D 2020

The Reproducibility Assessment of Black-White Pixels Ratio in Transcranial B-images of Medial Temporal Lobe in Application for Detectable Feature of Alzheimer's Disease

BLAHUTA, Jiří and Tomáš SOUKUP

Basic information

Original name

The Reproducibility Assessment of Black-White Pixels Ratio in Transcranial B-images of Medial Temporal Lobe in Application for Detectable Feature of Alzheimer's Disease

Authors

BLAHUTA, Jiří (203 Czech Republic, belonging to the institution) and Tomáš SOUKUP (203 Czech Republic)

Edition

Bulharsko, Proceedings of the International Conference on Biomedical Innovations and Applications, BIA 2020, p. 53-57, 5 pp. 2020

Publisher

Technical University - Varna

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

21100 2.11 Other engineering and technologies

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

RIV identification code

RIV/26867184:_____/20:N0000036

Organization unit

Moravian Business College Olomouc

ISBN

978-1-7281-7073-2

Keywords in English

Alzheimer's Disease; B-image echogenicity; black-white ratiomedial temporal lobe echogenicity; MTL atrophy

Tags

Změněno: 4/5/2021 13:44, Ing. Michaela Nováková

Abstract

V originále

The aim of this paper is analysis the black-white pixels ratio in medial temporal lobe (MTL) brain structure in digitized transcranial B-images using own developed software BMODE Assist. This ratio could be a corresponding marker with the echogenicity grade. In transcranial sonography, the MTL in B-image is anechogenic structure but increased echogenicity of surrounding cortex is detectable in the case of MTL atrophy which predicts Alzheimer's Disease. Totally of 97 B-images were analyzed. The goal is to verify the reproducibility in two. Firstly, between two observers and to show that the ratio is not significantly different between original image and a magnified segment. In parallel in the case of constant brightness increasing. The ratio should be independent on image resolution and brightness. To select MTL, a 20mm square-shaped Region of Interest is used. The correlation coefficient r =0.69 was achieved between two independent, non-experienced observers. Between two non-experienced observers the error of 27.95 % was achieved and between the measurements from the same observer the error was only 11.2 %. Meanwhile, the variance and the range were computed, both almost equal. These results have been judged by an experienced sonographer. In the future, the ratio could be an usable value to determine the MTL atrophy risk using the ratio value and possibility to create a rule-based expert system as a software tool to evaluate probability of Alzheimer's Disease using transcranial sonography.