Ischemic infarct detection, localization, and segmentation in noncontrast CT human brain scans: review of automated methods

Abstract

Noncontrast Computed Tomography (NCCT) of the brain has been the first-line diagnosis for emergency evaluation of acute stroke, so a rapid and automated detection, localization, and/or segmentation of ischemic lesions is of great importance. We provide the state-of-the-art review of methods for automated detection, localization, and/or segmentation of ischemic lesions on NCCT in human brain scans along with their comparison, evaluation, and classification. Twenty-two methods are (1) reviewed and evaluated; (2) grouped into image processing and analysis-based methods (11 methods), brain atlas-based methods (two methods), intensity template-based methods (1 method), Stroke Imaging Marker-based methods (two methods), and Artificial Intelligence-based methods (six methods); and (3) properties of these groups of methods are characterized. A new method classification scheme is proposed as a 2 × 2 matrix with local versus global processing and analysis, and density versus spatial sampling. Future studies are necessary to develop more efficient methods directed toward deep learning methods as well as combining the global methods with a high sampling both in space and density for the merged radiologic and neurologic data.

Taxonomy of Acute Stroke: Imaging, Processing, and Treatment

“…Rekik et al [16] divided methods for ischemic stroke image management into four groups: pixel-and voxel-based classification, image-based segmentation, atlasbased segmentation, and deformable model-based segmentation. Nowinski et al [13] proposed a 2 × 2 matrix-based classification with local versus global image processing and analysis, and density versus spatial sampling. Inamdar et al [17] The diagnosis and treatment of acute stroke have changed dramatically during the last few years because of the recent advances in endovascular treatment (as reviewed by Widimsky et al [138] in terms of key stroke trials, devices, and techniques) and portable stroke imaging, which is crucial in time-critical situations.…”

“…In addition, within the first 3 h, this sensitivity is lowered to 7% for CT and 46% for MR [12]. Numerous neuroimage processing and analysis methods have been developed for stroke management based on various criteria and techniques, as reviewed in several papers covering CT [13][14][15], MR and CT [16,17], and artificial intelligence (AI) and deep learning (DL) techniques [18][19][20][21][22][23]. They facilitate the interpretation of stroke scans and assist in decision-making in stroke management.…”

Identification of early invisible acute ischemic stroke in non-contrast computed tomography using two-stage deep-learning model

“…Using AI for image post-processing and interpretation in stroke can recognize in-depth information and reduce the differences between radiologists [15]. The AI model has shown great performance in detecting large vessel occlusion through the cerebral artery hyperdense sign in NCCT, and automated Alberta Stroke Program Early CT Score (ASPECTS) rating with lesions in the middle cerebral artery area [16][17][18][19], but few studies discussed the invisible multi-size lesions distributed over the entire brain.…”