检索结果-内蒙古大学图书馆

Applying deep Learning and Heatmap Techniques for Sinusitis diagnosis Using Enhanced 3-d Image segmentation

IEEE TRANSACTIONS ON INSTRUMENTATION ANd MEASUREMENT 2025年 74卷

作者： Huang, Pin-Siang Horng, Shi-Jinn Yang, Chia-Jung Chen, Hongmei Zhou, Wanlei Natl Taiwan Univ Sci & Technol Dept Comp Sci & Informat Engn Taipei 10607 Taiwan Asia Univ Dept Comp Sci & Informat Engn Taichung 41354 Taiwan China Med Univ China Med Univ Hosp Dept Med Res Taichung Taiwan Univ Technol Sydney Sch Comp Sci Ultimo NSW 2007 Australia Taitung MacKay Mem Hosp Dept Radiol Taitung 950 Taiwan Southwest Jiaotong Univ Sch Comp & Artificial Intelligence Chengdu 610032 Peoples R China City Univ Macau Fac Data Sci Macau Peoples R China

Sinusitis, characterized by inflammation of the sinus cavities, presents diagnostic challenges due to the subjective and time-consuming nature of manual computed tomography (CT) scan annotations. This study introduces a deep learning (dL) method combined with heatmap analysis to automate 3-d segmentation of sinusitis in CT images. The proposed approach reduces the dependency on fully segmented annotations, instead requiring only binary classification labels during training. A classification model identifies areas likely affected by inflammation, highlighted by gradient-weighted class activation mapping (Grad-CAM) to produce heatmaps, which are refined using a watershed algorithm for precise segmentation. This approach reduces annotation preparation time from 30 min to under 1 min while achieving a dice similarity coefficient (dSC) of 90.04%. Built on the EfficientNet-B2 architecture, the model outperforms state-of-the-art methods like U-Net, U-Net++, and statistical-based approaches. Additionally, a novel instrumentation system integrated with CT scanners calculates inflammation areas in real time, streamlining diagnostic workflows. This method accelerates the process while improving the consistency and reliability of sinusitis diagnosis, potentially transforming clinical practices with advanced image processing techniques.

关键词： Image segmentation Computed tomography deep learning Watersheds Three-dimensional displays Accuracy Medical diagnostic imaging Convolutional neural networks Annotations Training 3-d segmentation computed tomography (CT) scan deep learning (dL) diagnostic automation dice similarity coefficient (dSC) gradient-weighted class activation mapping (GRAd-CAM) image annotation medical image processing sinusitis watershed algorithm

来源：评论

学校读者我要写书评

暂无评论

3d segmentation of the Whole Heart Vasculature Using Improved Multi-threshold Otsu and White Top-Hat Scale Space Hessian Based Vessel Filter

3D Segmentation of the Whole Heart Vasculature Using Improve...

引用

IEEE Symposium Series on Computational Intelligence (IEEE SSCI)

作者： Bukenya, Faiza Ehling, Josef Kalema, Abdu Kiweewa Eyoh, Imo Robert, John Bai, Li Univ Nottingham Sch Comp Sci Nottingham England Rhein Westfal TH Aachen Dept Expt Mol Imaging Aachen Germany Univ Technol Malaysia Dept Comp Sci Johor Baharu Malaysia

ISBN: (纸本)9781509042401

Quantification of vessel density helps to know the stage of the disease during diagnosis and patient's response to treatment. However, this requires presence of all vessels in the image. The available segmentation techniques that are manual based are prone to errors, tiresome and slow, while some that are automated do face difficulty in distinguishing the vessel tissue from the non-vessel tissue due to the presence of intensity inhomogeneity and noise in images. Therefore, there is need for improved segmentation methods that can extract all sizes of vessels for better quantification of the vessel density and improved decision making during diagnosis. In this paper, a 3d hybrid approach for segmentation has been developed, based on white top hat scale space hessian vessel enhancement filter and multithreshold Otsu method. The hybrid method can address the intensity inhomogeneity, as a result, more vessels of different sizes are detected. The method is also robust and able to detect abnormalities in the vessels.

关键词： 3-d segmentation Heart Vessels

来源：评论

学校读者我要写书评

暂无评论

SimLVSeg: Simplifying Left Ventricular segmentation in 2-d+Time Echocardiograms With Self- and Weakly Supervised Learning

引用

ULTRASOUNd IN MEdICINE ANd BIOLOGY 2024年第12期50卷 1945-1954页

作者： Maani, Fadillah Ukaye, Asim Saadi, Nada Saeed, Numan Yaqub, Mohammad Mohamed bin Zayed Univ Artificial Intelligence Abu Dhabi U Arab Emirates

Objective: Achieving reliable automatic left ventricle (LV) segmentation from echocardiograms is challenging due to the inherent sparsity of annotations in the dataset, as clinicians typically only annotate two specific frames for diagnostic purposes. Here we aim to address this challenge by introducing simplified LV segmentation (SimLVSeg), a novel paradigm that enables video-based networks for consistent LV segmentation from sparsely annotated echocardiogram videos. Methods: SimLVSeg consists of two training stages: (i) self-supervised pre-training with temporal masking, which involves pre-training a video segmentation network by capturing the cyclic patterns of echocardiograms from largely unannotated echocardiogram frames, and (ii) weakly supervised learning tailored for LV segmentation from sparse annotations. Results: We extensively evaluated SimLVSeg using EchoNet-dynamic, the largest echocardiography dataset. SimLVSeg outperformed state-of-the-art solutions by achieving a 93.32% (95% confidence interval: 93.21 -93.43%) dice score while being more efficient. We further conducted an out-of-distribution test to showcase SimLVSeg's generalizability on distribution shifts (CAM US dataset). Conclusion: Our findings show that SimLVSeg exhibits excellent performance on LV segmentation with a relatively cheaper computational cost. This suggests that adopting video-based networks for LV segmentation is a promising research direction to achieve reliable LV segmentation. Our code is publicly available at https://***/Bio MedIA-MBZUAI/SimLVSeg.

关键词： Left ventriclular segmentation Sparse video segmentation Self-supervision Temporal masking 3-d segmentation Super image

来源：评论

学校读者我要写书评

暂无评论

3d segmentation of the Whole Heart Vasculature Using Improved Multi-threshold Otsu and White Top-Hat Scale Space Hessian Based Vessel Filter

3D Segmentation of the Whole Heart Vasculature Using Improve...

引用

IEEE Symposium Series on Computational Intelligence

作者： Faiza Bukenya Josef Ehling Abdu Kiweewa Kalema Imo Eyoh John Robert Li Bai School of Computer Science University of Nottingham United Kingdom Department of Experimental Molecular Imaging RWTH - Aachen University Germany Department of Computer Science University of Technology in Malaysia Johor Bahru Malaysia

ISBN: (纸本)9781509042418

Quantification of vessel density helps to know the stage of the disease during diagnosis and patient's response to treatment. However, this requires presence of all vessels in the image. The available segmentation techniques that are manual based are prone to errors, tiresome and slow, while some that are automated do face difficulty in distinguishing the vessel tissue from the non-vessel tissue due to the presence of intensity inhomogeneity and noise in images. Therefore, there is need for improved segmentation methods that can extract all sizes of vessels for better quantification of the vessel density and improved decision making during diagnosis. In this paper, a 3d hybrid approach for segmentation has been developed, based on white top hat scale space hessian vessel enhancement filter and multi-threshold Otsu method. The hybrid method can address the intensity inhomogeneity, as a result, more vessels of different sizes are detected. The method is also robust and able to detect abnormalities in the vessels.

关键词： 3-d segmentation Heart Vessels

来源：评论

学校读者我要写书评

暂无评论

Geometrical-Based displacement Measurement With Pseudostereo Monocular Camera on Bidirectional Cascaded Linear Actuator

引用

IEEE-ASME TRANSACTIONS ON MECHATRONICS 2021年第4期26卷 1923-1931页

作者： Lee, denzel Liu, Jingmin Lim, Ryan Chan, Jie Lin Foong, Shaohui Singapore Univ Technol & Design Engn Prod Dev Pillar Singapore 487372 Singapore

This article details the development of a geometrical-based displacement extraction framework capable of automatically extracting critical infrastructure measurements in one sequence. The framework is a novel rail viaduct bearing inspection pipeline implemented on Bearing Inspector for Narrow-space Observation Version 2 (BINOv2). BINOv2 is a tethered custom unmanned aerial vehicle system utilized to supplant labor-intensive pipelines and enhance inspection accuracy of infrastructure conditions in confined remote locations. The algorithm accepts stereoscopic images taken from a single monocular camera on a bidirectional cascaded linear actuator system in a rack-and-pinion configuration. A point cloud model generated from the image sets then runs through a hierarchical neural network for 3-d segmentation to extract targeted regions of interest. Our training pipeline generates and forms the full model's training dataset using only a small sample of real point clouds. The point cloud generated is inadequate to form the full bearing geometry profile. Therefore, the proposed framework projects best-fit circles based on the point cloud curvature to form the full bearing geometry profile so that the required displacement measurement is available for extraction. Several experiments were conducted on a mock-up and actual operational site to validate the proposed framework's accuracy, its robustness and comparison with other state-of-the-art alternatives.

关键词： Cameras Actuators Three-dimensional displays Inspection Feature extraction Force Bidirectional control Actuators condition monitoring displacement measurement learning (artificial intelligence) 3-d segmentation unmanned aerial vehicles (UAVs)

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC 3-d SKELETON-BASEd segmentation OF LIVER VESSELS FROM MRI ANd CT FOR COUINAUd REPRESENTATION 25

AUTOMATIC 3-D SKELETON-BASED SEGMENTATION OF LIVER VESSELS F...

引用

25th IEEE International Conference on Image Processing (ICIP)

作者： Lebre, Marie-Ange Vacavant, Antoine Grand-Brochier, Manuel Merveille, Odyssee Chabrot, Pascal Abergel, Armand Magnin, Benoit UCA CNRS SIGMA Inst PascalUMR 6602 Aubiere France Univ Strasbourg CNRS ICube UMR 7357 Strasbourg France Ctr Hosp Univ Clermont Ferrand France

ISBN: (纸本)9781479970612

Medical imaging systems as MRI and CT, provide useful information on the liver vascular network for surgical planning. However, manual segmentation is difficult and time consuming;an automatic procedure could thus help radiologists in their analysis. CT have been considered superior for hepatic vessels, but they are also visible in MRI, especially when a contrast agent is used. This study proposes an automatic 3-d skeleton-based segmentation for liver vessels. We identify vascular network to propose a segmentation of Couinaud anatomical segments. Experimental results show that the proposed method can segment liver vessels on both modalities with faithful 3-d representations.

关键词： 3-d segmentation liver CT-MRI vessels skeleton

来源：评论

学校读者我要写书评

暂无评论

Automatic segmentation of all lower limb muscles from high-resolution magnetic resonance imaging using a cascaded three-dimensional deep convolutional neural network

引用

JOURNAL OF MEdICAL IMAGING 2019年第4期6卷 044009页

作者： Ni, Renkun Meyer, Craig H. Blemker, Silvia S. Hart, Joseph M. Feng, Xue Springbok Inc Charlottesville VA 22903 USA Univ Virginia Dept Biomed Engn Charlottesville VA 22904 USA Univ Virginia Dept Kinesiol Charlottesville VA USA

High-resolution magnetic resonance imaging with fat suppression can obtain accurate anatomical information of all 35 lower limb muscles and individual segmentation can facilitate quantitative analysis. However, due to limited contrast and edge information, automatic segmentation of the muscles is very challenging, especially for athletes whose muscles are all well developed and more compact than the average population. deep convolutional neural network (dCNN)-based segmentation methods showed great promise in many clinical applications, however, a direct adoption of dCNN to lower limb muscle segmentation is challenged by the large three-dimensional (3-d) image size and lack of the direct usage of muscle location information. We developed a cascaded 3-d dCNN model with the first step to localize each muscle using low-resolution images and the second step to segment it using cropped high-resolution images with individually trained networks. The work-flow was optimized to account for different characteristics of each muscle for improved accuracy and reduced training and testing time. A testing augmentation technique was proposed to smooth the segmentation contours. The segmentation performance of 14 muscles was within interobserver variability and 21 were slightly worse than humans. (c) 2019 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： lower limb muscle segmentation magnetic resonance imaging deep convolutional neural network 3-d segmentation cascaded network

来源：评论

学校读者我要写书评

暂无评论

Automatic three-dimensional segmentation combined with in vivo microvascular network imaging of human retina by intensity-based doppler variance optical coherence tomography 20

Automatic three-dimensional segmentation combined with in vi...

引用

Conference on Optical Coherence Tomography and Coherence domain Optical Methods in Biomedicine XX

作者： Piao, Zhonglie Huang, Shenghai Qi, Li Zhu, Jiang Lu, Fan Chen, Zhongping Univ Calif Irvine Beckman Laser Inst Irvine CA 92612 USA Wenzhou Med Univ Sch Optometry & Ophthalmol 270 Xueyuan Rd Wenzhou 325027 Peoples R China Pusan Natl Univ Dept Cognomech Engn Busan 609735 South Korea

ISBN: (纸本)9781628419313

Optical coherence tomography (OCT) is a noninvasive method for retinal imaging. In this work, we present an in vivo human retinal microvascular network measurement by an intensity-based doppler variance (IBdV) based on swept-source OCT. In addition, an automatic three-dimensional (3-d) segmentation method was used for segmenting intraretinal layers. The microvascular networks were divided into six layers by visualizing of each individual layer with enhanced imaging contrast. This method has potential for earlier diagnosis and precise monitoring in retinal vascular diseases.

关键词： Optical coherence tomography swept-source OCT doppler OCT doppler variance intensity-based doppler variance retina angiography 3-d segmentation dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Region segmentation in 3-d optical coherence tomography images

Region segmentation in 3-D optical coherence tomography imag...

引用

IEEE International Symposium on Bioelectronics and Bioinformatics (ISBB)

作者： Chou, Cheng-wei Lee, Jiann-der Liu, Carol T. Tsai, Meng-tsan ChangGung Univ Dept Elect Engn Taoyuan Taiwan ChangGung Univ Dept Elect Engn Coll Engn Taoyuan Taiwan Rutgers State Univ Sch Enviornm & Biol Sci Piscataway NJ 08855 USA

ISBN: (纸本)9781479927708

This paper describes a novel region segmentation method created to enhance spatial relationships in 3-d optical coherence tomography (OCT) images. To reduce the noise and distortion problems in low-resolution OCT images, previous work used the mean value and an enhanced-fuzzy-c-mean algorithm to cluster pixels in 2-d OCT images and find the edge between different clustered regions. To utilize more spatial relationships and to reduce computation time, the proposed method uses the mean value and a 3-d filter-based-fuzzy-c-mean algorithm to cluster pixels in 3-d OCT images and find the edge between different clustered regions. The OCT images of an artificial object used to simulate vessels are tested in the experiment, and the segmented regions of interest are reconstructed via AVIZO for 3-d display purposes.

关键词： Optical coherence tomography OCT 3-d segmentation fuzzy-c-mean vessel

来源：评论

学校读者我要写书评

暂无评论

Factors Affecting dimensional Accuracy of 3-d Printed Anatomical Structures derived from CT data

引用

JOURNAL OF dIGITAL IMAGING 2015年第6期28卷 654-663页

作者： Ogden, Kent M. Aslan, Can Ordway, Nathaniel diallo, dalanda Tillapaugh-Fay, Gwen Soman, Pranav SUNY Upstate Med Univ Dept Radiol Syracuse NY 13210 USA SUNY Upstate Med Univ Dept Orthoped Surg Syracuse NY 13210 USA Syracuse Univ Dept Biomed & Chem Engn Syracuse NY 13210 USA Univ S Florida Dept Radiol Tampa FL 33620 USA

Additive manufacturing and bio-printing, with the potential for direct fabrication of complex patient-specific anatomies derived from medical scan data, are having an ever-increasing impact on the practice of medicine. Anatomic structures are typically derived from CT or MRI scans, and there are multiple steps in the model derivation process that influence the geometric accuracy of the printed constructs. In this work, we compare the dimensional accuracy of 3-d printed constructs of an L1 vertebra derived from CT data for an ex vivo cadaver T-L spine with the original vertebra. Processing of segmented structures using binary median filters and various surface extraction algorithms is evaluated for the effect on model dimensions. We investigate the effects of changing CT reconstruction kernels by scanning simple geometric objects and measuring the impact on the derived model dimensions. We also investigate if there are significant differences between physical and virtual model measurements. The 3-d models were printed using a commercial 3-d printer, the Replicator 2 (MakerBot, Brooklyn, NY) using polylactic acid (PLA) filament. We found that changing parameters during the scan reconstruction, segmentation, filtering, and surface extraction steps will have an effect on the dimensions of the final model. These effects need to be quantified for specific situations that rely on the accuracy of 3-d printed models used in medicine or tissue engineering applications.

关键词： Three-dimensional imaging (3-d imaging) 3-d reconstruction 3-d segmentation Computed tomography Additive manufacturing Orthopedic modeling dimensional accuracy

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：