Automatic detection of intracranial aneurysms in 3D-DSA based on a Bayesian optimized filter

Abstract

Background Intracranial aneurysm is a common type of cerebrovascular disease with a risk of devastating subarachnoid hemorrhage if it is ruptured. Accurate computer-aided detection of aneurysms can help doctors improve the diagnostic accuracy, and it is very helpful in reducing the risk of subarachnoid hemorrhage. Aneurysms are detected in 2D or 3D images from different modalities. 3D images can provide more vascular information than 2D images, and it is more difficult to detect. The detection performance of 2D images is related to the angle of view; it may take several angles to determine the aneurysm. As the gold standard for the diagnosis of vascular diseases, the detection on digital subtraction angiography (DSA) has more clinical value than other modalities. In this study, we proposed an adaptive multiscale filter to detect intracranial aneurysms on 3D-DSA. Methods Adaptive aneurysm detection consists of three parts. The first part is a filter based on Hessian matrix eigenvalues, whose parameters are automatically obtained by Bayesian optimization. The second part is aneurysm extraction based on region growth and adaptive thresholding. The third part is the iterative detection strategy for multiple aneurysms. Results The proposed method was quantitatively evaluated on data sets of 145 patients. The results showed a detection precision of 94.6%, and a sensitivity of 96.4% with a false-positive rate of 6.2%. Among aneurysms smaller than 5 mm, 93.9% were found. Compared with aneurysm detection on 2D-DSA, automatic detection on 3D-DSA can effectively reduce the misdiagnosis rate and obtain more accurate detection results. Compared with other modalities detection, we also get similar or better detection performance. Conclusions The experimental results show that the proposed method is stable and reliable for aneurysm detection, which provides an option for doctors to accurately diagnose aneurysms.

Multi-View Convolutional Neural Networks in Rupture Risk Assessment of Small, Unruptured Intracranial Aneurysms

“…The regional average grayscale suppression was used to differentiate ROI of aneurysm and enlargement area [ 24 ]. Hu et al [ 25 ] used Bayesian optimization for aneurysm detection based on DSA images, showing a sensitivity of 96.4% with a false-positive rate of 6.2%. However, in most cases in daily practice, DSA is additionally performed to acquire detailed information of aneurysm including relationship with nearby arteries to decide the treatment plan [ 26 ], but not the diagnosis of aneurysm itself [ 5 ].…”

Toward a 3D Arterial Tree Bifurcation Model for Intra-Cranial Aneurysm Detection and Segmentation

“…For each bifurcation, when its configuration made it possible, we have independently embedded three ICA (one between each pair of branches). In total, 14 073 ICA were thus generated, with arteries diameters in the range [4,8], the amplitude (in grey levels) of the arteries were in [220, 290], 3 different parameters were used for the elastic deformations, the target average of the background noise (white matter) was in the interval [50, 110] whereas its standard deviation was in [7,11]. As previously explained, the darker noise was simply set to 2/3 of the white matter average.…”

“…Furthermore, although ICA detection is a widely studied field [8], the aneurysm segmentation is more marginally investigated [9], [10]. Authors in [11] used a Bayesian optimized filter for the automatic detection of ICA on DSA acquisitions. Quite often, the authors turn to 2D projected images [8], such as Maximum Intensity Projection (MIP) for various tasks of pattern recognition, as such 2D projections offers a better contrast.…”

A deep learning–based automatic system for intracranial aneurysms diagnosis on three‐dimensional digital subtraction angiographic images

“…5 Deep neural network, such as convolutional neural network, has been applied in the detection of aneurysms from MRA images, [6][7][8][9] CTA images, [10][11][12][13][14] and DSA images. [15][16][17][18] For rupture risk prediction, most studies employ statistical learning algorithms such as logistic regression, support vector machine, and random forest, with features such as morphology, 19 hemodynamics, 20 radiomics, 21,22 and demographics 23 as input variables. A few studies applied deep learning on images for rupture prediction.…”

“…provided a detailed review of artificial intelligence applied for the detection, risk management, and treatment planning of IAs 5 . Deep neural network, such as convolutional neural network, has been applied in the detection of aneurysms from MRA images, 6–9 CTA images, 10–14 and DSA images 15–18 . For rupture risk prediction, most studies employ statistical learning algorithms such as logistic regression, support vector machine, and random forest, with features such as morphology, 19 hemodynamics, 20 radiomics, 21,22 and demographics 23 as input variables.…”