Genetic Programming for Feature Learning and Feature Construction in Glioma Survival Prediction

Created by W.Langdon from gp-bibliography.bib Revision:1.8344

@InProceedings{Chen:2024:ICNC-FSKD,

• author = "Kunjun Chen",
• title = "Genetic Programming for Feature Learning and Feature Construction in Glioma Survival Prediction",
• booktitle = "2024 20th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)",
• year = "2024",
• month = jul,
• keywords = "genetic algorithms, genetic programming, Representation learning, Three-dimensional displays, Magnetic resonance imaging, Feature extraction, Prediction algorithms, Classification algorithms, Prognostics and health management, Tumours, glioma, survival prediction, feature learning, feature construction",
• DOI = "doi:10.1109/ICNC-FSKD64080.2024.10702275",
• abstract = "MRI imaging plays a vital role in the initial tumour screening process and also aids in constructing a high-dimensional feature space for survival prediction tasks through the combination of sequences and tumour subregions. Traditional GP methods applied to feature construction treat features as part of the terminal set, which limits their search capabilities. Combining feature learning with GP allows for the direct use of image data, albeit dependent on predefined extraction functions. Our goal is to design a FLFC method that integrates feature learning and construction to automatically locate ROIs, extract features, construct new features, and match classifiers in 3D MRI images. To this end, we have introduced a new GP structure with an interpretable function set. To verify the algorithm, experiments were performed using the publicly available BraTS 2020 dataset. Ours achieved an average accuracy of 94.14percent in the binary classification task (differentiating between HGG and LGG) and 72.49percent in the four-class task (within HGG subtypes). These results underscore the efficacy of the FLFC method in harnessing the complexity of MRI data for meaningful survival prediction, illustrating its potential as a robust tool in medical imaging analysis and cancer prognosis.",
• notes = "Also known as \cite{10702275}",

}

Genetic Programming entries for Kunjun Chen

Citations