2D/3D Megavoltage Image Registration Using Convolutional Neural Networks

TL;DR

This paper introduces a CNN-based method for 2D/3D megavoltage image registration, addressing limitations of traditional intensity-based algorithms especially for low-quality MV images, with promising experimental results.

Contribution

The paper proposes a novel CNN approach for 2D/3D MV image registration, improving capture range and accuracy over traditional methods.

Findings

CNN method outperforms traditional registration techniques

Promising results on a dataset of 50 brain images

Addresses low image quality challenges in MV registration

Abstract

We presented a 2D/3D MV image registration method based on a Convolutional Neural Network. Most of the traditional image registration method intensity-based, which use optimization algorithms to maximize the similarity between to images. Although these methods can achieve good results for kilovoltage images, the same does not occur for megavoltage images due to the lower image quality. Also, these methods most of the times do not present a good capture range. To deal with this problem, we propose the use of Convolutional Neural Network. The experiments were performed using a dataset of 50 brain images. The results showed to be promising compared to traditional image registration methods.