ImageCAS
收藏资源简介:
ImageCAS是由广东省人民医院(广东省医学科学院)创建的大规模数据集,包含1000个基于计算机断层扫描血管造影(CTA)图像的冠状动脉分割案例。数据集由真实的临床案例组成,使用西门子128层双源扫描仪获取,旨在支持冠状动脉疾病的诊断和量化。数据集的创建过程涉及由两位放射科医生独立标注,并在有分歧时由第三位放射科医生进行裁决。ImageCAS数据集的应用领域主要集中在冠状动脉疾病的自动分割和诊断,旨在通过深度学习方法提高诊断的准确性和效率。
ImageCAS is a large-scale dataset developed by Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), which contains 1000 coronary artery segmentation cases based on computed tomography angiography (CTA) images. The dataset is composed of real clinical cases acquired using a Siemens 128-slice dual-source scanner, and is intended to support the diagnosis and quantification of coronary artery disease. The dataset creation process involved independent annotation by two radiologists, with discrepancies resolved by a third radiologist when disagreements arose. The primary application scenarios of the ImageCAS dataset focus on automatic segmentation and diagnosis of coronary artery disease, aiming to improve the accuracy and efficiency of diagnosis through deep learning methods.




