Head and Neck Cancers Coverage from Every Angle

Potential Applications of Machine Learning and Radiomics in Head and Neck Cancers

By: Joseph Fanelli
Posted: Thursday, May 9, 2019

Machine learning and radiomics may provide better modeling tools for both adverse events and survival in patients with head and neck cancers and may open the possibility for adaptive radiotherapy in this patient population, according to findings presented in Frontiers in Oncology. Radiomics, in particular, is a newer way to mine data from imaging and provide specific information on tumors, heterogeneity, human papillomavirus (HPV) status, lymphocytic infiltration, and thus prognostic signatures, observed Jean-Emmanuel Bibault, MD, PhD, of the Paris Descartes University, and colleagues.

“Radiotherapy treatment planning encompasses time-consuming tasks such as delineation, dosimetric planification, and adaptive radiotherapy,” the authors concluded. “Increasing automation of these tasks is a promising prospective. It may shorten and improve reproducibility of contouring that limits the implementation of adaptive radiation therapy and Normal Tissue Complication Probability (NTCP) modeling.”

In the study, the researchers performed a description of machine learning applications at each step of treatment by radiotherapy in patients with head and neck cancers. Then they focused on a systematic review of radiomics.

The authors found that machine learning has several promising applications in treatment planning with automatic organ at risk delineation improvements and adaptive radiotherapy workflow automation. Additionally, radiomics may provide further data on tumors for improved machine learning–powered predictive models for patient survival, as well as for risk of distant metastasis, in-field recurrence, HPV status, and extranodal disease spread.

However, further validation of these data is needed, the authors acknowledged. “Before we can reach this goal, [machine learning and radiomics] must be thoroughly assessed in prospective, multicentric trials to prove their actual benefit,” Dr. Bibault and colleagues noted. “Collaborating groups will have an important role in the design and conduct of these important studies.”

Disclosure: The study authors reported no conflicts of interest.


By continuing to browse this site you permit us and our partners to place identification cookies on your browser and agree to our use of cookies to identify you for marketing. Read our Privacy Policy to learn more.