Johan van Soest

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.

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.

Development and evaluation of an online three-level proton vs photon decision support prototype for head and neck cancer – Comparison of dose, toxicity and cost-effectiveness

To quantitatively assess the effectiveness of proton therapy for individual patients, we developed a prototype for an online platform for proton decision support (PRODECIS) comparing photon and proton treatments on dose metric, toxicity and cost-effectiveness levels. An evaluation was performed with 23 head and neck cancer datasets.

An umbrella protocol for standardized data collection (SDC) in rectal cancer: A prospective uniform naming and procedure convention to support personalized medicine

Predictive models allow treating physicians to deliver tailored treatment moving from prescription by consensus to prescription by numbers. The main features of an umbrella protocol for standardizing data and procedures to create a consistent dataset useful to obtain a trustful analysis for a Decision Support System for rectal cancer are reported.

Distributed learning: Developing a predictive model based on data from multiple hospitals without data leaving the hospital – A real life proof of concept

PURPOSE One of the major hurdles in enabling personalized medicine is obtaining sufficient patient data to feed into predictive models. Combining data originating from multiple hospitals is difficult because of ethical, legal, political, and administrative barriers associated with data sharing. In order to avoid these issues, a distributed learning approach can be used. Distributed learning is defined as learning from data without the data leaving the hospital. PATIENTS AND METHODS Clinical data from 287 lung cancer patients, treated with curative intent with chemoradiation (CRT) or radiotherapy (RT) alone were collected from and stored in 5 different medical institutes (123 patients at MAASTRO (Netherlands, Dutch), 24 at Jessa (Belgium, Dutch), 34 at Liege (Belgium, Dutch and French), 48 at Aachen (Germany, German) and 58 at Eindhoven (Netherlands, Dutch)). A Bayesian network model is adapted for distributed learning (watch the animation: http://youtu.be/nQpqMIuHyOk). The model predicts dyspnea, which is a common side effect after radiotherapy treatment of lung cancer. RESULTS We show that it is possible to use the distributed learning approach to train a Bayesian network model on patient data originating from multiple hospitals without these data leaving the individual hospital. The AUC of the model is 0.61 (95%CI, 0.51-0.70) on a 5-fold cross-validation and ranges from 0.59 to 0.71 on external validation sets. CONCLUSION Distributed learning can allow the learning of predictive models on data originating from multiple hospitals while avoiding many of the data sharing barriers. Furthermore, the distributed learning approach can be used to extract and employ knowledge from routine patient data from multiple hospitals while being compliant to the various national and European privacy laws.

Infrastructure and distributed learning methodology for privacy-preserving multi-centric rapid learning health care: euroCAT

Graphical abstract

Developing and Validating a Survival Prediction Model for NSCLC Patients Through Distributed Learning Across 3 Countries

Purpose Tools for survival prediction for non-small cell lung cancer (NSCLC) patients treated with chemoradiation or radiation therapy are of limited quality. In this work, we developed a predictive model of survival at 2 years. The model is based on a large volume of historical patient data and serves as a proof of concept to demonstrate the distributed learning approach. Methods and Materials Clinical data from 698 lung cancer patients, treated with curative intent with chemoradiation or radiation therapy alone, were collected and stored at 2 different cancer institutes (559 patients at Maastro clinic (Netherlands) and 139 at Michigan university [United States]). The model was further validated on 196 patients originating from The Christie (United Kingdon). A Bayesian network model was adapted for distributed learning (the animation can be viewed at https://www.youtube.com/watch?v=ZDJFOxpwqEA). Two-year posttreatment survival was chosen as the endpoint. The Maastro clinic cohort data are publicly available at https://www.cancerdata.org/publication/developing-and-validating-survival-prediction-model-nsclc-patients-through-distributed, and the developed models can be found at www.predictcancer.org. Results Variables included in the final model were T and N category, age, performance status, and total tumor dose. The model has an area under the curve (AUC) of 0.66 on the external validation set and an AUC of 0.62 on a 5-fold cross validation. A model based on the T and N category performed with an AUC of 0.47 on the validation set, significantly worse than our model (P<.001). Learning the model in a centralized or distributed fashion yields a minor difference on the probabilities of the conditional probability tables (0.6%); the discriminative performance of the models on the validation set is similar (P=.26). Conclusions Distributed learning from federated databases allows learning of predictive models on data originating from multiple institutions while avoiding many of the data-sharing barriers. We believe that distributed learning is the future of sharing data in health care.

Clinical evaluation of atlas and deep learning based automatic contouring for lung cancer

BACKGROUND AND PURPOSE Contouring of organs at risk (OARs) is an important but time consuming part of radiotherapy treatment planning. The aim of this study was to investigate whether using institutional created software-generated contouring will save time if used as a starting point for manual OAR contouring for lung cancer patients. MATERIAL AND METHODS Twenty CT scans of stage I-III NSCLC patients were used to compare user adjusted contours after an atlas-based and deep learning contour, against manual delineation. The lungs, esophagus, spinal cord, heart and mediastinum were contoured for this study. The time to perform the manual tasks was recorded. RESULTS With a median time of 20 min for manual contouring, the total median time saved was 7.8 min when using atlas-based contouring and 10 min for deep learning contouring. Both atlas based and deep learning adjustment times were significantly lower than manual contouring time for all OARs except for the left lung and esophagus of the atlas based contouring. CONCLUSIONS User adjustment of software generated contours is a viable strategy to reduce contouring time of OARs for lung radiotherapy while conforming to local clinical standards. In addition, deep learning contouring shows promising results compared to existing solutions.

Validation of a rectal cancer outcome prediction model with a cohort of Chinese patients

The risk of local recurrence (LR), distant metastases (DM) and overall survival (OS) of locally advanced rectal cancer after preoperative chemoradiation can be estimated by prediction models and visualized using nomograms, which have been trained and validated in European clinical trial populations. Data of 277 consecutive locally advanced rectal adenocarcinoma patients treated with preoperative chemoradiation and surgery from Shanghai Cancer Center, were retrospectively collected and used for external validation. Concordance index (C-index) and calibration curves were used to assess the performance of the previously developed prediction models in this routine clinical validation population. The C-index for the published prediction models was 0.72 ± 0.079, 0.75 ± 0.043 and 0.72 ± 0.089 in predicting 2-year LR, DM and OS in the Chinese population, respectively. Kaplan-Meier curves indicated good discriminating performance regarding LR, but could not convincingly discriminate a low-risk and medium-risk group for distant control and OS. Calibration curves showed a trend of underestimation of local and distant control, as well as OS in the observed data compared with the estimates predicted by the model. In conclusion, we externally validated three models for predicting 2-year LR, DM and OS of locally advanced rectal cancer patients who underwent preoperative chemoradiation and curative surgery with good discrimination in a single Chinese cohort. However, the model overestimated the local control rate compared to observations in the clinical cohort. Validation in other clinical cohorts and optimization of the prediction model, perhaps by including additional prognostic factors, may enhance model validity and its applicability for personalized treatment of locally advanced rectal cancer.

Distributed Learning to Protect Privacy in Multi-centric Clinical Studies

Research in medicine has to deal with the growing amount of data about patients which are made available by modern technologies. All these data might be used to support statistical studies, and for identifying causal relations. To use these data, which are spread across hospitals, efficient merging techniques as well as policies to deal with this sensitive information are strongly needed. In this paper we introduce and empirically test a distributed learning approach, to train Support Vector Machines (SVM), that allows to overcome problems related to privacy and data being spread around. The introduced technique allows to train algorithms without sharing any patients-related information, ensuring privacy and avoids the development of merging tools. We tested this approach on a large dataset and we described results, in terms of convergence and performance; we also provide considerations about the features of an IT architecture designed to support distributed learning computations.