Unsupervised model for structure segmentation applied to brain computed tomography

This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity constraints to generate segmentation maps of the anatomical head structures. Specifically designed for...

Full description

Saved in:
Bibliographic Details
Published in:PloS one 2024-06, Vol.19 (6), p.e0304017
Main Authors: dos Santos, Paulo Victor, Scoczynski Ribeiro Martins, Marcella, Amorim Nogueira, Solange, Gonçalves, Cristhiane, Maffei Loureiro, Rafael, Pacheco Calixto, Wesley
Format: Article
Language:English
Subjects:
Abnormalities
Artificial intelligence
Biology and Life Sciences
Brain
Computational neuroscience
Computed tomography
Computer and Information Sciences
Continuity (mathematics)
CT imaging
Datasets
Feature extraction
Medical imaging
Medicine and Health Sciences
Neural networks
Physical Sciences
Research and Analysis Methods
Segmentation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article presents an unsupervised method for segmenting brain computed tomography scans. The proposed methodology involves image feature extraction and application of similarity and continuity constraints to generate segmentation maps of the anatomical head structures. Specifically designed for real-world datasets, this approach applies a spatial continuity scoring function tailored to the desired number of structures. The primary objective is to assist medical experts in diagnosis by identifying regions with specific abnormalities. Results indicate a simplified and accessible solution, reducing computational effort, training time, and financial costs. Moreover, the method presents potential for expediting the interpretation of abnormal scans, thereby impacting clinical practice. This proposed approach might serve as a practical tool for segmenting brain computed tomography scans, and make a significant contribution to the analysis of medical images in both research and clinical settings.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0304017