98%
921
2 minutes
20
In radiomics, feature selection methods are primarily used to eliminate redundant features and identify relevant ones. Feature projection methods, such as principal component analysis (PCA), are often avoided due to concerns that recombining features may compromise interpretability. However, since most radiomic features lack inherent semantic meaning, prioritizing interpretability over predictive performance may not be justified. This study investigates whether feature projection methods can improve predictive performance compared to feature selection, as measured by the area under the receiver operating characteristic curve (AUC), the area under the precision-recall curve (AUPRC), and the F1, F0.5 and F2 scores. Models were trained on a large collection of 50 binary classification radiomic datasets derived from CT and MRI of various organs and representing different clinical outcomes. Evaluation was performed using nested, stratified 5-fold cross-validation with 10 repeats. Nine feature projection methods, including PCA, Kernel PCA, and Non-Negative Matrix Factorization (NMF), were compared to nine selection methods, such as Minimum Redundancy Maximum Relevance (MRMRe), Extremely Randomized Trees (ET), and LASSO, using four classifiers. The results showed that selection methods, particularly ET, MRMRe, Boruta, and LASSO, achieved the highest overall performance. Importantly, performance varied considerably across datasets, and some projection methods, such as NMF, occasionally outperformed all selection methods on individual datasets, indicating their potential utility. However, the average difference between selection methods and projection methods across all datasets was negligible and statistically insignificant, suggesting that both perform similarly based solely on methodological considerations. These findings support the notion that, in a typical radiomics study, selection methods should remain the primary approach but also emphasize the importance of considering projection methods in order to achieve the highest performance.
Download full-text PDF |
Source |
---|---|
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC12413460 | PMC |
http://dx.doi.org/10.1038/s41598-025-16070-w | DOI Listing |
Neuropsychobiology
September 2025
Introduction: Anxiety has been described in the initial stages of schizophrenia, and affective flattening in the chronic illness. The etiology remains unknown. Ketamine, a noncompetitive N-Methyl-D-amino-aspartate acid (NMDA) receptor antagonist, is used in rats as a translational model of schizophrenia.
View Article and Find Full Text PDFRheumatology (Oxford)
September 2025
Department of Orthopedics, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China.
Objectives: Osteoarthritis (OA) is a leading cause of chronic pain and disability worldwide, traditionally viewed as a disease of aging. However, emerging evidence highlights its increasing prevalence among middle-aged adults (40-59 years), a population critical to socioeconomic stability. This study is designed to assess the burden of OA among middle-aged adults.
View Article and Find Full Text PDFCyberattacks on transmitted signals are the most critical threats to modern microgrid (MG) systems and should be accurately addressed to ensure safe and reliable operation. This article investigates the cybersecurity of dc MGs against FDI attacks and develops a novel model-based observer system. The proposed projection operator (PO)-based UIO is uniquely designed to detect attacks on the transmitted data from other distributed generation units.
View Article and Find Full Text PDFIEEE Trans Neural Netw Learn Syst
September 2025
Temporal modeling plays an important role in the effective adaption of the powerful pretrained text-image foundation model into text-video retrieval. However, existing methods often rely on additional heavy trainable modules, such as transformer or BiLSTM, which are inefficient. In contrast, we avoid introducing such heavy components by leveraging frozen foundation models.
View Article and Find Full Text PDFPsychopharmacology (Berl)
September 2025
División de Neurociencias, Instituto de Fisiología Celular, Universidad Nacional Autónoma de México, Ciudad Universitaria, Mexico City, 04510, Mexico.
Rationale: One of the earliest changes associated with Alzheimer's disease (AD) is the loss of catecholaminergic terminals in the cortex and hippocampus originating from the Locus Coeruleus (LC). This decline leads to reduced catecholaminergic neurotransmitters in the hippocampus, affecting synaptic plasticity and spatial memory. However, it is unclear whether restoring catecholaminergic transmission in the terminals from the LC may alleviate the spatial memory deficits associated with AD.
View Article and Find Full Text PDF