msepulvedagodoy/acdc
收藏资源简介:
--- task_categories: - image-segmentation language: - es - en tags: - medical pretty_name: ACDC-Automated Cardiac Diagnosis Challenge size_categories: - 1K<n<10K ---  General information The overall ACDC dataset was created from real clinical exams acquired at the University Hospital of Dijon. Acquired data were fully anonymized and handled within the regulations set by the local ethical committee of the Hospital of Dijon (France). Our dataset covers several well-defined pathologies with enough cases to (1) properly train machine learning methods and (2) clearly assess the variations of the main physiological parameters obtained from cine-MRI (in particular diastolic volume and ejection fraction). The dataset is composed of 150 exams (all from different patients) divided into 5 evenly distributed subgroups (4 pathological plus 1 healthy subject groups) as described below. Furthermore, each patient comes with the following additional information : weight, height, as well as the diastolic and systolic phase instants. Tasks The main task of this dataset is the semantic segmentation of the heart in cardiac magnetic resonance images, specifically the endocardium and myocardium. The present task is very relevant for the detection of cardiovascular diseases. Segmentation is a very time-consuming process, so automatically performing the segmentation with Artificial Intelligence algorithms can be extremely beneficial to reduce the time spent in a manual segmentation. In this way, a very relevant bottleneck can be avoided and cardiovascular diseases can be detected in a timely manner. Reference O. Bernard, A. Lalande, C. Zotti, F. Cervenansky, et al. "Deep Learning Techniques for Automatic MRI Cardiac Multi-structures Segmentation and Diagnosis: Is the Problem Solved ?" in IEEE Transactions on Medical Imaging, vol. 37, no. 11, pp. 2514-2525, Nov. 2018 doi: 10.1109/TMI.2018.2837502
task_categories: - 图像分割(image-segmentation) language: - 西班牙语 - 英语 tags: - 医学(medical) pretty_name: ACDC-自动化心脏诊断挑战赛(Automated Cardiac Diagnosis Challenge) size_categories: - 1K<n<10K ---  ### 总体概况 本数据集整体源自法国第戎大学医院获取的真实临床检查数据。所采集的数据已完成完全匿名化处理,并严格遵循法国第戎医院地方伦理委员会制定的相关法规进行管理。本数据集涵盖多种明确界定的心血管病理类型,且样本量充足,可同时满足两大需求:(1)对机器学习方法开展充分训练;(2)精准评估从心脏电影磁共振(cine-MRI)图像中提取的主要生理参数(尤其是舒张末期容积与射血分数)的变化情况。数据集包含150例来自不同患者的检查数据,分为5个分布均匀的子组(4个病理组与1个健康对照组),具体分组说明如下。此外,每位患者还附带以下附加信息:体重、身高,以及舒张期与收缩期的成像时刻。 ### 任务说明 本数据集的核心任务为心脏磁共振图像中的心脏语义分割(semantic segmentation),具体目标为心内膜与心肌的分割。该任务对于心血管疾病的检测具有关键意义。人工分割流程耗时极长,因此借助人工智能算法实现自动化分割,可大幅缩减手动分割所需的时间,从而规避这一核心瓶颈,并实现心血管疾病的及时检测。 ### 参考文献 O. Bernard, A. Lalande, C. Zotti, F. Cervenansky 等. "深度学习技术用于磁共振心脏多结构自动分割与诊断:问题已解决?",发表于《IEEE Transactions on Medical Imaging》,2018年11月,第37卷第11期,页码2514-2525 DOI: 10.1109/TMI.2018.2837502
数据集概述
基本信息
- 任务类别:图像分割
- 语言:西班牙语、英语
- 标签:医学
- 美观名称:ACDC-Automated Cardiac Diagnosis Challenge
- 大小类别:1K<n<10K
数据集详情
- 来源:由法国第戎大学医院提供的真实临床检查数据,数据已完全匿名化,并遵守当地伦理委员会的规定。
- 组成:包含150次检查(来自不同患者),分为5个均匀分布的子组(4个病理性加1个健康组)。
- 附加信息:每位患者提供体重、身高以及舒张期和收缩期时刻。
任务描述
- 主要任务:心脏磁共振图像中的心脏语义分割,特别是心内膜和心肌。
- 应用:此任务对于心血管疾病的检测非常重要,自动分割算法可以显著减少手动分割所需的时间,及时检测心血管疾病。
参考文献
- O. Bernard, A. Lalande, C. Zotti, F. Cervenansky, et al. "Deep Learning Techniques for Automatic MRI Cardiac Multi-structures Segmentation and Diagnosis: Is the Problem Solved ?" in IEEE Transactions on Medical Imaging, vol. 37, no. 11, pp. 2514-2525, Nov. 2018. doi: 10.1109/TMI.2018.2837502




