How Can Radiomics Improve Clinical Choices?
Over the past decade, we have witnessed a great expansion of the use and the role of medical imaging technologies in clinical oncology from a primarily diagnostic, qualitative tool to include a central role in the context of individualized medicine, with
- PDF / 733,340 Bytes
- 15 Pages / 504.567 x 720 pts Page_size
- 59 Downloads / 217 Views
18
Elisa Meldolesi, Nicola Dinapoli, Roberto Gatta, Andrea Damiani, Vincenzo Valentini, and Alessandra Farchione
18.1 Introduction Over the past decade, we have witnessed a great expansion of the use and the role of medical imaging technologies in clinical oncology from a primarily diagnostic, qualitative tool to include a central role in the context of individualized medicine, with a dominant quantitative value [1]. Many patients and tumours related factors have been discovered, highlighting the existence, inside the tumour, of a large “heterogeneity” that can justify a different behaviour of apparently identical tumours. As a consequence, it became more and more apparent that such heterogeneity could be responsible for identifying different subpopulations that may or may not benefit from a specific treatment, or even may have a worse outcome. The awareness that cancers’ heterogeneity comprehends a wide range of temporal and spatial scales has created, in the past, new challenges. Morphological heterogeneity both intra- and inter-tumours is well known in clinical imaging since a long time [2], and numerous descriptors (e.g. necrotic, spiculated and enhanc-
ing areas) are common in radiology lexicon. During the last years, the main effort of radiology research has been focused on quantifying these imaging variations trying to understand their clinical and biological implications [3, 4]. In the past decade, quantitative measurements were commonly limited to the measurement of tumour size that do not reflect the complexity of tumour morphology or behaviour. In contrast, radiomics is a process that involves the highthroughput extraction of quantitative features with the intent of creating mineable databases from radiological images. When transformed into a quantitative form, radiologic tumour properties can be linked to genetic alterations and to medical outcomes. Recently, the need for quantitative imaging has been clearly recognized by the National Cancer Institute and has resulted in the formation of the Quantitative Imaging Network [5]. One goal of this programme is to identify reproducible quantifiable imaging features of tumours that will permit data mining and explicit examination of links between the imaging findings and the underlying molecular and cellular characteristics of the tumours.
E. Meldolesi • N. Dinapoli • R. Gatta (*) A. Damiani • V. Valentini Department of Radiation Oncology, Università Cattolica Sacro Cuore, Fondazione Policlinico Universitario A.Gemelli, Largo A. Gemelli 8, Rome 00168, Italy e-mail: [email protected]
A. Farchione Department of Diagnostic Imaging, Università Cattolica Sacro Cuore, Fondazione Policlinico Universitario A. Gemelli, Rome, Italy
© Springer-Verlag Berlin Heidelberg 2018 V. Valentini et al. (eds.), Multidisciplinary Management of Rectal Cancer, https://doi.org/10.1007/978-3-319-43217-5_18
135
E. Meldolesi et al.
136
18.2 Image Heterogeneity: A Potential New Tumour Biomarker? To date, even though highly personalized treatments are available, with s
Data Loading...
