Insights into radiomics: impact of feature selection and classification

• DOI: 10.1007/s11042-024-20388-4
• Publication Date: 2024-11-15T06:45:54Z
• Authors: Alessandra Pernic...; Andrea Loddo; Cecilia Di Ruberto; Barbara Pes
• Keywords: Feature (linguistics)

Radiomics is an innovative discipline in medical imaging that uses advanced quantitative feature extraction from radiological images to provide a non-invasive method of interpreting the intricate biological panorama diseases. This takes advantage unique characteristics imaging, where radiation or ultrasound combines with tissues, reveal disease features and important biomarkers are invisible human eye. plays crucial role healthcare, spanning diagnosis, prognosis, recurrences, treatment response assessment, personalized medicine. systematic approach includes image preprocessing, segmentation, extraction, selection, classification, evaluation. survey attempts shed light on roles selection classification play discovering forecasting directions despite challenges posed by high dimensionality (i.e., when data contains huge number features). By analyzing 47 relevant research articles, this study has provided several insights into key techniques used across different stages radiology workflow. The findings indicate 27 articles utilized SVM classifier, while 23 surveyed studies LASSO approach. demonstrates how these particular methodologies have been widely research. assessment did, however, also point out areas require more research, such as evaluating stability algorithms adopting novel approaches like ensemble hybrid methods. Additionally, we examine some emerging subfields within field radiomics.