Lisbon, Portugal

Quantitative methods in Radiation Oncology: models, trials and clinical outcomes

Radiation oncology is increasingly evidence based and data driven. This course presents an overview of the most important data analytic techniques covering the range from clinical trials to big data analytics. The focus is on using and understanding quantitative data to improve clinical practice.

The course is aimed at physicians, medical physicists, biologists and radiation therapists (RTTs), including PhD students in all these fields.

Course Director

  • Søren M. Bentzen, Biostatistician & Radiation Biologist, University of Maryland School of Medicine, Maryland (USA)

 

Teachers

  • Ane Appelt, Medical Physicist, University of Leeds, Leeds (UK)
  • Marleen de Bruijne, Computer Scientist, Erasmus Medical Center, Rotterdam (NL)
  • Clifton D. Fuller, Radiation Oncologist, MD Anderson Cancer Center, Houston, TX (USA)
  • Johannes Langendijk, Radiation Oncologist, University Medical Centre Groningen, Groningen (NL)
  • Ivan R. Vogelius, Medical Physicist, University of Copenhagen-Rigshospitalet, Copenhagen (DK)

 

 

The aim of this course is to introduce the attendees to a range of quantitative methods that are frequently used in radiation oncology research and, in some cases, clinical decision support tool. Radiation oncology probably has the most solid quantitative foundation among medical specialties. As in other specialties, results of randomized controlled trials form the basis for evidence-based treatment guidelines; but in addition, prognostic and predictive models provide clinical decision support for individualized management of cases.

 

Radiation bioeffect models of Normal Tissue Complication Probability (NTCP) and Tumor Control Probability (TCP) have become much more refined since the publication of the QUANTEC overviews 10 years ago and are increasingly being used in treatment plan comparisons or selecting cases likely to benefit from proton therapy. New generations of such models are emerging with artificial intelligence and machine learning (AI/ML) entering the scene for data aggregation, analysis and modeling.

 

While integration of quantitative estimates of various treatment outcomes is likely to improve patient care, it is also important to understand the limitations of model estimates and to be able to assess the validity or quality of a statistical data analysis or a mathematical model. Uncritical reliance on model results may compromise patient safety or treatment outcome or may take research down the wrong track.

Learning outcomes

By the end of this course participants should be able to:

  • Broadly describe the most commonly used quantitative methods in radiation oncology and radiation biology and the assumptions behind these;
  • Identify appropriate quantitative methods of analysis for a given data set;
  • Recognize the potential of artificial intelligence, deep learning and machine learning in radiation oncology;
  • Critically evaluate modelling results especially with respect to proper validation and estimates of uncertainties.

 

Course content

  • Models and modelling, hypothesis testing and parameter estimation, type I and II uncertainties
  • Clinical trials and evidence-based medicine, Phase 0, I, II, III, and IV trial designs, meta-analysis, clinical endpoints, survival statistics and the Cox Proportional Hazards Model
  • Statistical modelling and exploratory data analysis, external and internal validity of models, bootstrap and Monte Carlo methods, goodness of fit
  • Dose-response models, normal tissue complication probability (NTCP) and tumor control probability (TCP) models, modelling combined modality therapy, patient-level risk factors, the linear-quadratic model and beyond, use of models in treatment planning
  • Artificial Intelligence and Machine Learning applications. Deep learning and Convolutional Neural Networks in image analysis.
  • Big data analytics and Data Science, wide and tall data sets, dimensionality reduction, data mining, over-fitting, training and validation sets, sample splitting.
  • Predictive assays, ROC curves and AUC, sensitivity, specificity, positive and negative predictive value

 

Prerequisites

No specific requirements are needed for attending this course although a broad familiarity with the principles of cancer medicine and radiation oncology is expected.

All lectures and discussion are in English.

 

Teaching methods

The four-day course consists of 27 didactic 45-minute lectures, 4 half-hour interactive discussion sessions, a practical exercise (1.25 h), an interactive data analysis session (1.25 h) and a Meet-the-professor session where you can bring-your-own data analysis project and discuss one-on-one with faculty members (10-minute time slots, 1.25 h total time).

 

Methods of assessment

  • Course evaluation form
  • Self-assessment tools are integrated in some of the discussion sessions.

 

Programme to follow

Learning outcomes

By the end of this course participants should be able to:

  • Broadly describe the most commonly used quantitative methods in radiation oncology and radiation biology and the assumptions behind these;
  • Identify appropriate quantitative methods of analysis for a given data set;
  • Recognize the potential of artificial intelligence, deep learning and machine learning in radiation oncology;
  • Critically evaluate modelling results especially with respect to proper validation and estimates of uncertainties.

 

Course content

  • Models and modelling, hypothesis testing and parameter estimation, type I and II uncertainties
  • Clinical trials and evidence-based medicine, Phase 0, I, II, III, and IV trial designs, meta-analysis, clinical endpoints, survival statistics and the Cox Proportional Hazards Model
  • Statistical modelling and exploratory data analysis, external and internal validity of models, bootstrap and Monte Carlo methods, goodness of fit
  • Dose-response models, normal tissue complication probability (NTCP) and tumor control probability (TCP) models, modelling combined modality therapy, patient-level risk factors, the linear-quadratic model and beyond, use of models in treatment planning
  • Artificial Intelligence and Machine Learning applications. Deep learning and Convolutional Neural Networks in image analysis.
  • Big data analytics and Data Science, wide and tall data sets, dimensionality reduction, data mining, over-fitting, training and validation sets, sample splitting.
  • Predictive assays, ROC curves and AUC, sensitivity, specificity, positive and negative predictive value

 

Prerequisites

No specific requirements are needed for attending this course although a broad familiarity with the principles of cancer medicine and radiation oncology is expected.

All lectures and discussion are in English.

 

Teaching methods

The four-day course consists of 27 didactic 45-minute lectures, 4 half-hour interactive discussion sessions, a practical exercise (1.25 h), an interactive data analysis session (1.25 h) and a Meet-the-professor session where you can bring-your-own data analysis project and discuss one-on-one with faculty members (10-minute time slots, 1.25 h total time).

 

Methods of assessment

  • Course evaluation form
  • Self-assessment tools are integrated in some of the discussion sessions.

 

To follow

Membership

ESTRO members can order products at substantially reduced prices. Please note that in order to benefit from the member price, you must renew your membership for 2022 before registering to the course.To benefit from these member rates, please visit the membership page to become a member or renew your membership BEFORE proceeding with your order.

Fees

 

Early rate

Late rate

In-training members*

  450 EUR

 625 EUR

Members

  600 EUR 

 725 EUR

Non Members

  750 EUR

 850 EUR

* Members with specialty RadiationTherapist (RTT) may register at the In Training fee

Early rates are applied up to three months before the starting date of the course.

Late rates are applied three months before the starting date of the course.

The fee includes the course material, coffees, lunches, and the social event.

Advance registration & payment are required.

Since the number of participants is limited, late registrants are advised to contact the ESTRO office before payment, to inquire about availability of places. Access to homework and/or course material will become available upon receipt of full payment.

Insurance and cancellation

The organiser does not accept liability for individual medical, travel or personal insurance. Participants are strongly advised to take out their own personal insurance policies.   

In case an unforeseen event would force ESTRO to cancel the meeting, the Society will reimburse the participants fully the registration fees. ESTRO will not be responsible for the refund of travel and accommodation costs.

In case of cancellation, full refund of the registration fee minus 15% for administrative costs may be obtained up to three months before the course and 50% of the fee up to one month before the course. No refund will be made if the cancellation request is postmarked less than one month before the start of the course.

Reduced fees

Members from emerging countries may register at a preferential rate of 350 Euro. Emerging country fee applies to individuals from low-income and lower-middle-income economies according to the World Bank listing here.

Additionally, all specialties from the following countries can benefit from this preferential rate: Albania, Belarus, Bosnia and Herzegovina, Bulgaria, Croatia, Czech Republic, Estonia, Greece, Hungary, Latvia, Lithuania, Macedonia, Moldova, Montenegro, Poland, Portugal, Romania, Russian Federation, Serbia, Slovak Republic, Slovenia, Spain, Turkey, Ukraine.  In addition, medical physicists from Cyprus can email education@estro.org to apply for this fee.

The preferential rate of 350 Euro is granted automatically when you click on the  BOOK NOW  button and the three conditions below are met:

  1. Only ESTRO members for 2022 are eligible (please make sure your 2022 membership is in order before you click on the BOOK NOW  button)
  2. Only one course per person per year can be subsidized by ESTRO
  3. Sponsored candidates are not entitled to reduced fees (the invoicing address has to be the one of the participant)  

 Please note:

  • We can only guarantee a certain number of reduced fees per course
  • Application deadlines are the same as early registration fees (3 months before the course date).