RESUMEN
Computer-aided analysis of non-contrast computed tomography (NCCT) images for rapid diagnosis of ischaemic stroke is based on the augmented visualisation of evolving ischaemic lesions. Computerised support of NCCT often leads to overinterpretation of ischaemic areas, thus it is of great interest to provide neurologically verified regions in order to improve accuracy of subsequent radiological assessment. We propose Stroke Bricks (StBr) as an arbitrary spatial division of brain tissue into the regions associated with specific clinical symptoms of ischaemic stroke. Neurological stroke deficit is formally translated into respective areas of possible ischaemic lesions. StBr were designed according to formalised mapping of neurological symptoms and were attributed to the uniquely defined areas of impaired blood supply. StBr concept may be useful for an integrated radiological CT-based assessment of suspected stroke cases or can be included into computer-aided tools to optimise the evaluation of stroke site and its extent. These data in turn are appropriable for further diagnosis, predicting the therapeutic outcome as well as for patients' qualification for an appropriate form of reperfusion therapy. The usefulness of StBr was illustrated in the case studies.
RESUMEN
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.
Asunto(s)
Interpretación de Imagen Radiográfica Asistida por Computador/métodos , Accidente Cerebrovascular/diagnóstico por imagen , Tomografía Computarizada por Rayos X/métodos , Algoritmos , Mapeo Encefálico , HumanosRESUMEN
Nonenhanced computerized tomography (CT) exams were used to detect acute stroke by notification of hypodense area. Infarction perception improvement by data denoising and local contrast enhancement in multi-scale domain was proposed. The wavelet-based image processing method enhanced the subtlest signs of hypodensity, which were often invisible in standard CT scan review. Thus improved detection efficiency of perceptual ischemic changes was investigated. Data processing became more effective by initial segmentation of brain tissue and extraction of regions susceptible to tissue density changes. The new method was experimentally verified. Sensitivity of stroke diagnosis increased to 56.3% in comparison to 12.5% of standard CT scan preview.