Development and clinical application of radiomics in lung cancer

Chen et al. Radiation Oncology (2017) 12:154 DOI 10.1186/s13014-017-0885-x REVIEW Open Access Development and clinical application of radiomics in lung cancer Bojiang Chen, Rui Zhang, Yuncui Gan, Lan Yang and Weimin Li* Abstract Since the discovery of X-rays at the end of the 19th century, medical imageology has progressed for 100 years, and medical imaging has become an important auxiliary tool for clinical diagnosis. With the launch of the human genome project (HGP) and the development of various high-throughput detection techniques, disease exploration in the post-genome era has extended beyond investigations of structural changes to in-depth analyses of molecular abnormalities in tissues, organs and cells, on the basis of gene expression and epigenetics. These techniques have given rise to genomics, proteomics, metabolomics and other systems biology subspecialties, including radiogenomics. Radiogenomics is an important revolution in the traditional visually identifiable imaging technology and constitutes a new branch, radiomics. Radiomics is aimed at extracting quantitative imaging features automatically and developing models to predict lesion phenotypes in a non-invasive manner. Here, we summarize the advent and development of radiomics, the basic process and challenges in clinical practice, with a focus on applications in pulmonary nodule evaluations, including diagnostics, pathological and molecular classifications, treatment response assessments and prognostic predictions, especially in radiotherapy. Keywords: Radiomics, Pulmonary nodule, Lung cancer, Phenotype Introduction The suffix “-omics” is now widely used in basic and clinical medical fields to denote the concept of detecting a large dataset and extracting valuable information. It is well known that tumors arise from genetic abnormalities [1]. Treatment responses vary among patients, even those with the same kind of tumor, because of the different patterns of genetic alterations [2, 3]. In 2003, at the annual conference of the European Society for Radiotherapy and Oncology (ESTRO), Baumann et al. proposed the GENEPI project, with the aim of conducting a quantitative study of the relationship between tumor gene expression and radiosensitivity [4]. This project was considered to give rise to the original concept of radiogenomics. The initial definition of radiogenomics was confined to predicting the sensitivity of radiotherapy on the basis of gene expression. Inspired by this vision, many researchers began to analyze the correlation between the gene expression profile and the lesion image, thus expanding the meaning of radiogenomics [5, 6]. * Correspondence: Department of Respiratory and Critical Care Medicine, West China Hospital of Sichuan University, No. 37, Guo Xue Xiang, Chengdu, Sichuan 610041, China In 2012, the sequencing results of renal carcinoma were reported. Researchers found that the tumor gene sequences and their expression levels significantly differed among diverse renal cancer patients and even within the subregions of individual tumor samples. Moreover, phylogenetic reconstruction has revealed branched evolutionary tumor growth, wherein nearly 70% of all somatic mutations are undetectable across the tumor regions [7]. These studies opened the door for explorations of the spatiotemporal heterogeneity of tumors, at both the microscopic and macroscopic levels. Heterogeneity was then confirmed by a subsequent series of studies [8–10]. It has also been observed that tumors with greater genomic heterogeneity are less sensitive to treatment and more likely to metastasize [11–13]. Therefore, heterogeneity evaluations are important for tumor management. However, the value of the traditional small biopsy, even surgical biopsy, is limited, because despite complete resection of tumor tissues with surgery, pathological examinations usually focus on a fraction of the tumor, and the results might not comprehensively reflect the characteristics of the entire tumor. However, spatiotemporal heterogeneity provides a great opportunity for the development of medical imaging © The Author(s). 2017 Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated. Chen et al. Radiation Oncology (2017) 12:154 technology, which is non-invasive and can be used for continuous and repeated examinations of the entire lesion. The advent and development of radiomics Traditional imaging approaches, such as X-ray radiography, computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography (PET), allow extractions of the two-dimensional anatomical and morphological features of tumors semi-quantitatively. However, these methods are incapable of predicting tumor heterogeneity. Thus, there is a pressing need to develop more systematic and comprehensive image technologies. In fact, in addition to displaying conventional morphological signs distinctly, CT and MRI provide a variety of digital pathophysiological details, such as genetic variations and cell functions, thus facilitating individualized selection of therapies. In 2012, a Dutch researcher, Lambin P, proposed the concept of “Radiomics” for the first time and defined it as follows: The extraction of a large number of image features from radiation images with a high-throughput approach [14]. Radiomics has attracted a large amount of attention, and the definition was updated in 2014 to the highthroughput automated (or semi-automated) extraction of large amounts of quantifiable information (or image features) from a region of interest (ROI) in radiographic images. Radiomics was designed to decode the intrinsic heterogeneity, genetic characteristics and other phenotypes of a lesion to improve management [15]. Clearly, radiomics is a product of digital imaging combined with several types of advanced techniques. Radiologists, medical experts, mathematicians and computer scientists are all necessary in this interdisciplinary framework. Key technologies and challenges in radiomics According to the Quantitative Imaging Network (QIN) guidelines established by the National Cancer Institute (NCI), the key technologies and implementation steps of radiomics include the acquisition and reconstruction of standardized images, lesion segmentation, feature extraction, and quantitative data analyses [16]. Acquisition and reconstruction of standardized images Original images of radiomics can be derived from anatomical or molecular imaging (...truncated)