Evelyn E.C. de Jong

Radiomics: the bridge between medical imaging and personalized medicine

Radiomics, the high-throughput mining of quantitative image features from standard-of-care medical imaging that enables data to be extracted and applied within clinical-decision support systems to improve diagnostic, prognostic, and predictive accuracy, is gaining importance in cancer research. Radiomic analysis exploits sophisticated image analysis tools and the rapid development and validation of medical imaging data that uses image-based signatures for precision diagnosis and treatment, providing a powerful tool in modern medicine. Herein, we describe the process of radiomics, its pitfalls, challenges, opportunities, and its capacity to improve clinical decision making, emphasizing the utility for patients with cancer. Currently, the field of radiomics lacks standardized evaluation of both the scientific integrity and the clinical relevance of the numerous published radiomics investigations resulting from the rapid growth of this area. Rigorous evaluation criteria and reporting guidelines need to be established in order for radiomics to mature as a discipline. Herein, we provide guidance for investigations to meet this urgent need in the field of radiomics.

Modern clinical research: How rapid learning health care and cohort multiple randomised clinical trials complement traditional evidence based medicine.

ABSTRACT Background. Trials are vital in informing routine clinical care; however, current designs have major deficiencies. An overview of the various challenges that face modern clinical research and the methods that can be exploited to solve these challenges, in the context of personalised cancer treatment in the 21st century is provided. Aim. The purpose of this manuscript, without intending to be comprehensive, is to spark thought whilst presenting and discussing two important and complementary alternatives to traditional evidence-based medicine, specifically rapid learning health care and cohort multiple randomised controlled trial design. Rapid learning health care is an approach that proposes to extract and apply knowledge from routine clinical care data rather than exclusively depending on clinical trial evidence, (please watch the animation: http://youtu.be/ZDJFOxpwqEA). The cohort multiple randomised controlled trial design is a pragmatic method which has been proposed to help overcome the weaknesses of conventional randomised trials, taking advantage of the standardised follow-up approaches more and more used in routine patient care. This approach is particularly useful when the new intervention is a priori attractive for the patient (i.e. proton therapy, patient decision aids or expensive medications), when the outcomes are easily collected, and when there is no need of a placebo arm. Discussion. Truly personalised cancer treatment is the goal in modern radiotherapy. However, personalised cancer treatment is also an immense challenge. The vast variety of both cancer patients and treatment options makes it extremely difficult to determine which decisions are optimal for the individual patient. Nevertheless, rapid learning health care and cohort multiple randomised controlled trial design are two approaches (among others) that can help meet this challenge.

Decision support systems for personalized and participative radiation oncology.

Abstract A paradigm shift from current population based medicine to personalized and participative medicine is underway. This transition is being supported by the development of clinical decision support systems based on prediction models of treatment outcome. In radiation oncology, these models ‘learn’ using advanced and innovative information technologies (ideally in a distributed fashion — please watch the animation: http://youtu.be/ZDJFOxpwqEA) from all available/appropriate medical data (clinical, treatment, imaging, biological/genetic, etc.) to achieve the highest possible accuracy with respect to prediction of tumor response and normal tissue toxicity. In this position paper, we deliver an overview of the factors that are associated with outcome in radiation oncology and discuss the methodology behind the development of accurate prediction models, which is a multi‐faceted process. Subsequent to initial development/validation and clinical introduction, decision support systems should be constantly re‐evaluated (through quality assurance procedures) in different patient datasets in order to refine and re‐optimize the models, ensuring the continuous utility of the models. In the reasonably near future, decision support systems will be fully integrated within the clinic, with data and knowledge being shared in a standardized, dynamic, and potentially global manner enabling truly personalized and participative medicine. Graphical abstract Figure. No caption available.

Influence of gray level discretization on radiomic feature stability for different CT scanners, tube currents and slice thicknesses : a comprehensive phantom study

Abstract Background: Radiomic analyses of CT images provide prognostic information that can potentially be used for personalized treatment. However, heterogeneity of acquisition- and reconstruction protocols influences robustness of radiomic analyses. The aim of this study was to investigate the influence of different CT-scanners, slice thicknesses, exposures and gray-level discretization on radiomic feature values and their stability. Material and methods: A texture phantom with ten different inserts was scanned on nine different CT-scanners with varying tube currents. Scans were reconstructed with 1.5 mm or 3 mm slice thickness. Image pre-processing comprised gray-level discretization in ten different bin widths ranging from 5 to 50 HU and different resampling methods (i.e., linear, cubic and nearest neighbor interpolation to 1 × 1 × 3 mm3 voxels) were investigated. Subsequently, 114 textural radiomic features were extracted from a 2.1 cm3 sphere in the center of each insert. The influence of slice thickness, exposure and bin width on feature values was investigated. Feature stability was assessed by calculating the concordance correlation coefficient (CCC) in a test-retest setting and for different combinations of scanners, tube currents and slice thicknesses. Results: Bin width influenced feature values, but this only had a marginal effect on the total number of stable features (CCC > 0.85) when comparing different scanners, slice thicknesses or exposures. Most radiomic features were affected by slice thickness, but this effect could be reduced by resampling the CT-images before feature extraction. Statistics feature ‘energy’ was the most dependent on slice thickness. No clear correlation between feature values and exposures was observed. Conclusions: CT-scanner, slice thickness and bin width affected radiomic feature values, whereas no effect of exposure was observed. Optimization of gray-level discretization to potentially improve prognostic value can be performed without compromising feature stability. Resampling images prior to feature extraction decreases the variability of radiomic features.

A comparison of the relative biological effectiveness of low energy electronic brachytherapy sources in breast tissue: a Monte Carlo study

Electronic brachytherapy sources use low energy photons to treat the tumor bed during or after breast-conserving surgery. The relative biological effectiveness of two electronic brachytherapy sources was explored to determine if spectral differences due to source design influenced radiation quality and if radiation quality decreased with distance in the breast. The RBE was calculated through the number of DNA double strand breaks (RBEDSB) using the Monte Carlo damage simulator (MCDS) in combination with other Monte Carlo electron/photon spectrum calculations. 50kVp photons from the Intrabeam (Carl Zeiss Surgical) and Axxent (Xoft) through 40-mm spherical applicators were simulated to account for applicator and tissue attenuation in a variety of breast tissue compositions. 40kVp Axxent photons were also simulated. Secondary electrons (known to be responsible for most DNA damage) spectra at different distance were inputted into MCDS to calculate the RBEDSB. All RBEDSB used a cobalt-60 reference. RBEDSB data was combined with corresponding average photon spectrum energy for the Axxent and applied to model-based average photon energy distributions to produce an RBEDSB map of an accelerated partial breast irradiation (APBI) patient. Both Axxent and Intrabeam 50kVp spectra were shown to have a comparable RBEDSB of between 1.4 and 1.6 at all distances in spite of progressive beam hardening. The Axxent 40kVp also demonstrated a similar RBEDSB at distances. Most RBEDSB variability was dependent on the tissue type as was seen in rib (RBEDSB  ≈  1.4), gland (≈1.55), adipose (≈1.59), skin (≈1.52) and lung (≈1.50). RBEDSB variability between both sources was within 2%. A correlation was shown between RBEDSB and average photon energy and used to produce an RBEDSB map of a dose distribution in an APBI patient dataset. Radiation quality is very similar between electronic brachytherapy sources studied. No significant reductions in RBEDSB were observed with increasing distance from the source.

Quality assessment of positron emission tomography scans: recommendations for future multicentre trials

Abstract Background: Standardization protocols and guidelines for positron emission tomography (PET) in multicenter trials are available, despite a large variability in image acquisition and reconstruction parameters exist. In this study, we investigated the compliance of PET scans to the guidelines of the European Association of Nuclear Medicine (EANM). From these results, we provide recommendations for future multicenter studies using PET. Material and methods: Patients included in a multicenter randomized phase II study had repeated PET scans for early response assessment. Relevant acquisition and reconstruction parameters were extracted from the digital imaging and communications in medicine (DICOM) header of the images. The PET image parameters were compared to the guidelines of the EANM for tumor imaging version 1.0 recommended parameters. Results: From the 223 included patients, 167 baseline scans and 118 response scans were available from 15 hospitals. Scans of 19% of the patients had an uptake time that fulfilled the Uniform Protocols for Imaging in Clinical Trials response assessment criteria. The average quality score over all hospitals was 69%. Scans with a non-compliant uptake time had a larger standard deviation of the mean standardized uptake value (SUVmean) of the liver than scans with compliant uptake times. Conclusions: Although a standardization protocol was agreed on, there was a large variability in imaging parameters. For future, multicenter studies including PET imaging a prospective central quality review during patient inclusion is needed to improve compliance with image standardization protocols as defined by EANM.

Tracking tumor biology with radiomics: A systematic review utilizing a radiomics quality score

INTRODUCTION In this review we describe recent developments in the field of radiomics along with current relevant literature linking it to tumor biology. We furthermore explore the methodologic quality of these studies with our in-house radiomics quality scoring (RQS) tool. Finally, we offer our vision on necessary future steps for the development of stable radiomic features and their links to tumor biology. METHODS Two authors (S.S. and H.W.) independently performed a thorough systematic literature search and outcome extraction to identify relevant studies published in MEDLINE/PubMed (National Center for Biotechnology Information, NCBI), EMBASE (Ovid) and Web of Science (WoS). Two authors (S.S, H.W) separately and two authors (J.v.T and E.d.J) concordantly scored the articles for their methodology and analyses according to the previously published radiomics quality score (RQS). RESULTS In summary, a total of 655 records were identified till 25-09-2017 based on the previously specified search terms, from which n = 236 in MEDLINE/PubMed, n = 215 in EMBASE and n = 204 from Web of Science. After determining full article availability and reading the available articles, a total of n = 41 studies were included in the systematic review. The RQS scoring resulted in some discrepancies between the reviewers, e.g. reviewer H.W scored 4 studies ≥50%, reviewer S.S scored 3 studies ≥50% while reviewers J.v.T and E.d.J scored 1 study ≥50%. Up to nine studies were given a quality score of 0%. The majority of studies were scored below 50%. DISCUSSION In this study, we performed a systematic literature search linking radiomics to tumor biology. All but two studies (n = 39) revealed that radiomic features derived from ultrasound, CT, PET and/or MR are significantly associated with one or several specific tumor biologic substrates, from somatic mutation status to tumor histopathologic grading and metabolism. Considerable inter-observer differences were found with regard to RQS scoring, while important questions were raised concerning the interpretability of the outcome of such scores.

Applicability of a prognostic CT-based radiomic signature model trained on stage I-III non-small cell lung cancer in stage IV non-small cell lung cancer

OBJECTIVES Recently it has been shown that radiomic features of computed tomography (CT) have prognostic information in stage I-III non-small cell lung cancer (NSCLC) patients. We aim to validate this prognostic radiomic signature in stage IV adenocarcinoma patients undergoing chemotherapy. MATERIALS AND METHODS Two datasets of chemo-naive stage IV adenocarcinoma patients were investigated, dataset 1: 285 patients with CTs performed in a single center; dataset 2: 223 patients included in a multicenter clinical trial. The main exclusion criteria were EGFR mutation or unknown mutation status and non-delineated primary tumor. Radiomic features were calculated for the primary tumor. The c-index of cox regression was calculated and compared to the signature performance for overall survival (OS). RESULTS In total CT scans from 195 patients were eligible for analysis. Patients having a prognostic index (PI) lower than the signature median (n = 92) had a significantly better OS than patients with a PI higher than the median (n = 103, HR 1.445, 95% CI 1.07-1.95, p = 0.02, c-index 0.576, 95% CI 0.527-0.624). CONCLUSION The radiomic signature, derived from daily practice CT scans, has prognostic value for stage IV NSCLC, however the signature performs less than previously described for stage I-III NSCLC stages. In the future, machine learning techniques can potentially lead to a better prognostic imaging based model for stage IV NSCLC.

What you see is (not) what you get: tools for a non-radiologist to evaluate image quality in lung cancer

Medical images are an integral part of oncological patient records and they are reviewed by many different specialists. Therefore, it is important that besides imaging experts, other clinicians are also aware that the diagnostic value of a scan is influenced by the applied imaging protocol. Based on two clinical lung cancer trials, we experienced that, even within a study protocol, there is a large variability in imaging parameters, which has direct impact on the interpretation of the image. These two trials were: 1) the NTR3628 in which the added value of gadolinium magnetic resonance imaging (Gd-MRI) to dedicated contrast enhanced computed tomography (CE-CT) for detecting asymptomatic brain metastases in stage III non-small cell lung cancer (NSCLC) was investigated and 2) a sub-study of the NVALT 12 trial (NCT01171170) in which repeated 18 F-fludeoxyglucose positron emission tomography (18F-FDG-PET) imaging for early response assessment was investigated. Based on the problems encountered in the two trials, we provide recommendations for non-radiology clinicians, which can be used in daily interpretation of imaging. Variations in image parameters cannot only influence trial results, but sub-optimal imaging can also influence treatment decisions in daily lung cancer care, when a physician is not aware of the scanning details.