Protocol and Preliminary Results of the Establishment of Intracranial Aneurysm Database for Artificial Intelligence Application Based on CTA Images

Wei You; Wei You; Yong Sun; Junqiang Feng; Junqiang Feng; Zhiliang Wang; Lin Li; Xiheng Chen; Xiheng Chen; Jian Lv; Jian Lv; Yudi Tang; Dingwei Deng; Dachao Wei; Siming Gui; Xinke Liu; Xinke Liu; Peng Liu; Peng Liu; Hengwei Jin; Hengwei Jin; Huijian Ge; Huijian Ge; Yanling Zhang

doi:10.3389/fneur.2022.932933

Frontiers in Neurology (Jul 2022)

Protocol and Preliminary Results of the Establishment of Intracranial Aneurysm Database for Artificial Intelligence Application Based on CTA Images

Wei You,
Wei You,
Yong Sun,
Junqiang Feng,
Junqiang Feng,
Zhiliang Wang,
Lin Li,
Xiheng Chen,
Xiheng Chen,
Jian Lv,
Jian Lv,
Yudi Tang,
Dingwei Deng,
Dachao Wei,
Siming Gui,
Xinke Liu,
Xinke Liu,
Peng Liu,
Peng Liu,
Hengwei Jin,
Hengwei Jin,
Huijian Ge,
Huijian Ge,
Yanling Zhang

Affiliations

Wei You: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Wei You: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Yong Sun: Department of Neurosurgery, The First People's Hospital of Lianyungang and The First Affiliated Hospital of Kangda College, Nanjing Medical University, Lianyungang, China
Junqiang Feng: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Junqiang Feng: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Zhiliang Wang: Department of Neurosurgery, The People's Hospital of Nanpi Country, Cangzhou, China
Lin Li: Department of Emergency, The Fourth Hospital of Hebei Medical University, Shijiazhuang, China
Xiheng Chen: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Xiheng Chen: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Jian Lv: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Jian Lv: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Yudi Tang: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Dingwei Deng: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Dachao Wei: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Siming Gui: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Xinke Liu: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Xinke Liu: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Peng Liu: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Peng Liu: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Hengwei Jin: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Hengwei Jin: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Huijian Ge: Department of Interventional Neuroradiology, Beijing Neurosurgical Institute and Beijing Tiantan Hospital, Capital Medical University, Beijing, China
Huijian Ge: Department of Neurointerventional Engineering and Technology, Beijing Engineering Research Center, Beijing, China
Yanling Zhang: Department of Roradiology, Beijing Tiantan Hospital, Capital Medical University, Beijing, China

DOI: https://doi.org/10.3389/fneur.2022.932933
Journal volume & issue: Vol. 13

Abstract

Read online

Background and PurposeUnruptured intracranial aneurysms (UIAs) are increasingly being detected in clinical practice. Artificial intelligence (AI) has been increasingly used to assist diagnostic techniques and shows encouraging prospects. In this study, we reported the protocol and preliminary results of the establishment of an intracranial aneurysm database for AI application based on computed tomography angiography (CTA) images.MethodsThrough a review of picture archiving and communication systems, we collected CTA images of patients with aneurysms between January 2010 and March 2021. The radiologists performed manual segmentation of all diagnosed aneurysms on subtraction CTA as the basis for automatic aneurysm segmentation. Then, AI will be applied to two stages of aneurysm treatment, namely, automatic aneurysm detection and segmentation model based on the CTA image and the aneurysm risk prediction model.ResultsThree medical centers have been included in this study so far. A total of 3,190 cases of CTA examinations with 4,124 aneurysms were included in the database. All identified aneurysms from CTA images that enrolled in this study were manually segmented on subtraction CTA by six readers. We developed a structure of 3D-Unet for aneurysm detection and segmentation in CTA images. The algorithm was developed and tested using a total of 2,272 head CTAs with 2,938 intracranial aneurysms. The recall and false positives per case (FP/case) of this model for detecting aneurysms were 0.964 and 2.01, and the Dice values for aneurysm segmentation were 0.783.ConclusionThis study introduces the protocol and preliminary results of the establishment of the intracranial aneurysm database for AI applications based on CTA images. The establishment of a multicenter database based on CTA images of intracranial aneurysms is the basis for the application of AI in the diagnosis and treatment of aneurysms. In addition to segmentation, AI should have great potential for aneurysm treatment and management in the future.

Published in Frontiers in Neurology

ISSN: 1664-2295 (Online)
Publisher: Frontiers Media S.A.
Country of publisher: Switzerland
LCC subjects: Medicine: Internal medicine: Neurosciences. Biological psychiatry. Neuropsychiatry: Neurology. Diseases of the nervous system
Website: https://www.frontiersin.org/journals/neurology/

About the journal

Abstract

Keywords