Computerized Prediction of Treatment Outcomes and Radiomics Analysis
Imaging has been traditionally used in radiotherapy for the purposes of tumor delineation and treatment planning. Recent evidence suggests that such imaging information could be also used as biomarkers for predicting response and personalized treatment as
- PDF / 849,057 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 66 Downloads / 150 Views
Computerized Prediction of Treatment Outcomes and Radiomics Analysis Issam El Naqa
Abstract Imaging has been traditionally used in radiotherapy for the purposes of tumor delineation and treatment planning. Recent evidence suggests that such imaging information could be also used as biomarkers for predicting response and personalized treatment as part of an emerging field called “radiomics.” In this chapter, we discuss the application of imaging-based approaches to predict radiotherapy outcomes from single and hybrid imaging modalities. We describe the different steps involved in radiomics analysis and present examples from our own experiences. We highlight the current challenges and future potentials for imagebased decision support in radiotherapy. Keywords Radiotherapy • Outcomes prediction • Radiomics
14.1
Introduction
kV X-ray computed tomography (kV-CT) has been historically considered the standard modality for treatment planning in 3D conformal (3DCRT) or intensitymodulated radiotherapy (IMRT) because of its ability to provide electron density information for heterogeneous dose calculations (Khan 2007; Webb 2001). However, additional information from other imaging modalities could be also used to improve treatment monitoring and prognosis in different cancer sites (El Naqa et al. 2009; Kumar et al. 2012; Lambin et al. 2012). Physiological information (tumor metabolism, proliferation, necrosis, hypoxic regions, etc.) can be collected directly from nuclear imaging modalities such as single-photon emission computed tomography (SPECT) and positron emission tomography (PET) or indirectly from magnetic resonance imaging (MRI) (Condeelis and Weissleder 2010; Willmann et al. 2008). The complementary nature of these different imaging modalities has led to efforts toward combining information to achieve better treatment outcomes. For instance, PET/CT has been utilized for staging, planning, and assessment of
I. El Naqa, PhD, DABR (*) Department of Radiation Oncology, Physics Division, University of Michigan, Ann Arbor, MI 48103, USA e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2017 H. Arimura (ed.), Image-Based Computer-Assisted Radiation Therapy, DOI 10.1007/978-981-10-2945-5_14
357
358
I. El Naqa
response to radiation therapy in lung (Verhagen et al. 2004; Bradley et al. 2004a, b; Bradley 2004; Erdi et al. 2000; Mac Manus and Hicks 2003; Mac Manus et al. 2003; MacManus et al. 2003; Pandit et al. 2003; Toloza et al. 2003), gynecological (Mutic et al. 2003; Miller and Grigsby 2002), and colorectal cancers (Ciernik 2004). Similarly, MRI has been applied in tumor delineation and assessing toxicities in head and neck cancer (Newbold et al. 2006; Piet et al. 2008). Most recently, PET/MR has started to make its appearance in the field (Zaidi et al. 2007; Thorwarth et al. 2013). There are accumulating evidences that pretreatment or posttreatment information from anatomical or particularly functional imaging could be used to monitor and predict treatment outcomes in radiotherapy. For instance, c
Data Loading...
