Robust vs. Non-robust radiomic features: the quest for optimal machine learning models using phantom and clinical studies

Robust vs. Non-robust radiomic features: the quest for optimal machine learning models using phantom and clinical studies

Abstract Purpose This study aimed to select robust features against lung motion in a phantom study and use them as input to feature selection algorithms and machine learning classifiers in a clinical study to predict the lymphovascular invasion (LVI) of non-small cell lung cancer (NSCLC). The result...

Full description

Saved in:
Bibliographic Details
Main Authors: Seyyed Ali Hosseini, Ghasem Hajianfar, Brandon Hall, Stijn Servaes, Pedro Rosa-Neto, Pardis Ghafarian, Habib Zaidi, Mohammad Reza Ay
Format: Article
Language:English
Published: BMC 2025-03-01
Series:Cancer Imaging
Subjects:
PET¸ Radiomic features
NSCLC
Lymphovascular invasion
Feature selection
Machine learning
Robustness
Online Access:https://doi.org/10.1186/s40644-025-00857-1
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://doi.org/10.1186/s40644-025-00857-1

Similar Items