Intraoperative Organ Motion Models with an Ensemble of Conditional Generative Adversarial Networks

TL;DR

This paper presents a novel deep learning framework using an ensemble of conditional GANs to generate patient-specific prostate motion models from a single preoperative MRI, aiding intraoperative planning.

Contribution

It introduces a method combining multiple generative models and a conditioning network to accurately simulate prostate motion, addressing mode collapse and enhancing patient-specific modeling.

Findings

Generated motion models are physically plausible and patient-specific.

Median errors for generalisability and specificity are 2.8mm and 1.7mm.

The approach demonstrates feasibility of deep learning for organ motion simulation.

Abstract

In this paper, we describe how a patient-specific, ultrasound-probe-induced prostate motion model can be directly generated from a single preoperative MR image. Our motion model allows for sampling from the conditional distribution of dense displacement fields, is encoded by a generative neural network conditioned on a medical image, and accepts random noise as additional input. The generative network is trained by a minimax optimisation with a second discriminative neural network, tasked to distinguish generated samples from training motion data. In this work, we propose that 1) jointly optimising a third conditioning neural network that pre-processes the input image, can effectively extract patient-specific features for conditioning; and 2) combining multiple generative models trained separately with heuristically pre-disjointed training data sets can adequately mitigate the problem of mode collapse. Trained with diagnostic T2-weighted MR images from 143 real patients and 73,216 3D dense displacement fields from finite element simulations of intraoperative prostate motion due to transrectal ultrasound probe pressure, the proposed models produced physically-plausible patient-specific motion of prostate glands. The ability to capture biomechanically simulated motion was evaluated using two errors representing generalisability and specificity of the model. The median values, calculated from a 10-fold cross-validation, were 2.8+/-0.3 mm and 1.7+/-0.1 mm, respectively. We conclude that the introduced approach demonstrates the feasibility of applying state-of-the-art machine learning algorithms to generate organ motion models from patient images, and shows significant promise for future research.