心脏MRI数据集

从33位受试者中获取的心脏MR图像。 每个对象的序列由20帧和沿长轴的8-15切片组成，总共7980张图像。对应于每个主题x的序列位于名为sol_yxzt_pat x .mat 的不同.mat（MATLAB）文件中。这些是未经处理的原始图像，最初存储为16位DICOM图像。 以上序列的分段。我们手动分割了7980个图像，其中左心室的心内膜和心外膜 均可见，总共分割了5011个MR图像和10022个轮廓。与每个主题x对应的分段位于名为manual_seg_32points_pat x .mat 的不同.mat（MATLAB）文件中。每个轮廓由像素坐标中给出的32个点描述。 数据格式： .mat 文件 数据引用： Alexander Andreopoulos, John K. Tsotsos, Efficient and Generalizable Statistical Models of Shape and Appearance for Analysis of Cardiac MRI, Medical Image Analysis,Volume 12, Issue 3, June2008, Pages 335-357. PDF 数据提供者： 多伦多儿童病医院的放射线首席放射科医师Paul Babyn博士 和心脏放射科医师Shi-Joon Yoo博士

Cardiac MR images were acquired from 33 subjects. The imaging sequence for each subject consists of 20 frames and 8-15 slices along the long axis, totaling 7980 images. The sequence corresponding to each subject x is stored in a separate MATLAB .mat file named sol_yxzt_pat_x.mat. These are unprocessed raw images, originally stored as 16-bit DICOM images.

Segmentations for the aforementioned sequences: We manually segmented 7980 images where both the endocardium and epicardium of the left ventricle are visible, resulting in a total of 5011 MR images and 10022 contours. The segmentations corresponding to each subject x are stored in separate MATLAB .mat files named manual_seg_32points_pat_x.mat. Each contour is described by 32 points given in pixel coordinates.

Data Format: .mat files

Data Citation: Alexander Andreopoulos, John K. Tsotsos, *Efficient and Generalizable Statistical Models of Shape and Appearance for Analysis of Cardiac MRI*, Medical Image Analysis, Volume 12, Issue 3, June 2008, Pages 335-357. PDF

Data Providers: Dr. Paul Babyn, Chief Radiologist, and Dr. Shi-Joon Yoo, Cardiac Radiologist, The Hospital for Sick Children (Toronto)

搜集汇总

背景与挑战

背景概述

心脏MRI数据集包含33位受试者的7980张心脏MR图像，涵盖多帧和多切片数据，并提供手动分割的左心室心内膜和心外膜轮廓。数据以.mat文件格式存储，适用于心脏医学图像分析研究。