Deep learning-based metal artifact reduction using cycle-consistent adversarial network for intensity-modulated head and neck radiation therapy treatment planning

•Deep learning (DL)-based metal artifact reduction (MAR) using unpaired data.•CycleGAN reduced dental implant-induced metal artifacts within a few seconds.•Dose differences in the DL-MAR plan were

Saved in:
Bibliographic Details
Published in:Physica medica 2020-10, Vol.78, p.8-14
Main Authors: Koike, Yuhei, Anetai, Yusuke, Takegawa, Hideki, Ohira, Shingo, Nakamura, Satoaki, Tanigawa, Noboru
Format: Article
Language:English
Subjects:
CycleGAN
Deep learning
Metal artifact reduction
Treatment planning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Deep learning (DL)-based metal artifact reduction (MAR) using unpaired data.•CycleGAN reduced dental implant-induced metal artifacts within a few seconds.•Dose differences in the DL-MAR plan were
ISSN:1120-1797
1724-191X
DOI:10.1016/j.ejmp.2020.08.018