|
|
 |
|
Mercredi 24 Avril
| Heure: |
12:00 - 13:30 |
| Lieu: |
Salle B107, bâtiment B, Université de Villetaneuse |
| Résumé: |
Machine Learning as New Tool for Predicting Radiotherapy Response: Current Challenges and Future directions |
| Description: |
Issam El Naqa More than half all cancer patients receive radiation treatment (radiotherapy) as part of their treatment and it is the main treatment modality at advance stages of disease. Radiotherapy outcomes are determined by complex interactions between treatment dosimetric techniques, cancer pathology, and patientârelated physiological and biological factors. A common obstacle to building maximally predictive treatment outcome models for clinical practice in radiation oncology is the failure to capture this complexity of heterogeneous variable interactions and the ability to translate outcome models across different multiâinstitutional data. Methods based on machine learning can identify data patterns, variable interactions, and higher order relationships among prognostic variables. In addition, they have the ability to generalize to unseen data before. However, within the plethora of machine learning techniques one needs to tailor these methods to radiotherapy outcomes. Off-shelf techniques may not be sufficient to address the current questions faithfully. In this presentation, we will provide examples of the application of machine learning to radiotherapy from our own work and highlight the current challenges, stir discussion between the radiation oncology and the machine learning communities to improve potential application of this promising technology to improve response prediction of radiotherapy outcomes. |
|
|
