Stroke prognosis by applying double thresholds on CT-perfusion-brain images

Somchart Chokchaitam; Nittaya Santipromwong; Sombat Muengtaweepongsa

doi:10.1117/12.2011164

14 March 2013 Stroke prognosis by applying double thresholds on CT-perfusion-brain images

Somchart Chokchaitam, Nittaya Santipromwong, Sombat Muengtaweepongsa

Proceedings Volume 8768, International Conference on Graphic and Image Processing (ICGIP 2012); 876845 (2013) https://doi.org/10.1117/12.2011164
Event: 2012 International Conference on Graphic and Image Processing, 2012, Singapore, Singapore

Abstract

The CT-perfusion image shows information of brain abnormalities such as its size and location. Generally, neurologist diagnoses stroke disease using CT-perfusion images such as Cerebral blood flow (CBF), cerebral blood volume (CBV). In our previous report, we applied threshold technique to divide amount of CBV and CBF into low and high level. Then, their levels are applied to identify normal tissue areas, dead tissue areas (infract core) and blood-cot tissue areas (infract penumbra). However, it’s not totally correct, if the same threshold is applied to the whole area (it must depend on size of blood vessel in that area. In this report, we propose double thresholds to divided CBV and CBF into 3 levels: very low, medium and very high levels. Very low and very high levels are definitely implied to bad areas and good areas, respectively. The proposed double thresholds makes stroke prognosis more accurate. The simulation results confirm that our proposed results closed to results defined from neurologist comparing to the conventional results.

Citation Download Citation

Somchart Chokchaitam, Nittaya Santipromwong, and Sombat Muengtaweepongsa "Stroke prognosis by applying double thresholds on CT-perfusion-brain images", Proc. SPIE 8768, International Conference on Graphic and Image Processing (ICGIP 2012), 876845 (14 March 2013); https://doi.org/10.1117/12.2011164

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available