检索结果-内蒙古大学图书馆

Conference on Applications of Machine Learning

作者： Nasrin, Shamima Alom, Md Zahangir Asari, Vijayan K. Taha, Tarek M. Univ Dayton Dept Elect & Comp Engn Dayton OH 45469 USA

ISBN: (纸本)9781510638297

pathological image analysis can benefit significantly from deep learning. In this area, image sizes are quite large and can have different colors and textures. As computational pathology becomes a very promising area of research, it is important to determine which color space provides better results for pathological image segmentation tasks. In this paper, we have considered six different color spaces, namely RGB, Lab, CIE, YCrCb, HSV and HSL for nuclei segmentation tasks where the Recurrent Residual based U-Net (R2U-Net) model is applied. The ISMI-2017 publicly available dataset is used for evaluating the model in this implementation. The Lab color space shows an F1- score of 0.9365, which is the highest segmentation performance when compared to the other color spaces. The Lab color space model shows around 0.38% better performance in term of F1-score compared to the RGB color space for nuclei segmentation tasks. This investigation will provide a clear guidance for researchers in advance of pathological image segmentation and analysis tasks.

关键词： Computational pathology Deep Learning R2U-Net CNN pathological image segmentation

来源：评论

学校读者我要写书评

暂无评论

Category Feature Reconstruction For pathological image segmentation

Category Feature Reconstruction For Pathological Image Segme...

引用

Conference on Medical Imaging - Digital and Computational Pathology

作者： Zhou, Zhibang Xiang, Dehui Shi, Fei Zhu, Weifang Chen, Xinjian Soochow Univ Sch Elect & Informat Engn Suzhou 215006 Peoples R China

ISBN: (纸本)9781510660472;9781510660489

In recent works, more and more attention mechanisms have been used for medical image segmentation, however, attention mechanisms are not very good at distinguishing categories in multi-category medical image segmentation tasks. In this paper, we propose a category feature reconstruction module(CFRM) for multi-category pathological image segmentation of pancreatic adenosquamous carcinoma. Compared with the attention mechanism to enhance the features of the region of interest, the proposed CFRM pays more attention to the reconstruction of category features. The CFRM enables the network not only to highlight the features of the region of interest, but also to increase the discrimination of different categories of features. Based on UNet, the proposed CFRM is added at the top of the encoding path. Compared with other state-of-art methods, both the Dice coefficients and the Iou coefficients of the proposed method have reached the best level on our pancreatic adenosquamous carcinoma segmentation dataset.

关键词： pathological image segmentation Pancreatic Adenosquamous Carcinoma Mult-Category segmentation Category Feature Reconstruction

来源：评论

学校读者我要写书评

暂无评论

DAC-UNet: Dual Attention CNN-Enhanced CswinUnet for Gastric Cancer pathological image segmentation 2

DAC-UNet: Dual Attention CNN-Enhanced CswinUnet for Gastric ...

引用

2024 International Conference on Medical Artificial Intelligence

作者： Hu, Tao Pan, Jingshan Li, Na Tian, Tangbin Zhang, Shengyu Zhang, Lu Han, Yujiao Xu, Jiwei Shandong Comp Sci Ctr Key Lab Comp Power Network & Informat Secur Minist EducNatl Supercomp Ctr Jinan Ctr Nat Supercomp Ctr Jinan Jinan Shandong Peoples R China Qilu Univ Technol Shandong Acad Sci Jinan Peoples R China Shandong Fundamental Res Ctr Comp Sci Shandong Prov Key Lab Comp Power Internet & Serv Jinan Shandong Peoples R China

ISBN: (纸本)9798350377620;9798350377613

Gastric cancer is one of the most lethal cancers. Currently, clinical diagnosis primarily relies on gastroscopic biopsies and the manual experience of doctors to assess the development of lesions in tissue sections. However, pathological screening requires a significant amount of time from specialized pathologists. Due to variations in clinical experience and limitations in medical resources, the detection of gastric cancer still faces challenges. Traditional methods for segmenting gastric cancer images often overlook the hierarchical structure of features and the spatial details, both local and global, in the lesion images. To address the above issues, this paper proposes a hybrid and efficient pathological image segmentation network named DAC-UNet, designed for precise pathological image segmentation tasks. DAC-UNet uses Cswin Transformer blocks to build a hierarchical structure, allowing it to capture global information with less computational complexity. The network also includes multi-scale dual attention skip connections between the encoder and decoder to preserve local spatial details and improve global interactions across different scales. We conducted a thorough theoretical analysis of this method and validated it on a gastric slice dataset. The experimental results demonstrate that our proposed method achieves outstanding performance on both our gastric slice dataset and the MoNuSeg dataset. Specifically, on our gastric slice dataset, we obtained a Dice similarity coefficient (DSC) of 89.42% and an HD95 of 47.24, while on the MoNuSeg dataset, we achieved a DSC of 79.28% and a 95th percentile Hausdorff distance (HD95) of 19.38.

关键词： DAC-UNet pathological image segmentation gastric cancer attention mechanism convolutional neural network multi-scale features Transformer

来源：评论

学校读者我要写书评

暂无评论

pathological image segmentation Method Based on Multiscale and Dual Attention

引用

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS 2024年第1期2024卷

作者： Wu, Jia Niu, Yuxia Ling, Ziqiang Zhu, Jun Gou, Fangfang Guizhou Univ Coll Comp Sci & Technol State Key Lab Publ Big Data Guiyang 550025 Peoples R China Cent South Univ Sch Comp Sci & Engn Changsha 410083 Peoples R China Monash Univ Res Ctr Artificial Intelligence Clayton Vic 3800 Australia Monash Univ Res Ctr Artificial Intelligence Melbourne Vic 3800 Australia Hunan Univ Med Gen Hosp Huaihua Peoples R China Hunan Univ Med Collaborat Innovat Ctr Med Artificial Intelligence Huaihua Peoples R China

Medical images play a significant part in biomedical diagnosis, but they have a significant feature. The medical images, influenced by factors such as imaging equipment limitations, local volume effect, and others, inevitably exhibit issues like noise, blurred edges, and inconsistent signal strength. These imperfections pose significant challenges and create obstacles for doctors during their diagnostic processes. To address these issues, we present a pathology image segmentation technique based on the multiscale dual attention mechanism (MSDAUnet), which consists of three primary components. Firstly, an image denoising and enhancement module is constructed by using dynamic residual attention and color histogram to remove image noise and improve image clarity. Then, we propose a dual attention module (DAM), which extracts messages from both channel and spatial dimensions, obtains key features, and makes the edge of the lesion area clearer. Finally, capturing multiscale information in the process of image segmentation addresses the issue of uneven signal strength to a certain extent. Each module is combined for automatic pathological image segmentation. Compared with the traditional and typical U-Net model, MSDAUnet has a better segmentation performance. On the dataset provided by the Research Center for Artificial Intelligence of Monash University, the IOU index is as high as 72.7%, which is nearly 7% higher than that of U-Net, and the DSC index is 84.9%, which is also about 7% higher than that of U-Net.

关键词： auxiliary diagnosis dual attention mechanism dynamic residual attention multiscale information pathological image segmentation

来源：评论

学校读者我要写书评

暂无评论

A lightweight pathological image segmentation framework based on heterogeneous cross-layer sampling 9

A lightweight pathological image segmentation framework base...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Shi, Hai Chen, Hailong Zhang, Yangyang Wang, Zhengxia Hainan University School of Computer Science and Technology Haikou China

ISBN: (纸本)9798350319804

pathological image segmentation is an essential step in the early detection and diagnosis of various diseases. The features of high resolution, complex background structure, and different tissue shape and size of pathological images, bring great challenges to the segmentation algorithm of pathological images. Deep learning is proved to be an effective method for the segmentation of pathological images. However, there are still some difficulties such as poor capture ability of lesion characteristics and complex model parameters. To solve the above problems, this paper designs a lightweight segmentation network framework for pathological image, called HES-UNet. The framework employs a learning mode of heterogeneous cross-layer sampling and feature capture, which improves computational efficiency while guaranteeing the performance of image segmentation. The way of heterogeneous cross-layer sampling is used in the encoder and decoder to perform only two feature extractions at large and small scales, which greatly reduces the number of parameters of the model. And after drastic dimensional changes, an attention mechanism is adopted for a global feature and local feature capture to improve the learning ability of the network on pathological features and the performance of image segmentation algorithm. Finally, to verify the performance of the proposed segmentation framework, we conducted experiments on three different datasets. The experimental results show that the network outperforms the contrast algorithm on segmentation performance and efficiency to obtain more accurate segmentation results. Compared with the standard UNet3+, the number of parameters can be reduced to 1/39 of the original. It is indicated that our proposed segmentation framework not only has efficient segmentation performance, but also has good generalization ability. © 2023 IEEE.

关键词： attention mechanism cross-layer sampling lightweight pathological image segmentation

来源：评论

学校读者我要写书评

暂无评论

Domain-specific Knowledge Guided Self-supervised Learning for pathological image segmentation

Domain-specific Knowledge Guided Self-supervised Learning fo...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wang, Chenhui Kuang, Hulin Liu, Jin Li, Junjian Yue, Hailin Wang, Jianxin Central South University Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Hunan Changsha China

ISBN: (纸本)9798350337488

Self-supervised learning provides a possible solution to extract effective visual representations from unlabeled pathological images. However, most of the existing methods either do not effectively utilize domain-specific information or are designed and optimized for image classification, resulting in these pre-trained models that may not be optimal for pathological image segmentation. In this paper, we propose DKSL: Domain-specific Knowledge guided Self-supervised Learning, which uses image reconstruction tasks to aid contrastive learning and exploits single-dye stained pathological images after stain separation as domain-specific knowledge to guide the model. Our method provides a novel way to exploit the domain-specific knowledge of pathological images. In contrastive learning, we add single-dye stained images as an expansion of the original positive samples to the contrastive learning process to preserve more global semantic information. In image reconstruction, the model is forced to focus on local image details relevant to downstream tasks by reconstructing single-dye stained images from the representation extracted by the encoder of contrastive learning. Finally, the encoder and decoder from the pre-training stage are fine-tuned by the downstream segmentation task. Fine-tuning experimental results demonstrate that DKSL outperforms state-of-the-art methods with Dices of 90.50% and 79.68% on two publicly available datasets, GlaS and MoNuSeg, respectively. © 2023 IEEE.

关键词： Contrastive learning Domain-specific knowledge image reconstruction pathological image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Pooling-Convolution for pathological image Multi-class segmentation

Enhanced Pooling-Convolution for Pathological Image Multi-cl...

引用

Conference on Medical Imaging - Digital and Computational Pathology

作者： Wu, Hao Chen, Xinjian Zhu, Weifang Shi, Fei Xiang, Dehui Soochow Univ Sch Elect & Informat Engn Suzhou 215006 Jiangsu Peoples R China

ISBN: (纸本)9781510660472;9781510660489

Recent studies have achieved a great success in medical image segmentation, but do not perform well in the application of pathological image segmentation. In traditional segmentation networks, some important features may be lost during the encoding process. In this paper, an Enhanced Pooling-Convolution (EPC) module is proposed to add weights to the space and channels of features in the encoding process. EPC evaluates the differences and complementarities of features between max pooling, average pooling, and convolution in the pooling process. Channel based attention is further used to weight different channels. VGG16 is used as the backbone in the U-shaped network, and the number of channels for upsampling is reduced during decoding process. It shows that the pooling and convolution block with three consecutive convolution layers can be replaced with the EPC module. Experimental results shows that the average DICE coefficient of our method is 2.55% higher than that of U-Net.

关键词： pathological image segmentation Deep Learning Enhanced Pooling-Convolution Medical image Processing

来源：评论

学校读者我要写书评

暂无评论

TransRNetFuse: a highly accurate and precise boundary FCN-transformer feature integration for medical image segmentation

引用

COMPLEX & INTELLIGENT SYSTEMS 2025年第5期11卷 1-19页

作者： Li, Baotian Zhou, Jing Gou, Fangfang Wu, Jia Shandong Youth Univ Polit Sci Sch Informat Engn Jinan 250103 Peoples R China Hunan Univ Med Gen Hosp Huaihua 418000 Peoples R China Guizhou Univ Coll Comp Sci & Technol State Key Lab Publ Big Data Guiyang 550025 Peoples R China Monash Univ Res Ctr Artificial Intelligence Melbourne Vic 3800 Australia

Imaging examinations are integral to the diagnosis and treatment of cancer. Nevertheless, the intricate nature of medical images frequently necessitates that physicians follow time-consuming and potentially fallible diagnostic procedures. In response to these challenges, deep learning-based image segmentation technology has emerged as a potent instrument for aiding physicians in navigating diagnostic complexities by extracting pivotal information from extensive sets of medical images. Nonetheless, the majority of existing models prioritize overall high accuracy, often overlooking the sensitivity to local salient features and the precision of segmentation boundaries. This oversight limits the full realization of the practical utility of deep learning models in clinical settings. This study introduces a novel pathological image segmentation method, termed TransRNetFuse, which incorporates stepwise feature aggregation and a residual fully convolutional network architecture. The objective of this method is to address the issues associated with the extraction of local key features and the accurate delineation of boundaries in medical image segmentation. The proposed model achieves enhanced overall performance by merging a fully convolutional network branch with a Transformer branch and utilizing residual blocks along with dense U-net skip connections. It prevents attentional dispersion by emphasizing local features, and further employs an automatic augmentation strategy to identify the optimal data augmentation scheme, which is particularly advantageous for small-sample datasets. Furthermore, this paper introduces an edge enhancement loss function to enhance the model's sensitivity to tumor boundaries. A dataset comprising 2164 pathological images, provided by Hunan Medical University General Hospital, was utilized for model training. The experimental results indicate that the proposed method outperforms existing techniques, such as MedT, in terms of both accuracy and ed

关键词： Artificial intelligence pathological image segmentation FCN-transformer Edge-enhancement

来源：评论

学校读者我要写书评

暂无评论

Colon tissue image segmentation with MWSI-NET

引用

MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING 2022年第3期60卷 727-737页

作者： Cheng, Hao Wu, Kaijie Tian, Jie Ma, Kai Gu, Chaocheng Guan, Xinping Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China Shanghai Jiao Tong Univ Dept Automat Shanghai Peoples R China

Developments in deep learning have resulted in computer-aided diagnosis for many types of cancer. Previously, pathologists manually performed the labeling work in the analysis of colon tissues, which is both time-consuming and labor-intensive. Results are easily affected by subjective conditions. Therefore, it is beneficial to identify the cancerous regions of colon cancer with the assistance of computer-aided technology. pathological images are often difficult to process due to their irregularity, similarity between cancerous and non-cancerous tissues and large size. We propose a multi-scale perceptual field fusion structure based on a dilated convolutional network. Using this model, a structure of dilated convolution kernels with different aspect ratios is inserted, which can process cancerous regions of different sizes and generate larger receptive fields. Thus, the model can fuse detailed information at different scales for better semantic segmentation. Two different attention mechanisms are adopted to highlight the cancerous areas. A large, open-source dataset was used to verify improved efficacy when compared to previously disclosed methods.

关键词： pathological image segmentation Dilated convolution Multi-scale Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

CoUNet: An End-to-End Colonoscopy Lesion image segmentation and Classification Framework 20

CoUNet: An End-to-End Colonoscopy Lesion Image Segmentation ...

引用

Proceedings of the 2020 4th International Conference on Video and image Processing

作者： Wendong Xu Hong Liu Xiangdong Wang Hanqiang Ouyang Yueliang Qian Institute of Computing Technology Chinese Academy of Sciences China Chinese Academy of Sciences China Peking University Third Hospital China

ISBN: (纸本)9781450389075

Colonoscopy tissue slides examination can find cells of early-stage colon tumor, which is important to clinical diagnosis. DigestPath2019 in MICCAI is a recent challenge to automatically segment colonoscopy lesion regions and classify the whole slide image WSI into benign or malignant. To obtain high accuracy and refined boundary information for lesion segmentation, this paper proposes an end-to-end segmentation and classification framework CoUNet, which combines a segmentation model D-ResUNet and CRFasRNN. Our D-ResUNet combines Deformable ResNet and UNet structure, which modifies the last two residual blocks of ResNet into deformable residual blocks. This strategy can ensure extracting high-level semantic information and retaining low-level cell morphologic information to improve the edge and shape predictions. The connected CRFasRNN formulates the CRF as RNN to reduce noise prediction of segmentation model and refine final segmentation performance. We also propose WSI-level color normalization strategy to normalize each patch in WSI to relieve various staining problem and balanced dice loss for solving data-imbalanced problem. Experimental results on DigestPath2019 show the efficiency and robustness of our proposed framework.

关键词： colonoscopy pathological image segmentation WSI

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：