A method for automatic detection and classification of stroke from brain CT images

Abstract

Computed tomographic (CT) images are widely used in the diagnosis of stroke. In this paper, we present an automated method to detect and classify an abnormality into acute infarct, chronic infarct and hemorrhage at the slice level of non-contrast CT images. The proposed method consists of three main steps: image enhancement, detection of mid-line symmetry and classification of abnormal slices. A windowing operation is performed on the intensity distribution to enhance the region of interest. Domain knowledge about the anatomical structure of the skull and the brain is used to detect abnormalities in a rotation- and translation-invariant manner. A two-level classification scheme is used to detect abnormalities using features derived in the intensity and the wavelet domain. The proposed method has been evaluated on a dataset of 15 patients (347 image slices). The method gives 90% accuracy and 100% recall in detecting abnormality at patient level; and achieves an average precision of 91% and recall of 90% at the slice level.

Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: Segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal

“…All the previous methods were applied to MR images. For CT data, we only found one paper (Chawla et al, 2009): Chawla et al proposed an automatic histogram and wavelet-based two-level classification scheme to depict acute and chronic ischemic lesions separately.…”

Computer-aided simple triage

“…Among those are systems for stroke detection and classification [9,10], detection of pulmonary embolism (PE) [11], aortic dissection [12,13], coronary artery disease [14,19]. Let us examine the differences between this new CAD arena and the traditional CAD environment described in the previous section.…”

“…While some body of work has been reported on automatic emergency diagnostic imaging interpretation (aortic dissection [12,13], PE [11], coronary artery disease [14,19], stroke [9,10], lung diseases, bone fractures [18]), there are only a few CAD systems available commercially, which operate in CAST-related fields-namely PE and coronary artery disease. To the best of our knowledge, the diagnostic performance of PE CAD systems today (low specificity) prevents them to be used in CAST scenarios [11].…”

Recovery of CT stroke hypodensity – An adaptive variational approach

“…Domain knowledge of the skull and the brain anatomical structure was used to detect abnormalities in a rotation-and translationinvariant manner. Tissue descriptors calculated in both the image and the wavelet domains were confirmed to be effective [24]. Recently, automatic infarct delineation in stroke CT images with accurate normalization of CT scans into template space and the subsequent voxel-wise comparison with control CT images to define areas with hypointense signals were proposed [12].…”