Modeling bilateral lymphatic head and neck tumor progression for personalized elective target volume definition

Area of Science:

• Radiation Oncology
• Medical Imaging
• Biostatistics

Background:

• Large irradiated volumes in head and neck cancer radiotherapy increase severe side effects.
• Standard guidelines for elective clinical target volume (CTV-E) may lead to excessive irradiation.

Purpose of the Study:

• To develop a data-driven, patient-specific approach for defining CTV-E.
• To potentially reduce irradiated volumes and associated side effects compared to standard guidelines.

Main Methods:

• A bilateral Bayesian Network (BN) was trained on a large cohort.
• The BN estimates patient-specific risk of nodal involvement using clinical features.
• Individualized CTV-E were generated based on risk thresholds and compared to standard guidelines.

Main Results:

• The BN approach allowed for reductions in irradiated volumes across various patient scenarios.
• Defined CTV-E were associated with a low probability of undetected nodal involvement in excluded lymph node levels.
• Reductions were observed relative to standard clinical protocols for all considered scenarios.

Conclusions:

• A data-driven framework for personalized CTV-E definition was presented.
• This approach encourages discussion on patient-specific elective nodal target volumes.
• Potential for de-escalation of irradiated elective volumes in head and neck cancer treatment.