# Adversarial optimization for joint registration and segmentation in prostate CT radiotherapy

## TL;DR

This paper introduces an adversarial deep learning framework for joint registration and segmentation in prostate CT radiotherapy, enabling real-time contour propagation and improved accuracy over traditional methods.

## Contribution

It presents a novel unsupervised 3D deep learning model that estimates deformation fields for image registration without requiring segmentation labels during testing.

## Key findings

- Outperforms conventional elastix registration in accuracy.
- Reduces computation time significantly, enabling real-time application.
- Effective in propagating contours in prostate CT scans for radiotherapy.

## Abstract

Joint image registration and segmentation has long been an active area of research in medical imaging. Here, we reformulate this problem in a deep learning setting using adversarial learning. We consider the case in which fixed and moving images as well as their segmentations are available for training, while segmentations are not available during testing; a common scenario in radiotherapy. The proposed framework consists of a 3D end-to-end generator network that estimates the deformation vector field (DVF) between fixed and moving images in an unsupervised fashion and applies this DVF to the moving image and its segmentation. A discriminator network is trained to evaluate how well the moving image and segmentation align with the fixed image and segmentation. The proposed network was trained and evaluated on follow-up prostate CT scans for image-guided radiotherapy, where the planning CT contours are propagated to the daily CT images using the estimated DVF. A quantitative comparison with conventional registration using \texttt{elastix} showed that the proposed method improved performance and substantially reduced computation time, thus enabling real-time contour propagation necessary for online-adaptive radiotherapy.