Radiomics: Extracting more information from medical images using advanced feature analysis

Radiomics: Extracting more information from medical images using advanced feature analysis

2012 March ; 48(4): 441–446 | Philippe Lambin, Emmanuel Rios-Velazquez, Ralph Leijenaar, Sara Carvalho, Ruud G.P.M. van Stiphout, Patrick Granton, Catharina M.L. Zegers, Robert Gillies, Ronald Boellard, André Dekker, and Hugo J.W.L. Aerts
The article "Radiomics: Extracting more information from medical images using advanced feature analysis" by Philippe Lambin et al. discusses the potential of radiomics, a high-throughput method for extracting large amounts of quantitative features from medical images, to capture intra-tumoral heterogeneity in solid cancers. The authors highlight the limitations of invasive biopsy-based molecular assays due to the spatial and temporal heterogeneity of solid cancers, which can be better captured by non-invasive imaging techniques. They outline the advancements in medical imaging, including new hardware, imaging agents, standardized protocols, and automated analysis methodologies, which have enabled the field to move towards quantitative imaging. Radiomics is presented as a promising approach to extract additional information from image-based features, with the hypothesis that it can infer proteo-genomic and phenotypic information from radiological images. The article details the workflow of radiomics, from image acquisition and segmentation to feature extraction, selection, and analysis. It also reviews several studies that have linked imaging features with gene expression patterns and clinical outcomes, supporting the radiomics hypothesis. The authors conclude that while radiomics holds great promise, further validation in multi-centric settings and laboratory studies is needed to confirm its effectiveness.The article "Radiomics: Extracting more information from medical images using advanced feature analysis" by Philippe Lambin et al. discusses the potential of radiomics, a high-throughput method for extracting large amounts of quantitative features from medical images, to capture intra-tumoral heterogeneity in solid cancers. The authors highlight the limitations of invasive biopsy-based molecular assays due to the spatial and temporal heterogeneity of solid cancers, which can be better captured by non-invasive imaging techniques. They outline the advancements in medical imaging, including new hardware, imaging agents, standardized protocols, and automated analysis methodologies, which have enabled the field to move towards quantitative imaging. Radiomics is presented as a promising approach to extract additional information from image-based features, with the hypothesis that it can infer proteo-genomic and phenotypic information from radiological images. The article details the workflow of radiomics, from image acquisition and segmentation to feature extraction, selection, and analysis. It also reviews several studies that have linked imaging features with gene expression patterns and clinical outcomes, supporting the radiomics hypothesis. The authors conclude that while radiomics holds great promise, further validation in multi-centric settings and laboratory studies is needed to confirm its effectiveness.
Reach us at info@study.space