Angelou0516/ACDC

ACDC数据集来自第戎大学医院的真实临床检查数据，经过完全匿名化处理，并符合当地伦理委员会的规定。数据集包含150个检查（来自不同患者），分为5个均匀分布的亚组（4个病理组和1个健康组）。每个患者还附带体重、身高以及舒张和收缩相位的信息。数据集的主要任务是心脏磁共振图像的语义分割，特别是心内膜和心肌的分割，这对于心血管疾病的检测非常相关。自动化的分割可以大大减少手动分割的时间，从而及时检测心血管疾病。

The ACDC dataset was created from real clinical exams acquired at the University Hospital of Dijon. The data were fully anonymized and handled within the regulations set by the local ethical committee. The dataset includes 150 exams (all from different patients) divided into 5 evenly distributed subgroups (4 pathological plus 1 healthy subject groups). Each patient comes with additional information such as weight, height, and the diastolic and systolic phase instants. The main task of this dataset is the semantic segmentation of the heart in cardiac magnetic resonance images, specifically the endocardium and myocardium, which is highly relevant for the detection of cardiovascular diseases. Automated segmentation can significantly reduce the time spent on manual segmentation, enabling timely detection of cardiovascular diseases.

搜集汇总

背景与挑战

背景概述

ACDC数据集是一个用于心脏磁共振图像语义分割的医学影像数据集，专门针对内层心肌和中间心肌的分割，旨在辅助心血管疾病检测。它包含150个来自法国第戎大学医院的真实临床检查，分为5个均匀子组（4个病理组和1个健康组），并附带患者生理参数，总文件大小为2.45 GB，支持西班牙语和英语。