Towards developing a segmentation method for cerebral aneurysm using a statistical multiresolution approach

• Published in: Egyptian journal of neurosurgery Vol. 38; no. 1; pp. 33 - 14
• Main Authors: Regaya, Yousra, Amira, Abbes, Dakua, Sarada Prasad
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2023; Springer Nature B.V; SpringerOpen
• Subjects: 3D Rotational angiography; Accuracy; Algorithms; Aneurysms; Cerebral aneurysm; Datasets; Deep learning; Medical imaging; Medicine; Medicine & Public Health; Methods; Multiresolution analysis; Neural networks; Neurosurgery; Parameter estimation; Segmentation; Cerebral aneurysm; 3D Rotational angiography; Segmentation; Multiresolution analysis
• ISSN: 2520-8225; 1687-5982; 2520-8225
• DOI: 10.1186/s41984-023-00213-0

The computer aided diagnosis (CAD) algorithms are considered crucial during the treatment planning of cerebral aneurysms (CA), where segmentation is the first and foremost step. This paper presents a segmentation algorithm in two-dimensional domain combining a multiresolution and a statistical approach. Precisely, Contourlet transform (CT) extracts the image features, while Hidden Markov Random Field with Expectation Maximization (HMRF-EM) segments the image, based on the spatial contextual constraints. The proposed algorithm is tested on Three-Dimensional Rotational Angiography (3DRA) datasets; the average values of accuracy, DSC, FPR, FNR, specificity, and sensitivity, are found to be 99 . 64%, 92 . 44%, 0 . 09%, 5 . 81%, 99 . 84%, and 93 . 22%, respectively. Both qualitative and quantitative results obtained show the potential of the proposed method.