Subscribe to DSC Newsletter

Computational Precision Medicine Challenges- Develop your own algorithm to create peculiar radiomics signature for oropharyngeal cancers (OPC)

For those interested in Radiomics for cancer applications. Our University of Texas MD Anderson Cancer Center radiation oncology team, led by Dr. Clifton D. Fuller, MD, PhD recently launched two public challenges, supported by MICCAI 2016 (http://miccai2016.org/en/). The challenges are a part of the Computational Precision Medicine satellite activities at MICCAI 2016. The details can be found on each challenge Kaggle In Class home-page (https://inclass.kaggle.com/)

The challenges are designed to allow any participant to test his/her radiomics solutions, in order to discriminate etiologic and oncologic features of patients in a segmented, clinically curated anonymized head and neck cancer dataset with contrast CT-scans and standardized radiation oncologist-segmented primary tumor and target volumes. Challenge 1 evaluates competitor's ability to classify HPV+/p16+ status (https://inclass.kaggle.com/c/oropharynx-radiomics-hpv) while Challenge 2 seeks to predict which patients will have a local recurrence in the primary tumor volume (https://inclass.kaggle.com/c/opc-recurrence).

Competitors can submit to the leaderboard until September 18th; at that time, the top 3 teams will be invited to present at the MICCAI meeting. The winning team will also be offered a proffered paper option from the ESTRO sponsored open-access journal Clinical and Translational Radiation Oncology (http://www.ctro.science)

Tags: HPV, Radioms, and, cancer, head, learning, machine, neck, oropharyngeal, recurrence

Views: 303

Attachments:

On Data Science Central

© 2021   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service