Improving Diagnostic Value of CT Examinations in Hyperacute Ischemic Stroke
This paper presents a computer assisted support of ischemic stroke diagnosis based on nonenhanced CT examinations acquired in the hyperacute phase of stroke. Computational analysis, recognition, and image understanding methods were used for extraction of
- PDF / 684,625 Bytes
- 6 Pages / 595.276 x 790.866 pts Page_size
- 5 Downloads / 199 Views
Abstract This paper presents a computer assisted support of ischemic stroke diagnosis based on nonenhanced CT examinations acquired in the hyperacute phase of stroke. Computational analysis, recognition, and image understanding methods were used for extraction of the subtlest signs of hypodensity in diagnostically important areas. Starting from perception improvement, suggestive and coarse image data visualization was designed as a complement of the standard diagnosis procedure based on CT scan soft-copy review. The proposed method includes an evidence-based description of ischemic conditions and changes, de-skulling and segmenting of unusual areas, the analysis of hypodensity signs across scales and subbands with noise reduction, and hypodensity extraction. Following visualization, forms of empowered hypodensity symptoms localize suggested ischemic areas in source brain image space. Increased visibility of cerebral ischemia for difficult-to-diagnose cases was experimentally noticed and improved diagnostic value of CT was concluded. Keywords Computer aided diagnosis • hyperacute stroke detection • multiscale image analysis • image content extraction
Introduction The recent advent of thrombolytic therapy for hyperacute stroke treatment makes the earliest detection of areas of hypoattenuating ischemic parenchyma exceedingly important (1–4). However, although CT plays a crucial role in the evaluation of stroke patients, it is not sufficient for A. Przelaskowski (*) and G. Ostrek Institute of Radioelectronics, Warsaw University of Technology, Warsaw, Poland e-mail: [email protected] J. Walecki Department of Radiology and Department of Experimental Pharmacology, Centre of Experimental and Clinical Medicine, Polish Academy of Science, Warsaw, Poland K. Sklinda Department of Radiology CMKP, CSK MSWiA, Warsaw, Poland
visualizing infracted cerebral tissues in the hyperacute stage. On the initial CT-scan, performed during the hyperacute phase of stroke (0–6 h), a hypodense area (direct infarct sign defined as any area in the brain with density lower than normal) surrounding brain tissues does not need to be seen. Early indirect findings, such as obscuration of gray/white matter differentiation and effacement of sulci or “insular ribbon sign”, may be sometimes noticed instead. Afterwards, it becomes possible to detect a slight hypodense area of infarction either in the cortices or the basal ganglia. Initially, the low density region is poorly defined, becoming more sharply delineated in the following hours (1–7). However, many infarcts do not emerge on CT until hours after the onset of stroke; 50–60% of stroke cases have normal CT before 12 h after stroke onset (8). Hence, effective and reliable computer assistance, which has become one of the major research subjects in medical imaging and diagnostic radiology (9), is considered to improve diagnostic value of CT examinations for those cases. Computer aided diagnosis (CAD) is a sophisticated program that supports the doctor’s interpretations and findings. Automatic det
Data Loading...
