Abstract
Glioma diagnosis and prognosis prediction remain challenging due to the heterogeneity of these tumors and the limitations of current diagnostic approaches. Traditional methods often rely on subjective visual assessment, which can lead to inconsistent results. In this work, we propose a novel image signature-based radiomics method for precise glioma diagnosis and prognostic stratification.
Our approach introduces a comprehensive radiomics framework that extracts quantitative imaging features from multiple MRI sequences. The method consists of three key components: (1) an image signature extraction module that identifies distinctive imaging patterns, (2) a feature selection mechanism that identifies the most predictive biomarkers, and (3) a prognostic stratification model that provides personalized risk assessment.
We evaluate our method on a large cohort of glioma patients with comprehensive clinical follow-up data. Experimental results demonstrate that our image signature-based approach significantly improves diagnostic accuracy and prognostic prediction compared to traditional methods. The method shows robust performance across different glioma subtypes and provides valuable insights into tumor biology.
The proposed framework represents a significant advancement in glioma characterization, providing more precise diagnosis and personalized prognostic information that could improve patient management and treatment planning.
BibTeX
@article{luo2021novel,
title={A novel image signature-based radiomics method to achieve precise diagnosis and prognostic stratification of gliomas},
author={Luo, Huigao and Zhuang, Qiyuan and Wang, Yuanyuan and Abudumijiti, Aibaidula and Shi, Kuangyu and Rominger, Axel and Chen, Hong and Yang, Zhong and Tran, Vanessa and Wu, Guoqing and others},
journal={Laboratory investigation},
volume={101},
number={4},
pages={450--462},
year={2021},
publisher={Nature Publishing Group},
doi={10.1038/s41374-020-0472-x}
}