Evaluation of multiple deep neural networks for detection of intracranial dural arteriovenous fistula on susceptibility weighted angiography imaging

Abstract

Background

The natural history of intracranial dural arteriovenous fistula (DAVF) is variable and early diagnosis is crucial in order to positively impact the clinical course of aggressive DAVF. Artificial intelligence (AI) based techniques can be promising in this regard, and in this study, we used various deep neural network (DNN) architectures to determine whether DAVF could be reliably identified on susceptibility-weighted angiography images (SWAN).

Materials and Methods

A total of 3965 SWAN image slices from 30 digital subtraction angiographically proven DAVF patients and 4380 SWAN image slices from 40 age-matched patients with normal MRI findings as control group were included. The images were categorized as either DAVF or normal and the data was trained using various DNN such as VGG-16, EfficientNet-B0, and ResNet-50.

Results

Various DNN architectures showed the accuracy of 95.96% (VGG-16), 91.75% (EfficientNet-B0), and 86.23% (ResNet-50) on the SWAN image dataset. ROC analysis yielded an area under the curve of 0.796 (p < .001), best for VGG-16 model. Criterion of seven consecutive positive slices for DAVF diagnosis yielded a sensitivity of 74.68% with a specificity of 69.15%, while setting eight slices improved the sensitivity to above 80.38%, with a decrease of specificity up to 56.38%. Based on seven consecutive positive slices criteria, EfficientNet-B0 yielded a sensitivity of 73.21% with a specificity of 45.92% and ResNet-50 yielded a sensitivity of 72.39% with a specificity of 67.42%.

Conclusion

This study shows that DNN can extract discriminative features of SWAN for the classification of DAVF from normal with good accuracy, reasonably good sensitivity and specificity.

Keywords

Dural arteriovenous fistula deep neural network susceptibility-weighted angiography image artificial intelligence

Get full access to this article

View all access options for this article.

References

Saini

Thomas

Bodhey

, et al. Susceptibility-weighted imaging in cranial dural arteriovenous fistulas: 1. Am J Neuroradiol 2008; 30(1): e6–6.

Jain

Kannath

Kapilamoorthy

, et al. The application of susceptibility-weighted MRI in pre-interventional evaluation of intracranial dural arteriovenous fistulas. J Neurointerventional Surg 2017; 9(5): 502–507.

Reynolds

Lanzino

Zipfel

. Intracranial dural arteriovenous fistulae. Stroke 2017; 48(5): 1424–1431.

Zaharchuk

Gong

Wintermark

, et al. Deep learning in neuroradiology. AJNR Am J Neuroradiol 2018; 39(10): 1776–1784.

Hosny

Parmar

Quackenbush

, et al. Artificial intelligence in radiology. Nat Rev Cancer 2018; 18(8): 500–510, Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6268174/

Duong

Rauschecker

Mohan

. Diverse applications of artificial intelligence in neuroradiology. Neuroimaging Clin 2020; 30(4): 505–516. DOI: 10.1016/j.nic.2020.07.003.

Wang

Chen

. Neural network helps determine the hemorrhagic risk of cerebral arteriovenous malformation. Electronics 2023; 12(20): 4241.

Wang

Shen

Yang

, et al. A deep learning algorithm for automatic detection and classification of acute intracranial hemorrhages in head CT scans. Neuroimage Clin 2021; 32: 102785.

Zipfel

Shah

Refai

, et al. Cranial dural arteriovenous fistulas: modification of angiographic classification scales based on new natural history data. Neurosurg Focus 2009; 26(5): E14.

10.

Hou

, et al. Intracranial dural arteriovenous fistulas with brainstem engorgement: an under-recognized entity in diagnosis and treatment. Front Neurol 2020; 11: 11.

11.

Wang

van Heerden

Tacey

, et al. Neuroradiologists compared with non-neuroradiologists in the detection of new multiple sclerosis plaques. AJNR Am J Neuroradiol 2017; 38(7): 1323–1327.

12.

Geijer

. Added value of double reading in diagnostic radiology,a systematic review. Insights Imaging 2018; 9(3): 287–301.

13.

Joseph

Sekar

Kannath

, et al. Impaired intrinsic functional connectivity among medial temporal lobe and sub-regions related to memory deficits in intracranial dural arteriovenous fistula. Neuroradiology 2021; 63(10): 1679–1687.

14.

Sekar

Kannath

Ramachandran

, et al. Alterations in resting-state functional MRI connectivity related to cognitive changes in intracranial dural arteriovenous fistulas before and after embolization treatment. J Magn Reson Imag 2021.

15.

Yahav-Dovrat

Saban

Merhav

, et al. Evaluation of artificial intelligence–powered identification of large-vessel occlusions in a comprehensive stroke center. AJNR Am J Neuroradiol 2021;42(2):247–254. Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7872164/

16.

Nakao

Hanaoka

Nomura

, et al. Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imag 2018; 47(4): 948–953.

17.

Sichtermann

Faron

Sijben

, et al. Deep learning–based detection of intracranial aneurysms in 3D TOF-MRA. AJNR Am J Neuroradiol 2019; 40(1): 25–32.

18.

Park

Chute

Rajpurkar

, et al. Deep learning–assisted diagnosis of cerebral aneurysms using the HeadXNet model. JAMA Netw Open 2019;2(6):e195600. Available from: https://jamanetwork.com/journals/jamanetworkopen/fullarticle/2735471?resultClick=3

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.53 MB