DEVELOPMENT OF DETECTION MODEL FOR EMPHYSEMA PATTERNS IN COMPUTED TOMOGRAPHY IMAGES
Afrischolar Discovery · 30.07.2024
DOI: 10.60787/jnamp.v67i2.366 ↗Kurz gefasst
Fachartikel in der Zeitschrift Afrischolar Discovery, erschienen am 30.07.2024. Verfasst von Musibau A. Ibrahim und 2 weiteren Autor:innen.
Abstract (Originalsprache)
Fractal dimension is a very useful metric for measuring the statistical self-similarity features of biomedical images. Its applications include shape classification, texture segmentation, and medical picture analysis. The most often used technique for determining the fractal dimension of digital images is the box-counting method. Using this crucial characteristic to categorize patterns in high resolution computed tomography images (HRCT) is also highly tough and demanding. In order to identify emphysema patterns in HRCT images, this study computed the Holder exponent of the local intensity values. A good statistical analysis of emphysema patterns depends on the absolute differences between the normal and pathological regions in the images. The outcomes of this study showed how well the features taken from the Holder exponent could predict outcomes when it comes to the interpretation and classification of HRCT scans. The overall classification accuracy in lung tissue layers is more than 90%, demonstrating the effectiveness of the techniques examined in this work.
Schlagwörter
Zitieren
APA
Ibrahim, M. A., Ojo, O. A., & Oluwafisoye, P. A. (2024). DEVELOPMENT OF DETECTION MODEL FOR EMPHYSEMA PATTERNS IN COMPUTED TOMOGRAPHY IMAGES. Afrischolar Discovery. https://doi.org/10.60787/jnamp.v67i2.366
Vancouver
Ibrahim MA, Ojo OA, Oluwafisoye PA. DEVELOPMENT OF DETECTION MODEL FOR EMPHYSEMA PATTERNS IN COMPUTED TOMOGRAPHY IMAGES. Afrischolar Discovery. 2024. doi:10.60787/jnamp.v67i2.366
BibTeX
@article{Ibrahim2024,
author = {Ibrahim, Musibau A. and Ojo, Oladotun Ayotunde and Oluwafisoye, Peter A.},
title = {DEVELOPMENT OF DETECTION MODEL FOR EMPHYSEMA PATTERNS IN COMPUTED TOMOGRAPHY IMAGES},
journal = {Afrischolar Discovery},
year = {2024},
doi = {10.60787/jnamp.v67i2.366}
}
EUVIMED