Harvard Medical School - Dana-Farber Cancer Institute

Radiomics

One of the main research areas of our research group is Radiomics. Over the past decade, the use and role of medical imaging technologies in clinical practice has greatly expanded from primarily a diagnostic tool to include a more central role in the context of individualized medicine. ”Radiomics” extends traditional imaging consultation to deeper analysis of these medical images from different imaging modalities (e.g. CT, PET, or MRI), and refers to the extraction and analysis of large numbers of advanced quantitative imaging features with high throughput. Converting these images into useful data, will have an impact on personalized medicine, where treatment can be tailored towards patient specific needs. One of our main areas of interest is therefore connecting tumor specific Radiomic features with their underlying biology, for example by including pathology, gene-expression or mutation data.

Animation that provides a high-level overview of Radiomics

Radiomics research can be divided into distinct processes: (a) image acquisition and reconstruction, (b) image segmentation and rendering, (c) feature extraction and feature qualification and (d) bioinformatics analyses. As each of these individual processes poses unique challenges, we are active with research activities in each of these. For example, optimum protocols for image acquisition and reconstruction have to be identified and harmonized. Also, automatic segmentations algorithms are developed and validated to be robust and involve minimal operator input. Radiomics features have to be generated that robustly reflect the complexity of the individual volumes, but cannot be overly complex or redundant. Furthermore, informatics databases that allow incorporation of image features and image annotations, along with medical and genetic data, have to be generated. Finally, the biostatistical approaches to analyze these data have to be optimized.

For more information, please look at the following publications:

Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Cavalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D, Hoebers F, Rietbergen MM, Leemans CR, Dekker A, Quackenbush J, Gillies RJ, Lambin P
In collaboration with Maastro Clinic the CIBL published a large Radiomics study in Nature Communications. With this publication two large datasets were shared (see Data page for more information).
Volumetric CT-based segmentation of NSCLC using 3D-Slicer
Velazquez ER, Parmar C, Jermoumi M, Mak RH, van Baardwijk A, Fennessy FM, Lewis JH, De Ruysscher D, Kikinis R, Lambin P, Aerts HJ
In this study we assessed the clinical relevance of a semiautomatic computed tomography (CT)-based segmentation method using the competitive region-growing based algorithm, implemented in the free and public available 3D-Slicer software platform.
Radiomics: extracting more information from medical images using advanced feature analysis.
Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, Zegers CM, Gillies R, Boellard R, Dekker A, Aerts HJ
In this review we introduced the field of radiomics by describing the methodology and the clinical need.
Back to Top