This website is designed to inform physicians and provide them with probability scores for a number of outcomes. The models calculate the probability that certain side-effects, treatment outcomes and follow-up outcomes will occur. ptTheragnostic B.V. does not record prediction tool user outcome.

These models should only be used by physicians who are familiar with the complexity of treatment decisions in cancer treatment and should not be used directly by patients. We emphasize that the purpose of these models is to inform physicians and that the models should not be used for decision support. The models available on this website are not regarded as medical devices under the current MEDDEV guidelines from the European Commission.

The calculators which are provided are freeware for personal use only. They are not public domain software and may not be sold or used for commercial purposes. Permission to use and backup this software for any non-commercial purpose, without fee, and without a written agreement is hereby granted. Permission to distribute this software for any non-commercial purpose, without fee, and without a written agreement is hereby granted, provided that a reference to the following website and the entire License and Disclaimer are provided with all distributed copies: http://www.PredictCancer.org

The authors have made every effort to ensure that the information provided by this software is accurate and conforms to the methods described in the publications. However, the probability estimates published in the papers and which are estimated with these calculators may differ from those found in current clinical practice. In addition, a patient's prognosis may depend on other factors than those taken into account here. Thus, any decisions concerning patient care should not be based only on the use of these calculators, but should also take into account the patient's past history and other current patient and tumor characteristics. The model output supplements but does not substitute this individual clinical assessment. The creators of the PredictCancer website are not liable for clinical decision making that occurs between a physician and a patient.

As medical science is constantly changing and human error is always possible, the information contained in the prediction tools may be outdated, incomplete or incorrect. The authors, ptTheragnostic and MAASTRO clinic do not warrant the calculators' accuracy nor are they responsible for any omissions, errors or outcomes resulting from the use of these calculators. In no event shall either the authors, ptTheragnostic or MAASTRO clinic be liable to any party for any direct, indirect, special, incidental, or consequential damages, including lost profits, arising from the use of this software even if they have been advised of the possibility of such damage.

The authors, ptTheragnostic and MAASTRO clinic specifically disclaim any warranties, including but not limited to, the implied warranty of fitness for calculating the probabilities of outcomes for patients. The software provided hereunder is on an as is basis and neither the authors, ptTheragnostic nor the MAASTRO clinic have any obligations to provide maintenance, support, updates, enhancements or modifications.

By proceeding with use of the models, the user agrees that they have read and agreed with these terms.

Thank you for agreeing to participate in this experiment!

We are going to show you two images per screen: One segmented manually by doctors and another one segmented automatically by the software. We would like you to indicate which contour is, according to you, the most accurate.

For example, a contour encompassing some normal tissues around the tumour should be seen as inaccurate, same for a contour missing part of the tumour. It could be that you will find that both contours are not correct. In that case, we would like you to indicate the less bad one. We do not ask you to evaluate the "cosmetic" of the contour. Some contours can look unusual but it doesn't mean that they are not accurate.

If you want to add comments please write it in the dedicated window see Fig1.

What do you need to do?

For the record, we would like to register your **name** and **e-mail** ( in case we want you to redo the test to look at the reproducibility of your evaluation or if we would like to include you as a co-author or put your name in acknowledgments).

Note:
It is OK if you prefer to stay anonymous.
To make further subanalysis we also would like you to specify your training: **Medical Doctor, Radiologist, Radiation Oncologist, Computer Scientist, Student, Other**.

In order to increase contrast of specific tissues during the experiment you can vary image window parameters Window Width (WW) and Window Level (WL) in the window settings see Fig 1.

Figure 1. Experiment window

Click the link to Participate in this experiment

Journal articles that support this prediction tool

"Validated fully automated detection and segmentation of non-small cell lung cancer on computed tomography images"

Sergey P. Primakov, Abdalla Ibrahim, Janita E. van Timmeren, Guangyao Wua, Simon A. Keek, Manon Beuque, R. Granzierf, Madeleine Scrivener, Sebastian Sanduleanu , Esma Kayan , Iva Halilaj , Jianlin Wu , René Monshouwer , Hester A Gietema , Lizza E.L. Hendriks , Olivier Mori , Arthur Jochemsa, Henry . Woodruff, Philippe Lambina