Ruben T.H.M. Larue

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.

Quantitative radiomics studies for tissue characterization: a review of technology and methodological procedures

Quantitative analysis of tumour characteristics based on medical imaging is an emerging field of research. In recent years, quantitative imaging features derived from CT, positron emission tomography and MR scans were shown to be of added value in the prediction of outcome parameters in oncology, in what is called the radiomics field. However, results might be difficult to compare owing to a lack of standardized methodologies to conduct quantitative image analyses. In this review, we aim to present an overview of the current challenges, technical routines and protocols that are involved in quantitative imaging studies. The first issue that should be overcome is the dependency of several features on the scan acquisition and image reconstruction parameters. Adopting consistent methods in the subsequent target segmentation step is evenly crucial. To further establish robust quantitative image analyses, standardization or at least calibration of imaging features based on different feature extraction settings is required, especially for texture- and filter-based features. Several open-source and commercial software packages to perform feature extraction are currently available, all with slightly different functionalities, which makes benchmarking quite challenging. The number of imaging features calculated is typically larger than the number of patients studied, which emphasizes the importance of proper feature selection and prediction model-building routines to prevent overfitting. Even though many of these challenges still need to be addressed before quantitative imaging can be brought into daily clinical practice, radiomics is expected to be a critical component for the integration of image-derived information to personalize treatment in the future.

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.

Can metformin improve ‘the tomorrow’ of patients treated for oesophageal cancer?

INTRODUCTION Recent studies suggest that the use of metformin is associated with reduced cancer incidence and improved prognosis in patients with oesophageal cancer. We explored the relationship between the use of metformin and outcome (pathologic response rate, distant metastasis-free and overall survival) in our mono-institutional cohort of patients treated for oesophageal cancer. MATERIAL AND METHODS Between 2008 and 2014, a total of 196 patients with oesophageal cancer (ages ranged from 37 to 82 years) eligible for curative treatment entered the study. Patients were categorized as non-diabetic (n = 172), diabetic not taking metformin (n = 5) or diabetic taking metformin (n = 19). The majority of patients were treated with trimodality therapy (n = 189). Pathologic response was graded according to Mandards tumour regression score at the time of surgery. Distant metastasis-free and overall survival were calculated using the Kaplan-Meier method with log rank comparisons performed to determine significance. RESULTS The overall pathologic complete response rate for the study population was 26%. It was 25% for patients not using metformin and 39% for diabetics taking metformin (p = 0.260). The two-year overall survival rate for the whole group was 59%. Use of metformin was associated with a significantly better distant metastasis-free survival rate (p = 0.040) or overall survival rate (p = 0.012). Multivariate analysis using Cox regression found that metformin treatment significantly prolonged survival (p = 0.043). CONCLUSION In our population-based study, the use of metformin was associated with an improved overall and distant metastasis-free survival rate in patients with oesophageal cancer. These data are complementary to one other clinical study and warrant further prospective study.

A qualitative synthesis of the evidence behind elective lymph node irradiation in oesophageal cancer

BACKGROUND AND PURPOSE Oesophageal cancer is the sixth leading cause of cancer death worldwide and radiotherapy plays a prominent role in its treatment. The presence of lymph node (LN) metastasis has been demonstrated to be one of the most significant prognostic factors related to oesophageal cancer. The use of elective lymph node irradiation (ENI) is still a topic of persistent controversy. The conservative school is to irradiate positive lymph nodes only; the other school is to prophylactically irradiate the regional lymph node area according to different tumour sites. This review investigated the justification for including ENI in the treatment of patients with oesophageal cancer. MATERIAL AND METHODS We performed a systematic literature search to find surgical data about lymph node distribution depending on different tumour subgroups: early, cervical, thoracic and gastroesophageal junction cancer. Furthermore, we performed a qualitative assessment of recurrence patterns in patients treated with or without ENI to derive estimates of the potential area at risk for lymph node harvest. RESULTS We identified and reviewed 49 studies: 10 in early, 8 in cervical, 10 in thoracic and the remaining 21 in gastroesophageal junction cancer. In general, these studies were conclusive in incidence and location of pathologic lymph nodes for different subgroups. Data for lymph node recurrence patterns are scarce and contributed little to our review. CONCLUSIONS This review resulted in five recommendations for radiation oncologists in daily practice. We used the available evidence about metastatic lymph node distribution to develop a careful reasonable radiation protocol for the corresponding tumour subgroups.

The influence of gastric filling instructions on dose delivery in patients with oesophageal cancer: A prospective study.

PURPOSE To evaluate whether adaptive radiotherapy for unaccounted stomach changes in patients with adenocarcinoma of the gastroesophageal junction (GEJ) is necessary and whether dose differences could be prevented by giving patients food and fluid instructions before treatment simulation and radiotherapy. MATERIAL AND METHODS Twenty patients were randomly assigned into two groups: patients with and without instructions about restricting food and fluid intake prior to radiotherapy simulation and treatment. Redelineation and offline recalculation of dose distributions based on cone-beam computed tomography (n=100) were performed. Dose-volume parameters were analysed for the clinical target volume extending into the stomach. RESULTS Four patients who did not receive instructions had a geometric miss (0.7-12 cm(3)) in only one fraction. With instructions, 3 out of 10 patients had a geometric miss (0.1-1.9 cm(3)) in one (n=2) or two (n=1) fractions. The V95% was reduced by more than 5% for one patient, but this underdosage was in an in-air region without further clinical importance. CONCLUSIONS Giving patients food and fluid instructions for the treatment of GEJ cancer offers no clinical benefit. Using a planning target volume margin of 1cm implies that there is no need for adaptive radiotherapy for GEJ tumours.

4DCT imaging to assess radiomics feature stability: An investigation for thoracic cancers

BACKGROUND AND PURPOSE Quantitative tissue characteristics derived from medical images, also called radiomics, contain valuable prognostic information in several tumour-sites. The large number of features available increases the risk of overfitting. Typically test-retest CT-scans are used to reduce dimensionality and select robust features. However, these scans are not always available. We propose to use different phases of respiratory-correlated 4D CT-scans (4DCT) as alternative. MATERIALS AND METHODS In test-retest CT-scans of 26 non-small cell lung cancer (NSCLC) patients and 4DCT-scans (8 breathing phases) of 20 NSCLC and 20 oesophageal cancer patients, 1045 radiomics features of the primary tumours were calculated. A concordance correlation coefficient (CCC) >0.85 was used to identify robust features. Correlation with prognostic value was tested using univariate cox regression in 120 oesophageal cancer patients. RESULTS Features based on unfiltered images demonstrated greater robustness than wavelet-filtered features. In total 63/74 (85%) unfiltered features and 268/299 (90%) wavelet features stable in the 4D-lung dataset were also stable in the test-retest dataset. In oesophageal cancer 397/1045 (38%) features were robust, of which 108 features were significantly associated with overall-survival. CONCLUSION 4DCT-scans can be used as alternative to eliminate unstable radiomics features as first step in a feature selection procedure. Feature robustness is tumour-site specific and independent of prognostic value.

Hypoxia and hypoxia response-associated molecular markers in esophageal cancer: A systematic review

PURPOSE In this systematic review, the existing evidence of available hypoxia-associated molecular response biomarkers in esophageal cancer (EC) patients is summarized and set into the context of the role of hypoxia in the prediction of esophageal cancer, treatment response and treatment outcome. METHODS A systematic literature search was performed in Web of Science, MEDLINE, and PubMed databases using the keywords: hypoxia, esophagus, cancer, treatment outcome and treatment response. Eligible publications were independently evaluated by two reviewers. In total, 22 out of 419 records were included for systematic review. The described search strategy was applied weekly, with the last update being performed on April 3rd, 2017. RESULTS In esophageal cancer, several (non-)invasive biomarkers for hypoxia could be identified. Independent prognostic factors for treatment response include HIF-1α, CA IX, GLUT-1 overexpression and elevated uptake of the PET-tracer 18F-fluoroerythronitroimidazole (18F-FETNIM). Hypoxia-associated molecular responses represents a clinically relevant phenomenon in esophageal cancer and detection of elevated levels of hypoxia-associated biomarkers and tends to be associated with poor treatment outcome (i.e., overall survival, disease-free survival, complete response and local control). CONCLUSION Evaluation of tumor micro-environmental conditions, such as intratumoral hypoxia, is important to predict treatment outcome and efficacy. Promising non-invasive imaging-techniques have been suggested to assess tumor hypoxia and hypoxia-associated molecular responses. However, extensive validation in EC is lacking. Hypoxia-associated markers that are independent prognostic factors could potentially provide targets for novel treatment strategies to improve treatment outcome. For personalized hypoxia-guided treatment, safe and reliable makers for tumor hypoxia are needed to select suitable patients.