CT datasets for Aortic dissection

Citation Author(s):
Xiangyu
Xiong
Submitted by:
xiangyu xiong
Last updated:
Thu, 06/30/2022 - 09:55
DOI:
10.21227/mqe9-gs13
Data Format:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

Contrast-enhanced computed tomography (CE-CT) is  the gold standard for diagnosing aortic dissection (AD). However,  contrast agents can cause allergic reactions or renal failure in  some patients. Moreover, AD diagnosis by radiologists using non- contrast-enhanced CT (NCE-CT) images has poor sensitivity. To address this issue, a novel  deep learning methos was proposed  for AD detection using NCE-CT volumes.  It may have great potential to reduce the misdiagnosis of AD using NCE-CT in clinical practice.

Instructions: 

All datasets were collected from two medical centers (i.e., Beijing Anzhen Hospital, Capital Medical University, Beijing, China; Fujian Provincial Hospital, Fuzhou, China) using three vendors (i.e., SIEMENS, TOSHIBA, and GE MEDICAL SYSTEMS) with kilovolt peak (KVP) of 100 ∼ 120. The datasets consisted of 207 subjects (i.e., 78 AD patients and 129 non-AD patients with other cardiovascular diseases). We sequentially performed Non-contrast enhanced CT and Contrast enhanced CT on each subject with the same scan conditions, including position, coverage, and parameters. To reduce motion artifacts and misregistration between NCE-CE and CE-CT, we acquired the datasets using electrocardiographic (ECG) triggering and breath-holding at the end of respiration.

In addition, we provide the true and false lumen masks for segmentation. True lumen was anotated with 1 and false lumen was anotated with 2.