A deep learning model for inter-fraction head and neck anatomical changes

TL;DR

This paper introduces a probabilistic deep learning model based on variational autoencoders to predict and simulate inter-fraction anatomical changes in head and neck cancer patients, aiding treatment planning and robustness evaluation.

Contribution

A novel variational autoencoder-based probabilistic model for predicting realistic inter-fraction anatomical changes in head and neck patients.

Findings

Achieved a DICE score of 0.92 on test data.

Generated anatomies closely matching observed clinical changes.

Model captures distribution of anatomical variations effectively.

Abstract

Objective: To assess the performance of a probabilistic deep learning based algorithm for predicting inter-fraction anatomical changes in head and neck patients. Approach: A probabilistic daily anatomy model for head and neck patients $(\mathrm{DAM}_{\mathrm{HN}})$ is built on the variational autoencoder architecture. The model approximates the generative joint conditional probability distribution of the repeat computed tomography (rCT) images and their corresponding masks on the planning CT images (pCT) and their masks. The model outputs deformation vector fields, which are used to produce possible rCTs and associated masks. The dataset is composed of 93 patients (i.e., 367 pCT - rCT pairs), 9 (i.e., 37 pairs) of which were set aside for final testing. The performance of the model is assessed based on the reconstruction accuracy and the generative performance for the set aside patients. Main results: The model achieves a DICE score of 0.92 and an image similarity score of 0.65 on the test set. The generated parotid glands volume change distributions and center of mass shift distributions were also assessed. For both, the medians of the distributions are close to the true ones, and the distributions are broad enough to encompass the real observed changes. Moreover, the generated images display anatomical changes in line with the literature reported ones, such as the medial shifts of the parotids glands. Significance: $(\mathrm{DAM}_{\mathrm{HN}})$ is capable of generating realistic anatomies observed during the course of the treatment and has applications in anatomical robust optimization, treatment planning based on plan library approaches and robustness evaluation against inter-fractional changes.