The work is devoted to describe our automated technique of tumour and neoplasm volume assessment on brain MRI. First we proposed adaptive processing of dynamic local surroundings by estimating of local entropy. Secondly, the investigation of volume assessments directly is ground on the proposition to check extent of interdependency between adjacent slices. The overall approach uses double-criterion principle. The first one estimates cross correlation, the second one is based on Max-dependency principle. Obtained results prove consistency of the implemented approaches.
KEYWORDS: Tissues, Magnetic resonance imaging, 3D modeling, Brain, Data modeling, Error analysis, Statistical analysis, Tumors, 3D metrology, Reconstruction algorithms
The purpose of the paper is to propose a fully automated method of volume assessment of structures within human brain. Our statistical approach uses maximum interdependency principle for decision making process of measurements consistency and unequal observations. Detecting outliers performed using maximum normalized residual test. We propose a statistical model which utilizes knowledge of tissues distribution in human brain and applies partial data restoration for precision improvement. The approach proposes completed computationally efficient and independent from segmentation algorithm used in the application.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.