Region of Interest focused MRI to Synthetic CT Translation using Regression and Classification Multi-task Network

TL;DR

This paper introduces a multi-task neural network with a region of interest focused loss function for generating accurate synthetic CT images from MRI, emphasizing precise bone density prediction for improved clinical and radiation therapy applications.

Contribution

The work presents a novel multi-task network with a specialized loss function that enhances ROI localization and accuracy in sCT generation from MRI, especially for bone density estimation.

Findings

Multi-task network improves bone density prediction accuracy.

ROI focused loss enhances local accuracy in sCT images.

Better dose calculation maps in radiation therapy planning.

Abstract

In this work, we present a method for synthetic CT (sCT) generation from zero-echo-time (ZTE) MRI aimed at structural and quantitative accuracies of the image, with a particular focus on the accurate bone density value prediction. We propose a loss function that favors a spatially sparse region in the image. We harness the ability of a multi-task network to produce correlated outputs as a framework to enable localisation of region of interest (RoI) via classification, emphasize regression of values within RoI and still retain the overall accuracy via global regression. The network is optimized by a composite loss function that combines a dedicated loss from each task. We demonstrate how the multi-task network with RoI focused loss offers an advantage over other configurations of the network to achieve higher accuracy of performance. This is relevant to sCT where failure to accurately estimate high Hounsfield Unit values of bone could lead to impaired accuracy in clinical applications. We compare the dose calculation maps from the proposed sCT and the real CT in a radiation therapy treatment planning setup.