Prediction of mandibular ORN incidence from 3D radiation dose distribution maps using deep learning

TL;DR

This study introduces a deep learning approach using 3D DenseNet121 to predict mandibular osteoradionecrosis (ORN) from radiation dose maps, outperforming traditional DVH-based models and potentially improving patient management.

Contribution

The paper presents a novel deep learning model that directly utilizes 3D radiation dose maps for ORN prediction, capturing spatial dose information overlooked by previous models.

Findings

3D DenseNet121 achieved an AUC of 0.71 in ORN prediction.

Compared to RF models, the deep learning approach showed improved discrimination.

Direct use of dose distribution maps enhances NTCP model performance.

Abstract

Background. Absorbed radiation dose to the mandible is an important risk factor in the development of mandibular osteoradionecrosis (ORN) in head and neck cancer (HNC) patients treated with radiotherapy (RT). The prediction of mandibular ORN may not only guide the RT treatment planning optimisation process but also identify which patients would benefit from a closer follow-up post-RT for an early diagnosis and intervention of ORN. Existing mandibular ORN prediction models are based on dose-volume histogram (DVH) metrics that omit the spatial localisation and dose gradient and direction information provided by the clinical mandible radiation dose distribution maps. Methods. We propose the use of a binary classification 3D DenseNet121 to extract the relevant dosimetric information directly from the 3D mandible radiation dose distribution maps and predict the incidence of ORN. We compare the results to a Random Forest ensemble with DVH-based parameters. Results. The 3D DenseNet121 model was able to discriminate ORN vs. non-ORN cases with an average AUC of 0.71 (0.64-0.79), compared to 0.65 (0.57-0.73) for the RF model. Conclusion. Obtaining the dosimetric information directly from the clinical radiation dose distribution maps may enhance the performance and functionality of ORN normal tissue complication probability (NTCP) models.