Detail publikačního výsledku

From CT Imaging to Clinical Outcomes: Image Feature Selection for Thrombus Radiomic Analysis

NEMČEKOVÁ, P.; CHMELÍK, J.; MARQUERING, H.; JAKUBÍČEK, R.

Originální název

From CT Imaging to Clinical Outcomes: Image Feature Selection for Thrombus Radiomic Analysis

Anglický název

From CT Imaging to Clinical Outcomes: Image Feature Selection for Thrombus Radiomic Analysis

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

The study examines feature selection techniques for identifying key thrombus-related radiomic features from non-contrast CT (NCCT) and CT angiography (CTA) images to differentiate between patients with successful reperfusion and those without after endovascular treatment in acute stroke cases. Using data from 212 patients, 1208 radiomic features were analyzed through a pipeline combining unsupervised and supervised methods, ensuring robustness with 5-fold cross-validation. The study found modality-specific importance in features, noting the relevance of GLCM correlation in CTA, but not NCCT, and identified wavelet-based features as significant across both modalities. The research suggests tailored feature selection to optimize prediction accuracy for different imaging modalities and plans to explore these features' clinical applicability to outcomes like the first-pass effect and their correlation with thrombus histology. The findings aim to enhance the interpretability and reliability of radiomic analyses, contributing to personalized treatment strategies for acute stroke patients.

Anglický abstrakt

The study examines feature selection techniques for identifying key thrombus-related radiomic features from non-contrast CT (NCCT) and CT angiography (CTA) images to differentiate between patients with successful reperfusion and those without after endovascular treatment in acute stroke cases. Using data from 212 patients, 1208 radiomic features were analyzed through a pipeline combining unsupervised and supervised methods, ensuring robustness with 5-fold cross-validation. The study found modality-specific importance in features, noting the relevance of GLCM correlation in CTA, but not NCCT, and identified wavelet-based features as significant across both modalities. The research suggests tailored feature selection to optimize prediction accuracy for different imaging modalities and plans to explore these features' clinical applicability to outcomes like the first-pass effect and their correlation with thrombus histology. The findings aim to enhance the interpretability and reliability of radiomic analyses, contributing to personalized treatment strategies for acute stroke patients.

Klíčová slova

Stroke; Thrombus; Heterogeneity; Computed tomography; Radiomics

Klíčová slova v angličtině

Stroke; Thrombus; Heterogeneity; Computed tomography; Radiomics

Autoři

NEMČEKOVÁ, P.; CHMELÍK, J.; MARQUERING, H.; JAKUBÍČEK, R.

Vydáno

01.04.2026

Nakladatel

Springer

Místo

Cham

ISBN

978-3-032-06530-8

Kniha

CMBEBIH 2025

Periodikum

IFMBE Proceedings

Svazek

133

Číslo

April

Stát

Francouzská republika

Strany od

470

Strany do

479

Strany počet

10

URL

https://link.springer.com/chapter/10.1007/978-3-032-06531-5_42

BibTex

@inproceedings{BUT199659,
  author="Petra {Nemčeková} and Jiří {Chmelík} and Henk {Marquering} and Roman {Jakubíček}",
  title="From CT Imaging to Clinical Outcomes: Image Feature Selection for Thrombus Radiomic Analysis",
  booktitle="CMBEBIH 2025",
  year="2026",
  journal="IFMBE Proceedings",
  volume="133",
  number="April",
  pages="470--479",
  publisher="Springer",
  address="Cham",
  doi="10.1007/978-3-032-06531-5\{_}42",
  isbn="978-3-032-06530-8",
  issn="1680-0737",
  url="https://link.springer.com/chapter/10.1007/978-3-032-06531-5_42"
}