检索结果-内蒙古大学图书馆

multi-Center Fetal Brain Tissue Annotation (FeTA) Challenge 2022 Results

IEEE TRANSACTIONS ON MEDICAL IMAGING 2025年第3期44卷 1257-1272页

作者： Payette, Kelly Steger, Celine Licandro, Roxane Dumast, Priscille de Li, Hongwei Bran Barkovich, Matthew Li, Liu Dannecker, Maik Chen, Chen Ouyang, Cheng Mcconnell, Niccolo Miron, Alina Li, Yongmin Uus, Alena Grigorescu, Irina Gilliland, Paula Ramirez Siddiquee, Md Mahfuzur Rahman Xu, Daguang Myronenko, Andriy Wang, Haoyu Huang, Ziyan Ye, Jin Alenya, Mireia Comte, Valentin Camara, Oscar Masson, Jean-Baptiste Nilsson, Astrid Godard, Charlotte Mazher, Moona Qayyum, Abdul Gao, Yibo Zhou, Hangqi Gao, Shangqi Fu, Jia Dong, Guiming Wang, Guotai Rieu, Zunhyan Yang, Hyeonsik Lee, Minwoo Plotka, Szymon Grzeszczyk, Michal K. Sitek, Arkadiusz Daza, Luisa Vargas Usma, Santiago Arbelaez, Pablo Lu, Wenying Zhang, Wenhao Liang, Jing Valabregue, Romain Joshi, Anand A. Nayak, Krishna N. Leahy, Richard M. Wilhelmi, Luca Dandliker, Aline Ji, Hui Gennari, Antonio G. Jakovcic, Anton Klaic, Melita Adzic, Ana Markovic, Pavel Grabaric, Gracia Kasprian, Gregor Dovjak, Gregor Rados, Milan Vasung, Lana Cuadra, Meritxell Bach Jakab, Andras Univ Zurich Univ Childrens Hosp Zurich Ctr MR Res CH-8006 Zurich Switzerland Kings Coll London Dept Perinatal Imaging & Hlth London SE5 9RS England Univ Zurich Neurosci Ctr Zurich CH-8057 Zurich Switzerland Harvard Med Sch Massachusetts Gen Hosp Athinoula A Martinos Ctr Biomed Imaging Lab Computat Neuroimaging Boston MA 02115 USA Med Univ Vienna Dept Biomed Imaging & Image Guided Therapy Computat Imaging Res Lab A-1090 Vienna Austria Lausanne Univ Hosp Dept Diagnost & Intervent Radiol Med Image Anal Lab CH-1011 Lausanne Switzerland Univ Lausanne CH-1011 Lausanne Switzerland Harvard Med Sch Athinoula A Martinos Ctr Biomed Imaging Boston MA 02114 USA Univ Calif San Francisco UCSF Benioff Childrens Hosp Dept Radiol & Biomed Imaging San Francisco CA 94143 USA Imperial Coll London Comp Dept London SW7 2AZ England Tech Univ Munich Sch Computat Informat & Technol Munich Germany Tech Univ Munich Sch Med & Hlth D-80333 Munich Germany Univ Oxford Dept Engn Sci Oxford OX1 3PJ England Univ Sheffield Dept Comp Sci Sheffield S1 4DP England Brunel Univ London Comp Sci Dept Uxbridge UB8 3PH England UCL Inst Hlth Informat London WC1E 6BT England Kings Coll London Sch Biomed Engn & Imaging Sci Biomed Engn Dept London WC2R 2LS England NVIDIA Sch Comp & Augmented Intelligence Bethesda MD 20814 USA Arizona State Univ Tempe AZ 85281 USA NVIDIA Bethesda MD 20814 USA Shanghai Jiao Tong Univ Med Robot Shanghai 200240 Peoples R China Shanghai AI Lab Shanghai 200240 Peoples R China Univ Pompeu Fabra Dept Informat & Commun Technol BCN Medtech Barcelona 08002 Spain Inst Pasteur F-75015 Paris France Ecole Polytech F-91120 Palaiseau France UCL Ctr Med Image Comp Dept Comp Sci London WC1E 6BT England Imperial Coll London Natl Heart & Lung Inst London SW3 6LY England Fudan Univ Sch Data Sci Shanghai 200437 Peoples R China Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu 611731 Peoples R China NEUROPHET Res Inst Seoul 03080 South Korea Sano Ctr

segmentation is a critical step in analyzing the developing human fetal brain. There have been vast improvements in automatic segmentation methods in the past several years, and the Fetal Brain Tissue Annotation (FeTA) Challenge 2021 helped to establish an excellent standard of fetal brain segmentation. However, FeTA 2021 was a single center study, limiting real-world clinical applicability and acceptance. The multi-center FeTA Challenge 2022 focused on advancing the generalizability of fetal brain segmentation algorithms for magnetic resonance imaging (MRI). In FeTA 2022, the training dataset contained images and corresponding manually annotated multi-class labels from two imaging centers, and the testing data contained images from these two centers as well as two additional unseen centers. The multi-center data included different MR scanners, imaging parameters, and fetal brain super-resolution algorithms applied. 16 teams participated and 17 algorithms were evaluated. Here, the challenge results are presented, focusing on the generalizability of the submissions. Both in- and out-of-domain, the white matter and ventricles were segmented with the highest accuracy (Top Dice scores: 0.89, 0.87 respectively), while the most challenging structure remains the grey matter (Top Dice score: 0.75) due to anatomical complexity. The top 5 average Dices scores ranged from 0.81-0.82, the top 5 average $95<^>{\text {th}}$ percentile Hausdorff distance values ranged from 2.3-2.5mm, and the top 5 volumetric similarity scores ranged from 0.90-0.92. The FeTA Challenge 2022 was able to successfully evaluate and advance generalizability of multi-class fetal brain tissue segmentation algorithms for MRI and it continues to benchmark new algorithms.

关键词： image segmentation Imaging Magnetic resonance imaging Testing Training Topology Measurement Hospitals Biomedical imaging Superresolution Deep learning domain generalization fetal brain MRI multi-class image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep multi-Magnification Networks for multi-class breast cancer image segmentation

引用

COMPUTERIZED MEDICAL IMAGING AND GRAPHICS 2021年 88卷 101866-101866页

作者： Ho, David Joon Yarlagadda, Dig V. K. D'Alfonso, Timothy M. Hanna, Matthew G. Grabenstetter, Anne Ntiamoah, Peter Brogi, Edi Tan, Lee K. Fuchs, Thomas J. Mem Sloan Kettering Canc Ctr Dept Pathol New York NY 10065 USA Weill Cornell Grad Sch Med Sci New York NY 10065 USA

Pathologic analysis of surgical excision specimens for breast carcinoma is important to evaluate the completeness of surgical excision and has implications for future treatment. This analysis is performed manually by pathologists reviewing histologic slides prepared from formalin-fixed tissue. In this paper, we present Deep multi-Magnification Network trained by partial annotation for automated multi-class tissue segmentation by a set of patches from multiple magnifications in digitized whole slide images. Our proposed architecture with multi-encoder, multi-decoder, and multi-concatenation outperforms other single and multi-magnification-based architectures by achieving the highest mean intersection-over-union, and can be used to facilitate pathologists' assessments of breast cancer.

关键词： Breast cancer Computational pathology multi-class image segmentation Deep multi-Magnification Network Partial annotation

来源：评论

学校读者我要写书评

暂无评论

multiclass image segmentation using Deep Residual Encoder-Decoder Models in Highly Turbid Underwater Ambiances

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGE...

引用

INTERNATIONAL JOURNAL OF MATHEMATICAL ENGINEERING AND MANAGEMENT SCIENCES 2024年第6期9卷 1510-1530页

作者： Haridas, T. P. Mithun Kamal, Suraj Balakrishnan, Arun A. Thomas, Rosemol Nezla, N. A. Balakrishnan, Kannan Supriya, M. H. Cochin Univ Sci & Technol Ctr Ocean Elect Lab CUCENTOL Dept Elect Kochi 682021 Kerala India Cochin Univ Sci & Technol Dept Comp Applicat Kochi 682021 Kerala India

Underwater environments, especially the coral reefs, are the habitat of many critically endangered species. Extensive monitoring of these aquatic ecosystems is essential for conserving and deep understanding of these vulnerable habitats. Monitoring by extracting details from underwater images of turbid, hazy marine environments is extremely challenging. In this work, a novel annotated dataset is created for three classes of objects in the images of coral reef environment considering fish, rock/coral and background for the Fish4Knowledge dataset, a benchmark dataset primarily for binary segmentation. This work also proposes a multiclass ResUnet based image segmentation model for the newly created multiclass annotations. Various encoder-decoder convolutional architectures were analysed and found that ResUnet exhibits better robustness. The performance of the multiclass ResUnet model is also analysed by optimizing with different cost functions. Various underwater noisy conditions are simulated in the test images to find the robustness of the model, and observed that the proposed model optimised with Jaccard loss performs better even in extremely noisy scenarios.

关键词： Underwater image Encoder-decoder model multi-class image segmentation Fish4Knowledge

来源：评论

学校读者我要写书评

暂无评论

multi-class segmentation with relative location prior

引用

INTERNATIONAL JOURNAL OF COMPUTER VISION 2008年第3期80卷 300-316页

作者： Gould, Stephen Rodgers, Jim Cohen, David Elidan, Gal Koller, Daphne Stanford Univ Dept Comp Sci Stanford CA 94305 USA

multi-class image segmentation has made significant advances in recent years through the combination of local and global features. One important type of global feature is that of inter-class spatial relationships. For example, identifying "tree" pixels indicates that pixels above and to the sides are more likely to be "sky" whereas pixels below are more likely to be "grass." Incorporating such global information across the entire image and between all classes is a computational challenge as it is image-dependent, and hence, cannot be precomputed. In this work we propose a method for capturing global information from inter-class spatial relationships and encoding it as a local feature. We employ a two-stage classification process to label all image pixels. First, we generate predictions which are used to compute a local relative location feature from learned relative location maps. In the second stage, we combine this with appearance-based features to provide a final segmentation. We compare our results to recent published results on several multi-class image segmentation databases and show that the incorporation of relative location information allows us to significantly outperform the current state-of-the-art.

关键词： multi-class image segmentation segmentation relative location

来源：评论

学校读者我要写书评

暂无评论

multiclass segmentation Of 3d Medical Data With Deep Learning

Multiclass Segmentation Of 3d Medical Data With Deep Learnin...

引用

作者： Slunsky, Tomas Brno University of Technology

This paper deals with multiclass image segmentation using convolutional neural networks. The theoretical part of paper focuses on image segmentation. There are basics principles of neural networks and image segmentation with more types of approaches. In practical part the Unet architecture is choosen and is described for image segmentation more. U-net was applied for medicine dataset which consist from 3D MRI of human brain. There is processing procedure which is more described for image proccesing of three-dimmensional data. There are also methods for data preproccessing which were applied for image multiclass segmentation. Final part of paper evaluates results which were achieved with choosen method.

关键词： deep learning convolutional neural network multi-class image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fetal brain tissue annotation and segmentation challenge results

引用

MEDICAL image ANALYSIS 2023年第1期88卷 102833页

作者： Payette, Kelly Li, Hongwei Bran de Dumast, Priscille Licandro, Roxane Ji, Hui Siddiquee, Md Mahfuzur Rahman Xu, Daguang Myronenko, Andriy Liu, Hao Pei, Yuchen Wang, Lisheng Peng, Ying Xie, Juanying Zhang, Huiquan Dong, Guiming Fu, Hao Wang, Guotai Rieu, ZunHyan Kim, Donghyeon Kim, Hyun Gi Karimi, Davood Gholipour, Ali Torres, Helena R. Oliveira, Bruno Vilaca, Joao L. Lin, Yang Avisdris, Netanell Ben-Zvi, wOri Ben Bashat, Dafna Fidon, Lucas Aertsen, Michael Vercauteren, Tom Sobotka, Daniel Langs, Georg Alenya, Mireia Villanueva, Maria Inmaculada Camara, Oscar Fadida, Bella Specktor Joskowicz, Leo Weibin, Liao Yi, Lv Xuesong, Li Mazher, Moona Qayyum, Abdul Puig, Domenec Kebiri, Hamza Zhang, Zelin Xu, Xinyi Wu, Dan Liao, Kuanlun Wu, Yixuan Chen, Jintai Xu, Yunzhi Zhao, Li Vasung, Lana Menze, Bjoern Cuadra, Meritxell Bach Jakab, Andras Univ Zurich Univ Childrens Hosp Zurich Ctr MR Res Zurich Switzerland Univ Zurich Neurosci Ctr Zurich Zurich Switzerland Univ Zurich Dept Quantitat Biomed Zurich Switzerland Tech Univ Munich Dept Informat Munich Germany Lausanne Univ Hosp Dept Radiol Lausanne Switzerland Univ Lausanne Lausanne Switzerland CIBM Ctr Biomed Imaging Lausanne Switzerland Harvard Med Sch Massachusetts Gen Hosp Lab Computat Neuroimaging Athinoula Martinos Ctr Biomed Imaging Charlestown MA USA Med Univ Vienna Dept Biomed Imaging & Image Guided Therapy Computat Imaging Res Lab CIR Vienna Austria Arizona State Univ Tempe AZ USA NVIDIA Santa Clara CA USA Shanghai Jiao Tong Univ Shanghai Peoples R China Shaanxi Normal Univ Sch Comp Sci Xian 710119 Peoples R China Univ Elect Sci & Technol China Sch Mech & Elect Engn Chengdu Peoples R China NEUROPHET Inc Res Inst Seoul 06247 South Korea Catholic Univ Korea Eunpyeong St Marys Hosp Dept Radiol Seoul 06247 South Korea Boston Childrens Hosp Boston MA USA Harvard Med Sch Boston MA USA IPCA Sch Technol 2Ai Barcelos Portugal Univ Minho Sch Engn Algoritmi Ctr Guimaraes Portugal Univ Minho Life & Hlth Sci Res Inst ICVS Sch Med Braga Portugal ICVS 3Bs PT Govt Associate Lab Braga Portugal Hong Kong Univ Sci & Technol Dept Comp Sci Hong Kong Peoples R China Hebrew Univ Jerusalem Sch Comp Sci & Engn Jerusalem Israel Tel Aviv Sourasky Med Ctr Sagol Brain Inst Tel Aviv Israel Tel Aviv Univ Sagol Sch Neurosci Tel Aviv Israel Tel Aviv Univ Sackler Fac Med Tel Aviv Israel Tel Aviv Univ Sackler Fac Med Tel Aviv Israel Kings Coll London Sch Biomed Engn Imaging Sci London SE1 7EU England Univ Hosp Leuven Dept Radiol B-3000 Leuven Belgium Med Univ Vienna Dept Biomed Imaging & Image Guided Therapy Computat Imaging Res Lab Vienna Austria Univ Pompeu Fabra Dept Informat & Communicat Technol BCN MedTech Barcelona Spain Univ Pompeu Fabra Dept Informat & Communicat Technol Barcelona Spain Inst Invest Biomed August Pi i Su

In-utero fetal MRI is emerging as an important tool in the diagnosis and analysis of the developing human brain. Automatic segmentation of the developing fetal brain is a vital step in the quantitative analysis of prenatal neurodevelopment both in the research and clinical context. However, manual segmentation of cerebral struc-tures is time-consuming and prone to error and inter-observer variability. Therefore, we organized the Fetal Tissue Annotation (FeTA) Challenge in 2021 in order to encourage the development of automatic segmentation algorithms on an international level. The challenge utilized FeTA Dataset, an open dataset of fetal brain MRI reconstructions segmented into seven different tissues (external cerebrospinal fluid, gray matter, white matter, ventricles, cerebellum, brainstem, deep gray matter). 20 international teams participated in this challenge, submitting a total of 21 algorithms for evaluation. In this paper, we provide a detailed analysis of the results from both a technical and clinical perspective. All participants relied on deep learning methods, mainly U-Nets, with some variability present in the network architecture, optimization, and image pre-and post-processing. The majority of teams used existing medical imaging deep learning frameworks. The main differences between the submissions were the fine tuning done during training, and the specific pre-and post-processing steps performed. The challenge results showed that almost all submissions performed similarly. Four of the top five teams used ensemble learning methods. However, one team's algorithm performed significantly superior to the other sub-missions, and consisted of an asymmetrical U-Net network architecture. This paper provides a first of its kind benchmark for future automatic multi-tissue segmentation algorithms for the developing human brain in utero.

关键词： multi-class image segmentation Fetal brain MRI Congenital disorders Super-resolution reconstructions

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：