A Systematic Review of Deep-Learning Methods for Intracranial Aneurysm Detection in CT Angiography

被引:17
作者
Bizjak, Ziga [1 ]
Spiclin, Ziga [1 ]
机构
[1] Univ Ljubljana, Fac Elect Engn, Lab Imaging Technol, Ljubljana 1000, Slovenia
关键词
computed tomography angiography; CTA; aneurysm detection; meta-analysis; PRISMA; QUADAS-2; sensitivity; specificity; false positives per image; healthy controls; evaluation guidelines; ARTIFICIAL-INTELLIGENCE; DIAGNOSIS;
D O I
10.3390/biomedicines11112921
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Background: Subarachnoid hemorrhage resulting from cerebral aneurysm rupture is a significant cause of morbidity and mortality. Early identification of aneurysms on Computed Tomography Angiography (CTA), a frequently used modality for this purpose, is crucial, and artificial intelligence (AI)-based algorithms can improve the detection rate and minimize the intra- and inter-rater variability. Thus, a systematic review and meta-analysis were conducted to assess the diagnostic accuracy of deep-learning-based AI algorithms in detecting cerebral aneurysms using CTA. Methods: PubMed (MEDLINE), Embase, and the Cochrane Library were searched from January 2015 to July 2023. Eligibility criteria involved studies using fully automated and semi-automatic deep-learning algorithms for detecting cerebral aneurysms on the CTA modality. Eligible studies were assessed using the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. A diagnostic accuracy meta-analysis was conducted to estimate pooled lesion-level sensitivity, size-dependent lesion-level sensitivity, patient-level specificity, and the number of false positives per image. An enhanced FROC curve was utilized to facilitate comparisons between the studies. Results: Fifteen eligible studies were assessed. The findings indicated that the methods exhibited high pooled sensitivity (0.87, 95% confidence interval: 0.835 to 0.91) in detecting intracranial aneurysms at the lesion level. Patient-level sensitivity was not reported due to the lack of a unified patient-level sensitivity definition. Only five studies involved a control group (healthy subjects), whereas two provided information on detection specificity. Moreover, the analysis of size-dependent sensitivity reported in eight studies revealed that the average sensitivity for small aneurysms (<3 mm) was rather low (0.56). Conclusions: The studies included in the analysis exhibited a high level of accuracy in detecting intracranial aneurysms larger than 3 mm in size. Nonetheless, there is a notable gap that necessitates increased attention and research focus on the detection of smaller aneurysms, the use of a common test dataset, and an evaluation of a consistent set of performance metrics.
引用
收藏
页数:14
相关论文
共 34 条
[1]   Automated computerized scheme for detection of unruptured intracranial aneurysms in three-dimensional magnetic resonance angiography [J].
Arimura, H ;
Li, Q ;
Korogi, Y ;
Hirai, T ;
Abe, H ;
Yamashita, Y ;
Katsuragawa, S ;
Ikeda, R ;
Doi, K .
ACADEMIC RADIOLOGY, 2004, 11 (10) :1093-1104
[2]   Toward human intervention-free clinical diagnosis of intracranial aneurysm via deep neural network [J].
Bo, Zi-Hao ;
Qiao, Hui ;
Tian, Chong ;
Guo, Yuchen ;
Li, Wuchao ;
Liang, Tiantian ;
Li, Dongxue ;
Liao, Dan ;
Zeng, Xianchun ;
Mei, Leilei ;
Shi, Tianliang ;
Wu, Bo ;
Huang, Chao ;
Liu, Lu ;
Jin, Can ;
Guo, Qiping ;
Yong, Jun-Hai ;
Xu, Feng ;
Zhang, Tijiang ;
Wang, Rongpin ;
Dai, Qionghai .
PATTERNS, 2021, 2 (02)
[3]  
Bossuyt P.M., 2013, Cochrane handbook for systematic reviews of diagnostic test accuracy
[4]   Deep learning for automated cerebral aneurysm detection on computed tomography images [J].
Dai, Xilei ;
Huang, Lixiang ;
Qian, Yi ;
Xia, Shuang ;
Chong, Winston ;
Liu, Junjie ;
Di Ieva, Antonio ;
Hou, Xiaoxi ;
Ou, Chubin .
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2020, 15 (04) :715-723
[5]   Detection of cerebral aneurysms using artificial intelligence: a systematic review and meta-analysis [J].
Din, Munaib ;
Agarwal, Siddharth ;
Grzeda, Mariusz ;
Wood, David A. ;
Modat, Marc ;
Booth, Thomas C. .
JOURNAL OF NEUROINTERVENTIONAL SURGERY, 2023, 15 (03) :262-+
[6]   Worldwide Incidence of Aneurysmal Subarachnoid Hemorrhage According to Region, Time Period, Blood Pressure, and Smoking Prevalence in the Population A Systematic Review and Meta-analysis [J].
Etminan, Nima ;
Chang, Han-Sol ;
Hackenberg, Katharina ;
de Rooij, Nicolien K. ;
Vergouwen, Mervyn D. I. ;
Rinkel, Gabriel J. E. ;
Algra, Ale .
JAMA NEUROLOGY, 2019, 76 (05) :588-597
[7]   Performance of deep learning in the detection of intracranial aneurysm: systematic review and meta-analysis [J].
Gu, Feng ;
Wu, Xiaoxiao ;
Wu, Wenxue ;
Wang, Zilan ;
Yang, Xingyu ;
Chen, Zhouqing ;
Wang, Zhong ;
Chen, Gang .
EUROPEAN JOURNAL OF RADIOLOGY, 2022, 155
[8]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[9]   RAPID Aneurysm: Artificial intelligence for unruptured cerebral aneurysm detection on CT angiography [J].
Heit, Jeremy J. ;
Honce, Justin M. ;
Yedavalli, Vivek S. ;
Baccin, Carlos E. ;
Tatit, Rafael T. ;
Copeland, Karen ;
Timpone, Vincent M. .
JOURNAL OF STROKE & CEREBROVASCULAR DISEASES, 2022, 31 (10)
[10]   2023 Guideline for the Management of Patients With Aneurysmal Subarachnoid Hemorrhage: A Guideline From the American Heart Association/American Stroke Association [J].
Hoh, Brian L. ;
Ko, Nerissa U. ;
Amin-Hanjani, Sepideh ;
Chou, Sherry Hsiang-Yi ;
Cruz-Flores, Salvador ;
Dangayach, Neha S. ;
Derdeyn, Colin P. ;
Du, Rose ;
Haenggi, Daniel ;
Hetts, Steven W. ;
Ifejika, Nneka L. ;
Johnson, Regina ;
Keigher, Kiffon M. ;
Leslie-Mazwi, Thabele M. ;
Lucke-Wold, Brandon ;
Rabinstein, Alejandro A. ;
Robicsek, Steven A. ;
Stapleton, Christopher J. ;
Suarez, Jose I. ;
Tjoumakaris, Stavropoula I. ;
Welch, Babu G. .
STROKE, 2023, 54 (07) :E314-E370