Algorithm Shanghai Peoples R China Zhangjiang Fudan Int Innovat Ctr Shanghai Peoples R China Hong Kong Univ Sci & Technol Dept Elect & Comp Engn Hong Kong Peoples R China

Multi-scale dense connection has been widely used in the biomedical image community to enhance the segmentation performance. In this way, features from all or most scales are aggregated or iteratively fused. However, by analyzing the details, we discover that some connections involving distant scales may not contribute to, or even harm, the performance, while they always introduce a noticeable increase in computational cost. In this paper, we propose constrained multi-scale dense connections (CMDC) for biomedical image segmentation. In contrast to current general lightweight approaches, we first introduce two methods, a naive method and a network architecture search (NAS)-based method, to remove redundant connections and verify the optimal connection configuration, thereby improving overall efficiency and accuracy. The results demonstrate that the two approaches obtain a similar optimal configuration in which most features at the adjacent scales are connected. Then, we applied the optimal configuration to various backbone networks to build constrained multi-scale dense networks (CMD-Net). Experimental results evaluated on eight image segmentation datasets covering biomedical images and natural images demonstrate the effectiveness of CMDNet across a variety of backbone networks (FCN, U-Net, DeepLabV3, SegNet, FCNsa, ConvUNeXt) with a much lower increase in computational cost. Furthermore, CMD-Net achieves state-of-the-art performance on four publicly available datasets. We believe that the CMDC method can offer valuable insight for ways to engage in dense connectivity at multiple scales within communities. The source code has been made available at https://***/JerRuy/CMD-Net.

关键词： Multi-scale dense connections image segmentation Network architecture search Feature fusion

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：