Three-dimensional semi-automatic segmentation of intracranial aneurysms in CTA

Nikravanshalmani, Alireza; Qanadli, Salah D.; Ellis, Tim; Crocker, Matthew; Ebrahimdoost, Yousef; Karamimohammadi, Mojdeh; Dehmeshki, Jamshid

doi:10.1109/itab.2010.5687759

Cited by 4 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Conventional approaches have used rule-based 2D or 3D shape analyses. For example, Nikravanshalmani et al [3,12] used a level set algorithm and a region growing based approach for semi-automatic segmentation of cerebral aneurysms from computed tomography angiography (CTA) images. Law and Chung [4,13] proposed an intensity-based algorithm to segment intracranial vessels and embedded aneurysms using multirange filters and local variances.…”

Section: Segmentationmentioning

confidence: 99%

“…Over the last decade, many extraction algorithms have been designed by calculating local geometric features [3,4]; however, rule-based methods have high computational costs and time requirements, and their performance is limited because of the wide variety of aneurysm shapes. Meanwhile, deep learning techniques are becoming increasingly popular in medical image processing; however, they are mostly used for classification and detection.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms

et al. 2022

View full text Add to dashboard Cite

The exact shape of intracranial aneurysms is critical in medical diagnosis and surgical planning. While voxel-based deep learning frameworks have been proposed for this segmentation task, their performance remains limited. In this study, we offer a two-step surface-based deep learning pipeline that achieves significantly better results. Our proposed model takes a surface model of an entire set of principal brain arteries containing aneurysms as input and returns aneurysm surfaces as output. A user first generates a surface model by manually specifying multiple thresholds for time-of-flight magnetic resonance angiography images. The system then samples small surface fragments from the entire set of brain arteries and classifies the surface fragments according to whether aneurysms are present using a point-based deep learning network (PointNet++). Finally, the system applies surface segmentation (SO-Net) to surface fragments containing aneurysms. We conduct a direct comparison of the segmentation performance of our proposed surface-based framework and an existing voxel-based method by counting voxels: our framework achieves a much higher Dice similarity (72%) than the prior approach (46%).

show abstract

Section: Segmentationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms

et al. 2022

View full text Add to dashboard Cite

show abstract

“…There are several advantages associated with the use of level sets, which are able to handle the topological changes of the contours and achieve sub-pixel accuracy for detection of the vessel boundaries. The proposed technique is an extension of our previous research applied on pulmonary embolism (PE) and brain aneurysms (BA) segmentation [6], [7] with the inclusion of a new stopping criterion which has frequently been ignored by other level set implementations. The remainder of this paper organized as follows; section-2 presents the proposed method: section-3 presents the experimental results and section-4 the conclusion.…”

Section: Introductionmentioning

confidence: 99%

Automatic segmentation of Pulmonary Artery (PA) in 3D pulmonary CTA images

Ebrahimdoost

Qanadli

Nikravanshalmani

et al. 2011

2011 17th International Conference on Digital Signal Processing (DSP)

Self Cite

View full text Add to dashboard Cite

This paper proposes an efficient algorithm for segmenting the Pulmonary Artery (PA) tree in 3D pulmonary Computed Tomography Angiography (CTA) images. In this algorithm, to reduce the search area the lung regions from the original image are first segmented and the heart region is extracted by selecting the regions between the lungs. A pre-processing algorithm based on Hessian matrix and its eigenvalues is used to remove the connectivity between the pulmonary artery and other nearby pulmonary organs. To extract the pulmonary artery tree, we first use a region growing method initialized by a seed point which is automatically selected within the pulmonary artery trunk in the heart region. In the second step, the segmentation of the pulmonary artery is performed using a 3D level set algorithm, using the output of region grower as the initial contour. We use a new stopping criterion for the used level set algorithm, a consideration often neglected in many level set implementations. To validate and assess the robustness of the method, 20 CT angiography datasets were used (10 free pulmonary embolism scans and 10 CT with pulmonary emboli). A very good agreement with the visual judgment was obtained in both normal and positive pulmonary emboli CT scans.

show abstract

Amalgamation of iterative double automated thresholding and morphological filtering: a new proposition in the early detection of cerebral aneurysm

Chandra

Mondal

2016

Multimed Tools Appl

View full text Add to dashboard Cite

Three-dimensional semi-automatic segmentation of intracranial aneurysms in CTA

Cited by 4 publications

References 9 publications

A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms

A two-step surface-based 3D deep learning pipeline for segmentation of intracranial aneurysms

Automatic segmentation of Pulmonary Artery (PA) in 3D pulmonary CTA images

Amalgamation of iterative double automated thresholding and morphological filtering: a new proposition in the early detection of cerebral aneurysm

Contact Info

Product

Resources

About