Komputerowe wspomaganie detekcji zmian chorobowych w badaniach perfuzji mózgowej

• Autorzy: Ogiela M. R. , Hachaj T.

Warianty tytułu

EN

Computer - aided detection of brain perfusion lesions

• Języki publikacji: PL

Abstrakty

PL

Autorzy artykułu prezentują nowoczesne podejście do zadania komputerowego wspomagania detekcji zmian chorobowych perfuzji mózgowej. Na podstawie zaprezentowanego w tej pracy algorytmu stworzony został systemu wspomagający diagnozę medyczną, którego działanie zostało sprawdzone na rzeczywistych danych medycznych. Rozmiar zbioru testowego obejmował 75 zestawów zobrazowań pochodzących od 30 różnych pacjentów (w zbiorze tym znajdowały się zarówno zobrazowania pacjentów, u których zdiagnozowano zmiany perfuzyjne o różnym stopniu nasilenia, jak i pacjenci z prawidłowymi wartościami perfuzji). W 77,3% przypadkach opis zdjęcia wygenerowany przez algorytm autorów był taki sam jak opis sporządzony przez lekarza radiologii.

EN

The paper presents a novel approach to analysis of brain perfusion maps based on automatic image understanding. Perfusion-weighted CT (computer tomography) and MR (magnetic resonance) tech-niques, in contrast to MR and CT angiography detecting bulk vessel flow, are sensitive to microscopic, tissue-level blood flow. PCT (perfusion CT) technique enables evaluating total and regional blood flows per unit time. PCT gives a variety of functional maps of cerebral perfusion parameters such as regional Cerebral Blood Flow (CBF), Cerebral Blood Volume (CBV) and Mean Transit Time (MTT). Each pixel of a perfusion map corresponds to the perfusion value at a given point. The colour images help quick diagnosis of an acute stroke in the event of a crisis (Fig. 1). Computer vision at the current development stage offers three types of computer image handling methods [1]: image processing (quality improvement, distinguishing object of interests from the whole complex image), image analysis (defining the features of entire image or particular objects) and pattern recognition. The fusion of those three methods with medical knowledge leads to complete understanding of the visualized symptoms (Fig. 2) [13]. Automatic image understanding of medical images is a new approach that enables drawing con-clusions about the nature of the observed disease process (Fig. 3) as well as deciding on the way in which this pathology can be cured of with use of various therapeutics methods. The validation of the presented algorithms was performed on a set of 75 triplets of medical images acquired from 30 different adult patients (men and women) with suspected ischemia / stroke. In 77.3% cases description generated by the algorithm match the diagnosis made by a physician.

Słowa kluczowe

PL

inteligentna analiza i rozumienie obrazów; badanie dynamicznej perfuzji mózgu; systemy komputerowego wspomagania diagnostyki medycznej

EN

intelligent image processing and understanding; dynamic brain perfusion treatment; computer-aided diagnosis systems

• Wydawca: Wydawnictwo PAK
• Czasopismo: Pomiary Automatyka Kontrola
• Rocznik: 2010
• Tom: R. 56, nr 5
• Strony: 453--456
• Opis fizyczny: Bibliogr. 15 poz., rys., wzory

Twórcy

autor

Ogiela M. R.

autor

Hachaj T.

• Katedra Automatyki, Akademia Górniczo-Hutnicza im. Stanisława Staszica, Al. Mickiewicza 30, 30-059 Kraków,

Bibliografia

• [1] Ogiela M. R., Tadeusiewicz R.: Modern Computational Intelligence Methods for the Interpretation of Medical Images, Studies in Computational Intelligence, Vol. 84, Springer 2008.
• [2] Zierler K. L.: Equations for measuring blood flow by external monitoring of radioisotopes, Circ Res 1965;16:309-21.
• [3] Hachaj T.: An algorithm for detecting lesions in CBF and CBV perfusion maps, Bio-Algorithms and Med-Systems, Collegium Medicum - Jagiellonian University Vol. 7, Collegium Medicum - Jagiellonian University, 2008; 35-41.
• [4] Hachaj T.: The unified algorithm for detection potential lesions in dynamic perfusion maps CBF, CBV and TTP, Journal of Medical Informatics & Technologies, Vol. 12, 2008; 117-122.
• [5] Thompson P., Mega M., Narr K., Sowell E., Blanton R., Toga A.: Brain image analysis and atlas construction, Handbook of Medical Imaging chapter 17. SPIE. 2000; 1066-1119.
• [6] Hachaj T.: The registration and atlas construction of noisy brain computer tomography images based on free form deformation technique, Bio-Algorithms and Med-Systems, Vol. 7, Collegium Medicum - Jagiellonian University, 2008; 43-50.
• [7] Eastwood J. D. et al.: CT perfusion scanning with deconvolution analysis: pilot study in patients with acute middle cerebral artery stroke., Radiology 2002;222(1):227-36.
• [8] Parraga A. et al.: Non-rigid registration methods assessment of 3D CT images for head-neck radiotherapy, Proceedings of SPIE Medical Imaging, February, 2007.
• [9] Latchaw R. E., Yonas H., Hunter G. J.: Guidelines and recommendations for perfusion imaging in cerebral ischemia: a scientific statement for healthcare professionals by the writing group on perfusion imaging, from the Council on Cardiovascular Radiology of the American Heart Association, Stroke, 2003; 34: 1084-1104.
• [10] Koenig M., Klotz E., Heuser L.: Perfusion CT in acute stroke: characterization of cerebral ischemia using parameter images of cerebral blood flow and their therapeutic relevance. Clinical experiences, Electromedica 1998;66:61-67.
• [11] Sasaki M. et al.: Procedure Guidelines for CT/MR Perfusion Imaging 2006, Joint Committee for the Procedure Guidelines for CT/MR Perfusion Imaging, http://mr-proj2.umin.jp/data/guidelineCtpMrp2006-e.pdf
• [12] Lev M. H. et al.: Utility of Perfusion-Weighted CT Imaging in Acute Middle Cerebral Artery Stroke Treated With Intra-Arterial Thrombolysis: Prediction of Final Infarct Volume and Clinical Outcome, Stroke. 2001;32:2021.
• [13] Tadeusiewicz R., Ogiela M. R.: Medical Image Understanding Technology, Springer Verlag, Berlin-Heidelberg 2004.
• [14] Duvernoy H. M., Bourgouin P., Vannson J. L.: The Human Brain: Surface, Three- dimensional Sectional Anatomy with MRI, and Blood Supply, Springer, 1999.
• [15] Ogiela M. R., Tadeusiewicz R.: Nowe klasy inteligentnych systemów interpretacji danych obrazowych. Systemy UBIAS, PAK-Pomiary, Automatyka, Kontrola, Vol. 56, No 2, 2010; 193-196.