Sowmya V L, Bharathi Malakreddy A, Natarajan Santhi, Prathik N, Rajesh I S
Department of Artificial Intelligence & Machine Learning, BMS Institute of Technology & Management, Bangalore, India.
Department of CSE, Shiv Nadar University, Chennai, India.
Front Artif Intell. 2025 Jul 16;8:1583079. doi: 10.3389/frai.2025.1583079. eCollection 2025.
Radiomics-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.
This 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.
SERFE 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.
The 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.
基于放射组学的胶质母细胞瘤分类需要能够有效捕捉肿瘤异质性同时保持计算效率的特征提取技术。诸如PyRadiomics和CaPTk等传统工具依赖大量手工制作的特征集，这往往会导致冗余，并且需要进一步的优化步骤。
本研究提出了一种新颖的框架，即谱熵放射组学特征提取（SERFE），它整合了谱频率分解、熵驱动的特征选择和基于图的空间编码。SERFE将体素强度波动分解为谱特征，采用基于熵的加权来对信息丰富的特征进行优先级排序，并通过基于图的建模保留空间拓扑结构。使用公开的TCIA胶质母细胞瘤数据集对该方法进行了评估。
SERFE从最初的2260个特征池中生成了一组精简的350个放射组学特征，稳定性得分达到92%，分类准确率达到91.7%。这一性能在预测准确性和特征紧凑性方面均超过了传统的放射组学方法。
结果表明SERFE有能力在无需提取后特征约简的情况下增强肿瘤特征描述并简化放射组学流程。它与现有临床工作流程的兼容性使其成为未来神经肿瘤学应用中一个有前景的工具。
