Multiorgan segmentation using distance-aware adversarial networks

Roger Trullo; Caroline Petitjean; Bernard Dubray; Su Ruan

doi:10.1117/1.JMI.6.1.014001

Translator Disclaimer

10 January 2019 Multiorgan segmentation using distance-aware adversarial networks

Roger Trullo, Caroline Petitjean, Bernard Dubray, Su Ruan

Author Affiliations +

J. of Medical Imaging, 6(1), 014001 (2019). https://doi.org/10.1117/1.JMI.6.1.014001

Abstract

Segmentation of organs at risk (OAR) in computed tomography (CT) is of vital importance in radiotherapy treatment. This task is time consuming and for some organs, it is very challenging due to low-intensity contrast in CT. We propose a framework to perform the automatic segmentation of multiple OAR: esophagus, heart, trachea, and aorta. Different from previous works using deep learning techniques, we make use of global localization information, based on an original distance map that yields not only the localization of each organ, but also the spatial relationship between them. Instead of segmenting directly the organs, we first generate the localization map by minimizing a reconstruction error within an adversarial framework. This map that includes localization information of all organs is then used to guide the segmentation task in a fully convolutional setting. Experimental results show encouraging performance on CT scans of 60 patients totaling 11,084 slices in comparison with other state-of-the-art methods.

Citation Download Citation

Roger Trullo, Caroline Petitjean, Bernard Dubray, and Su Ruan "Multiorgan segmentation using distance-aware adversarial networks," Journal of Medical Imaging 6(1), 014001 (10 January 2019). https://doi.org/10.1117/1.JMI.6.1.014001

Received: 30 June 2018; Accepted: 3 December 2018; Published: 10 January 2019

ACCESS THE FULL ARTICLE