Application of AI-assisted head and neck CT angiography in diagnosis of intracranial aneurysms

Hao DENG; Xin WEI; Wenting CAO; Guangyong AI; Han YU; Jing FANG; Bohan WU; Zhiming ZHOU; Jinhua CHEN; Weijuan CHEN

doi:10.16016/j.1000-5404.202103144

您当前的位置：

首页 >

文章列表页 >

Application of AI-assisted head and neck CT angiography in diagnosis of intracranial aneurysms

Clinical Medicine | 更新时间：2026-01-09

- Application of AI-assisted head and neck CT angiography in diagnosis of intracranial aneurysms
- Journal of Third Military Medical University Vol. 43, Issue 12, Pages: 1179-1184(2021)
- 作者机构：
  
  400010重庆，重庆医科大学附属第二医院放射科
- 作者简介：
- 基金信息：
- DOI：10.16016/j.1000-5404.202103144
  CLC： R445.3;R651.1;R814.42
- Received：17 March 2021，
  
  Revised：2021-04-25，
  
  Published：30 June 2021
- 稿件说明：
移动端阅览
Hao DENG, Xin WEI, Wenting CAO, et al. Application of AI-assisted head and neck CT angiography in diagnosis of intracranial aneurysms[J]. Journal of Third Military Medical University, 2021, 43(12): 1179-1184.
DOI：

Hao DENG, Xin WEI, Wenting CAO, et al. Application of AI-assisted head and neck CT angiography in diagnosis of intracranial aneurysms[J]. Journal of Third Military Medical University, 2021, 43(12): 1179-1184. DOI： 10.16016/j.1000-5404.202103144.

摘要

目的

探究人工智能(artificial intelligence，AI)在头颈CT血管成像(CT angiography，CTA)诊断颅内动脉瘤中的价值。

方法

回顾性分析本院2020年8月至2021年1月117例临床疑似颅内动脉瘤患者间隔2周内头颈CTA及数字减影血管造影(digital subtraction angiography，DSA)资料。以DSA结果为金标准，计算AI诊断动脉瘤的敏感度和准确率。记录AI自动测量动脉瘤径线的结果，并与DSA人工测量结果进行一致性检验。

结果

117例患者经DSA确诊为颅内动脉瘤105例，共计136个动脉瘤。①诊断效能方面，以患者为单位，AI对动脉瘤诊断的敏感度和准确率分别为87.6%和79.5%。以病灶为单位，对总体、＜3 mm、3~5 mm和＞5 mm的动脉瘤，AI诊断敏感度分别为79.4%、55.2%、81.5%和92.9%，准确率分别为72.0%、53.8%、75.3%和86.3%。②定量分析方面，对动脉瘤总体瘤体长径、总体瘤体短径、＞5 mm动脉瘤的瘤体长径、＜3 mm动脉瘤的瘤体长径和3~5 mm动脉瘤的瘤体长径的测量结果，AI自动测量和DSA人工测量的一致性分别为好、好、较好、差和差(ICC=0.778、0.822和0.722，

均＜0.001；ICC=0.113和0.142，

均＞0.05)。

结论

AI在头颈CTA诊断颅内动脉瘤中具有较高的价值，对瘤体长径＞5 mm的径线测量结果可作为参考标准，可以作为辅助诊断工具进一步推广和应用。

Abstract

Objective

To explore the clinical value of artificial intelligence (AI) in the diagnosis of intracranial aneurysms by head and neck CT angiography (CTA).

Methods

A total of 117 patients with clinically suspected intracranial aneurysms admitted in our hospital from August 2020 to January 2021 were enrolled

and their head and neck CTA and digital subtraction angiography (DSA) data were collected and retrospectively analyzed. Taking DSA results as the gold standard

the sensitivity and accuracy of AI in the diagnosis of intracranial aneurysms were calculated. In addition

the results of AI automatic measurement were recorded

and the consistency test was conducted with the results of DSA manual measurement.

Results

Among the 117 suspected patients

there were 105 cases diagnosed with intracranial aneurysms by DSA

with a total of 136 aneurysms. ①Diagnostic efficiency: The sensitivity and accuracy of AI for aneurysm diagnosis were 87.6% and 79.5%

respectively

taking patients as unit. While taking lesions as unit

the sensitivity of AI diagnosis was 55.2%

81.5%

92.9% and 79.4% for aneurysms

3 mm

3.5 mm

5 mm

as well as for the total number of aneurysms

respectively; And the accuracy was 53.8%

75.3%

86.3% and 72.0%. ②Quantitative analysis: The results of AI and DSA showed good consistency in the measurement of the total aneurysm length diameter

total short diameter

and

5 mm aneurysm length diameter (ICC=0.778

0.822 and 0.722

0.001); But poor consistency was seen in the measurement for

3 mm and 3~5 mm aneurysm length diameter (ICC=0.113

0.142

0.05).

Conclusion

AI has a high value in the application of head and neck CTA in the diagnosis of intracranial aneurysms

with its measurement results to be used as a reference standard in tumors with length diameter >5 mm

it can be further promoted and applied as an auxiliary diagnostic tool.

关键词

Keywords

references

SHAHZAD R, PENNIG L, GOERTZ L, et al . Fully automated detection and segmentation of intracranial aneurysms in subarachnoid hemorrhage on CTA using deep learning[J ] . Sci Rep, 2020, 10(1): 21799. DOI: 10.1038/s41598-020-78384-1.

JOO B, AHN S S, YOON P H, et al . A deep learning algorithm may automate intracranial aneurysm detection on MR angiography with high diagnostic performance[J ] . Eur Radiol, 2020, 30(11): 5785-5793. DOI: 10.1007/s00330-020-06966-8.

郑鉴峰, 张晓冬, 郭宗铎, 等. 介入栓塞治疗小型与中大型颅内未破裂动脉瘤的效果对比[J]. 第三军医大学学报, 2016, 38(3): 288-291, 306. DOI: 10.16016/j.1000-5404.201506069.

ZHENG J F, ZHANG X D, GUO Z D, et al . Efficacy of embolization in treatment of small vs medium-large intracranial unruptured aneurysms: report of 54 cases[J ] . J Third Mil Med Univ, 2016, 38(3): 288-291, 306. DOI: 10.16016/j.1000-5404.201506069.

黄清海, 杨鹏飞. 颅内动脉瘤血管内介入治疗中国专家共识(2013)[J]. 中华医学杂志, 2013, 93(39): 3093-3103. DOI: 10.3760/cma.j.issn.0376-2491.2013.39.003.

HUANG Q H, YANG P F. Chinese expert consensus on endovascular interventional therapy of intracranial aneurysms (2013)[J]. Natl Med J China, 2013, 93(39): 3093-3103. DOI: 10.3760/cma.j.issn.0376-2491.2013.39.003.

时代, 蔡武, 乔方, 等. 256排CT诊断颅内小动脉瘤能力研究[J]. 临床放射学杂志, 2019, 38(8): 1357-1361. DOI: 10.13437/j.cnki.jcr.20190828.019.

SHI D, CAI W, QIAO F, et al . Study on the ability of 256-slice CT in diagnosing intracranial small aneurysms[J ] . J Clin Radiol, 2019, 38(8): 1357-1361. DOI: 10.13437/j.cnki.jcr.20190828.019.

余娜, 严敏, 傅浪舟, 等. 应用能谱CT技术去除颅内动脉瘤弹簧圈栓塞术后金属伪影[J]. 第三军医大学学报, 2020, 42(20): 2069-2074. DOI: 10.16016/j.1000-5404.202005207.

YU N, YAN M, FU L Z, et al . Application of spectral computed tomography for artifact removal after coil embolization of intracranial aneurysms[J ] . J Third Mil Med Univ, 2020, 42 (20): 2069-2074. DOI: 10.16016/j.1000-5404.202005207.

YANG J H, XIE M F, HU C P, et al . Deep learning for detecting cerebral aneurysms with CT angiography[J ] . Radiology, 2021, 298(1): 155-163. DOI: 10.1148/radiol.2020192154.

GENG C, XIA W, HUANG L, et al . Automated computer-assisted detection system for cerebral aneurysms in time-of-flight magnetic resonance angiography using fully convolutional network[J ] . Biomed Eng Online, 2020, 19(1): 38. DOI: 10.1186/s12938-020-00770-7.

UEDA D, YAMAMOTO A, NISHIMORI M, et al . Deep learning for MR angiography: automated detection of cerebral aneurysms[J ] . Radiology, 2019, 290(1): 187-194. DOI: 10.1148/radiol.2018180901.

PARK A, CHUTE C, RAJPURKAR P, et al . Deep learning-assisted diagnosis of cerebral aneurysms using the HeadXNet model[J ] . JAMA Netw Open, 2019, 2(6): e195600. DOI: 10.1001/jamanetworkopen.2019.5600.

HANAOKA S, NOMURA Y, TAKENAGA T, et al . HoTPiG: a novel graph-based 3-D image feature set and its applications to computer-assisted detection of cerebral aneurysms and lung nodules[J ] . Int J Comput Assist Radiol Surg, 2019, 14(12): 2095-2107. DOI: 10.1007/s11548-019-01942-0.

DAI X L, HUANG L X, QIAN Y, et al . Deep learning for automated cerebral aneurysm detection on computed tomography images[J ] . Int J Comput Assist Radiol Surg, 2020, 15(4): 715-723. DOI: 10.1007/s11548-020-02121-2.

SHI Z, MIAO C C, SCHOEPF U J, et al . A clinically applicable deep-learning model for detecting intracranial aneurysm in computed tomography angiography images[J ] . Nat Commun, 2020, 11(1): 6090.DOI: 10.1038/s41467-020-19527-w.

MALDANER N, STIENEN M N, BIJLENGA P, et al . Interrater agreement in the radiologic characterization of ruptured intracranial aneurysms based on computed tomography angiography[J ] . World Neurosurg, 2017, 103: 876-882. e1. DOI: 10.1016/j.wneu.2017.04.131.

SHI Z, HU B, SCHOEPF U J, et al . Artificial intelligence in the management of intracranial aneurysms: current status and future perspectives[J ] . AJNR Am J Neuroradiol, 2020, 41(3): 373-379. DOI: 10.3174/ajnr.A6468.

FU F, WEI J, ZHANG M, et al . Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network[J ] . Nat Commun, 2020, 11(1): 4829. DOI: 10.1038/s41467-020-18606-2.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Early identification of delayed cerebral ischemia following aneurysmal subarachnoid hemorrhage: development and validation of a multifactorial clinical prediction model

Diagnostic value of endoscopic LCPL sign for high-risk intestinal metaplasia in gastric mucosa

Construction of a diagnostic model for chronic mountain sickness among young male migrants to high-altitude areas

Prediction of in-hospital mortality risk in intensive care unit with support vector machine

Development of intelligent delineation model for clinical target volume of nasopharyngeal carcinoma based on integrated clinical health care system

Related Author

ZHENG Hui

TAO Yihao

JI Xiang

MA Ying

ZHENG Xipeng

PAN Huilin

WU Linyu

HOU Yongying

Related Institution

Department of Neurosurgery， the Second Affiliated Hospital of Chongqing Medical University

Department of Gastroenterology， Chongqing Key Laboratory of Precise Prevention and Treatment of Digestive Malignancies

Department of Pathology， Army Medical Center of PLA/Daping Hospital of Third Military Medical University， Chongqing

First Clinical College of Chongqing Medical University

Department of High Altitude Physiology and Pathology, Faculty of High Altitude Military Medicine， Army Medical University （Third Military Medical University）

⁰