Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification

IntroductionRadiomics-based glioblastoma classification demands feature extraction techniques that can effectively capture tumor heterogeneity while maintaining computational efficiency. Conventional tools such as PyRadiomics and CaPTk rely on extensive handcrafted feature sets, which often result i...

Full description

Saved in:
Bibliographic Details
Main Authors: V. L. Sowmya, A. Bharathi Malakreddy, Santhi Natarajan, N. Prathik, I. S. Rajesh
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Artificial Intelligence
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/frai.2025.1583079/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849423997606821888
author V. L. Sowmya
A. Bharathi Malakreddy
Santhi Natarajan
N. Prathik
I. S. Rajesh
author_facet V. L. Sowmya
A. Bharathi Malakreddy
Santhi Natarajan
N. Prathik
I. S. Rajesh
author_sort V. L. Sowmya
collection DOAJ
description IntroductionRadiomics-based glioblastoma classification demands feature extraction techniques that can effectively capture tumor heterogeneity while maintaining computational efficiency. Conventional tools such as PyRadiomics and CaPTk rely on extensive handcrafted feature sets, which often result in redundancy and necessitate further optimization steps.MethodsThis study proposes a novel framework, Spectral Entropic Radiomics Feature Extraction (SERFE), which integrates spectral frequency decomposition, entropy-driven feature selection, and graph-based spatial encoding. SERFE decomposes voxel intensity fluctuations into spectral signatures, employs entropy-based weighting to prioritize informative features, and preserves spatial topology through graph-based modeling. The method was evaluated using the public TCIA glioblastoma dataset.ResultsSERFE generated a refined feature set of 350 radiomic features from an initial pool of 2,260, achieving a 92% stability score and 91.7% classification accuracy. This performance surpasses traditional radiomics methods in both predictive accuracy and feature compactness.DiscussionThe results demonstrate SERFE’s capacity to enhance tumor characterization and streamline radiomics pipelines without requiring post-extraction feature reduction. Its compatibility with existing clinical workflows makes it a promising tool for future neuro-oncology applications.
format Article
id doaj-art-e2c309602c0c4793985ae4a6e0fd93c6
institution Kabale University
issn 2624-8212
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Artificial Intelligence
spelling doaj-art-e2c309602c0c4793985ae4a6e0fd93c62025-08-20T03:30:23ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122025-07-01810.3389/frai.2025.15830791583079Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classificationV. L. Sowmya0A. Bharathi Malakreddy1Santhi Natarajan2N. Prathik3I. S. Rajesh4Department of Artificial Intelligence & Machine Learning, BMS Institute of Technology & Management, Bangalore, IndiaDepartment of Artificial Intelligence & Machine Learning, BMS Institute of Technology & Management, Bangalore, IndiaDepartment of CSE, Shiv Nadar University, Chennai, IndiaItron Inc., Bangalore, IndiaDepartment of Artificial Intelligence & Machine Learning, BMS Institute of Technology & Management, Bangalore, IndiaIntroductionRadiomics-based glioblastoma classification demands feature extraction techniques that can effectively capture tumor heterogeneity while maintaining computational efficiency. Conventional tools such as PyRadiomics and CaPTk rely on extensive handcrafted feature sets, which often result in redundancy and necessitate further optimization steps.MethodsThis study proposes a novel framework, Spectral Entropic Radiomics Feature Extraction (SERFE), which integrates spectral frequency decomposition, entropy-driven feature selection, and graph-based spatial encoding. SERFE decomposes voxel intensity fluctuations into spectral signatures, employs entropy-based weighting to prioritize informative features, and preserves spatial topology through graph-based modeling. The method was evaluated using the public TCIA glioblastoma dataset.ResultsSERFE generated a refined feature set of 350 radiomic features from an initial pool of 2,260, achieving a 92% stability score and 91.7% classification accuracy. This performance surpasses traditional radiomics methods in both predictive accuracy and feature compactness.DiscussionThe results demonstrate SERFE’s capacity to enhance tumor characterization and streamline radiomics pipelines without requiring post-extraction feature reduction. Its compatibility with existing clinical workflows makes it a promising tool for future neuro-oncology applications.https://www.frontiersin.org/articles/10.3389/frai.2025.1583079/fullspectral radiomicsentropy-weighted feature selectiongraph-theoretic encodingadaptive radiomics modellingglioblastoma classificationTCIA-based radiomics
spellingShingle V. L. Sowmya
A. Bharathi Malakreddy
Santhi Natarajan
N. Prathik
I. S. Rajesh
Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification
Frontiers in Artificial Intelligence
spectral radiomics
entropy-weighted feature selection
graph-theoretic encoding
adaptive radiomics modelling
glioblastoma classification
TCIA-based radiomics
title Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification
title_full Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification
title_fullStr Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification
title_full_unstemmed Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification
title_short Spectral Entropic Radiomics Feature Extraction (SERFE): an adaptive approach for glioblastoma disease classification
title_sort spectral entropic radiomics feature extraction serfe an adaptive approach for glioblastoma disease classification
topic spectral radiomics
entropy-weighted feature selection
graph-theoretic encoding
adaptive radiomics modelling
glioblastoma classification
TCIA-based radiomics
url https://www.frontiersin.org/articles/10.3389/frai.2025.1583079/full
work_keys_str_mv AT vlsowmya spectralentropicradiomicsfeatureextractionserfeanadaptiveapproachforglioblastomadiseaseclassification
AT abharathimalakreddy spectralentropicradiomicsfeatureextractionserfeanadaptiveapproachforglioblastomadiseaseclassification
AT santhinatarajan spectralentropicradiomicsfeatureextractionserfeanadaptiveapproachforglioblastomadiseaseclassification
AT nprathik spectralentropicradiomicsfeatureextractionserfeanadaptiveapproachforglioblastomadiseaseclassification
AT israjesh spectralentropicradiomicsfeatureextractionserfeanadaptiveapproachforglioblastomadiseaseclassification