A Deep Learning Model with High Standalone Performance for Diagnosis of Unruptured Intracranial Aneurysm
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: This study aimed to investigate whether a deep learning model for automated detection of unruptured intracranial aneurysms on time-of-flight (TOF) magnetic resonance angiography (MRA) can achieve a target diagnostic performance comparable to that of human radiologists for approval from the Korean Ministry of Food and Drug Safety as an artificial intelligence-applied software. Materials and Methods: In this single-center, retrospective, confirmatory clinical trial, the diagnostic performance of the model was evaluated in a predetermined test set. After sample size estimation, the test set consisted of 135 aneurysm-containing examinations with 168 intracranial aneurysms and 197 aneurysm-free examinations. The target sensitivity and specificity were set as 87% and 92%, respectively. The patient-wise sensitivity and specificity of the model were analyzed. Moreover, the lesion-wise sensitivity and false-positive detection rate per case were also investigated. Results: The sensitivity and specificity of the model were 91.11% [95% confidence interval (CI): 84.99, 95.32] and 93.91% (95% CI: 89.60, 96.81), respectively, which met the target performance values. The lesion-wise sensitivity was 92.26%. The overall falsepositive detection rate per case was 0.123. Of the 168 aneurysms, 13 aneurysms from 12 examinations were missed by the model. Conclusion: The present deep learning model for automated detection of unruptured intracranial aneurysms on TOF MRA achieved the target diagnostic performance comparable to that of human radiologists. With high standalone performance, this model may be useful for accurate and efficient diagnosis of intracranial aneurysm.
Abstract
Purpose: This study aimed to investigate whether a deep learning model for automated detection of unruptured intracranial aneurysms on time-of-flight (TOF) magnetic resonance angiography (MRA) can achieve a target diagnostic performance comparable to that of human radiologists for approval from the Korean Ministry of Food and Drug Safety as an artificial intelligence-applied software. Materials and Methods: In this single-center, retrospective, confirmatory clinical trial, the diagnostic performance of the model was evaluated in a predetermined test set. After sample size estimation, the test set consisted of 135 aneurysm-containing examinations with 168 intracranial aneurysms and 197 aneurysm-free examinations. The target sensitivity and specificity were set as 87% and 92%, respectively. The patient-wise sensitivity and specificity of the model were analyzed. Moreover, the lesion-wise sensitivity and false-positive detection rate per case were also investigated. Results: The sensitivity and specificity of the model were 91.11% [95% confidence interval (CI): 84.99, 95.32] and 93.91% (95% CI: 89.60, 96.81), respectively, which met the target performance values. The lesion-wise sensitivity was 92.26%. The overall falsepositive detection rate per case was 0.123. Of the 168 aneurysms, 13 aneurysms from 12 examinations were missed by the model. Conclusion: The present deep learning model for automated detection of unruptured intracranial aneurysms on TOF MRA achieved the target diagnostic performance comparable to that of human radiologists. With high standalone performance, this model may be useful for accurate and efficient diagnosis of intracranial aneurysm.
참고문헌 (30)
- van Gijn J, "Subarachnoid haemorrhage", Lancet, 369, pp.306~318 (2007)
- UCAS Japan Investigators, "The natural course of unruptured cerebral aneurysms in a Japanese cohort", N Engl J Med, 366, pp.2474~2482 (2012)
- Backes D, "PHASES score for prediction of intracranial aneurysm growth", Stroke, 46, pp.1221~1226 (2015)
- Thompson BG, "Guidelines for the management of patients with unruptured intracranial aneurysms : a guideline for healthcare professionals from the American Heart Association", American Stroke Association, 2015, pp.46, 2368~2400
- Sailer AM, "Diagnosing intracranial aneurysms with MR angiography : systematic review and meta-analysis", Stroke, 45, pp.119~126 (2014)
- Li MH, "Accurate diagnosis of small cerebral aneurysms ≤5 mm in diameter with 3.0-T MR angiography", Radiology, 271, pp.553~560 (2014)
- McDonald RJ, "The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload", Acad Radiol, 22, pp.1191~1198 (2015)
- "Magnetic resonance imaging (MRI) exams"[URL]
- Shi Z, "Artificial intelligence in the management of intracranial aneurysms : current status and future perspectives", AJNR Am J Neuroradiol, 41, pp.373~379 (2020)
- Nakao T, "Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography", J Magn Reson Imaging, 47, pp.948~953 (2018)
- Ueda D, "Deep learning for MR angiography : automated detection of cerebral aneurysms", Radiology, 290, pp.187~194 (2019)
- Sichtermann T, "Deep learning-based detection of intracranial aneurysms in 3D TOF-MRA", AJNR Am J Neuroradiol, 40, pp.25~32 (2019)
- Stember JN, "Convolutional neural networks for the detection and measurement of cerebral aneurysms on magnetic resonance angiography", J Digit Imaging, 32, pp.808~815 (2019)
- Faron A, "Performance of a deep-learning neural network to detect intracranial aneurysms from 3D TOF-MRA compared to human readers", Clin Neuroradiol, 30, pp.591~598 (2020)
- Joo B, "A deep learning algorithm may automate intracranial aneurysm detection on MR angiography with high diagnostic performance", Eur Radiol, 30, pp.5785~5793 (2020)
- Hiratsuka Y, "Diagnosis of unruptured intracranial aneurysms : 3T MR angiography versus 64-channel multi-detector row CT angiography", Magn Reson Med Sci, 7, pp.169~178 (2008)
- Li MH, "Contrastfree MRA at 3.0 T for the detection of intracranial aneurysms", Neurology, 77, pp.667~676 (2011)
- White PM, "Intracranial aneurysms : CT angiography and MR angiography for detection prospective blinded comparison in a large patient cohort", Radiology, 219, pp.739~749 (2001)
- White PM, "The non-invasive detection of intracranial aneurysms: are neuroradiologists any better than other observers?", Eur Radiol, 13, pp.389~396 (2003)
- Hajian-Tilaki K, "Sample size estimation in diagnostic test studies of biomedical informatics", J Biomed Inform, 48, pp.193~204 (2014)
- Wang R, "Threshold segmentation algorithm for automatic extraction of cerebral vessels from brain magnetic resonance angiography images", J Neurosci Methods, 241, pp.30~36 (2015)
- He K, "Deep residual learning for image recognition", Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016), Institute of Electrical and Electronics Engineers (IEEE)
- Ronneberger O, "U-net: convolutional networks for biomedical image segmentation", Proceedings of the 18th International Conference on Medical Image Computing and ComputerAssisted Intervention 2015 (MICCAI 2015), pp.234~241 (2015), Springer
- Park A, "Deep learning-assisted diagnosis of cerebral aneurysms using the HeadXNet model", JAMA Netw Open, 2, pp.e195600~ (2019)
- Miki S, "Computer-assisted detection of cerebral aneurysms in MR angiography in a routine image-reading environment : effects on diagnosis by radiologists", AJNR Am J Neuroradiol, 37, pp.1038~1043 (2016)
- van Ginneken B, "Computer-aided diagnosis : how to move from the laboratory to the clinic", Radiology, 261, pp.719~732 (2011)
- Hyoung Soo Byoun, "Natural History of Unruptured Intracranial Aneurysms : A Retrospective Single Center Analysis", 대한신경외과학회지, 59(1), pp.11~16 (2016), 대한신경외과학회
- Wiebers DO, "Unruptured intracranial aneurysms : natural history, clinical outcome, and risks of surgical and endovascular treatment", Lancet, 362, pp.103~110 (2003)
- Sekhar LN, "Unyielding progress : treatment paradigms for giant aneurysms", Clin Neurosurg, 59, pp.6~21 (2012)
- Howard BM, "Comprehensive review of imaging of intracranial aneurysms and angiographically negative subarachnoid hemorrhage", Neurosurg Focus, 47, pp.E20~ (2019)