Browse by author
Lookup NU author(s): Dr Rachel Pearson, Dr Ross Maxwell, JJ Wyatt, Dr Hazel McCallum
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License (CC BY-ND 4.0).
Copyright © 2023 Czipczer, Kolozsvári, Deák-Karancsi, Capala, Pearson, Borzási, Együd, Gaál, Kelemen, Kószó, Paczona, Végváry, Karancsi, Kékesi, Czunyi, Irmai, Keresnyei, Nagypál, Czabány, Gyalai, Tass, Cziria, Cozzini, Estkowsky, Ferenczi, Frontó, Maxwell, Megyeri, Mian, Tan, Wyatt, Wiesinger, Hideghéty, McCallum, Petit and Ruskó.Introduction: The excellent soft-tissue contrast of magnetic resonance imaging (MRI) is appealing for delineation of organs-at-risk (OARs) as it is required for radiation therapy planning (RTP). In the last decade there has been an increasing interest in using deep-learning (DL) techniques to shorten the labor-intensive manual work and increase reproducibility. This paper focuses on the automatic segmentation of 27 head-and-neck and 10 male pelvis OARs with deep-learning methods based on T2-weighted MR images. Method: The proposed method uses 2D U-Nets for localization and 3D U-Net for segmentation of the various structures. The models were trained using public and private datasets and evaluated on private datasets only. Results and discussion: Evaluation with ground-truth contours demonstrated that the proposed method can accurately segment the majority of OARs and indicated similar or superior performance to state-of-the-art models. Furthermore, the auto-contours were visually rated by clinicians using Likert score and on average, 81% of them was found clinically acceptable.
Author(s): Czipczer V, Kolozsvari B, Deak-Karancsi B, Capala ME, Pearson RA, Borzasi E, Egyud Z, Gaal S, Kelemen G, Koszo R, Paczona V, Vegvary Z, Karancsi Z, Kekesi A, Czunyi E, Irmai BH, Keresnyei NG, Nagypal P, Czabany R, Gyalai B, Tass BP, Cziria B, Cozzini C, Estkowsky L, Ferenczi L, Fronto A, Maxwell R, Megyeri I, Mian M, Tan T, Wyatt J, Wiesinger F, Hideghety K, McCallum H, Petit SF, Rusko L
Publication type: Article
Publication status: Published
Journal: Frontiers in Physics
Year: 2023
Volume: 11
Online publication date: 19/09/2023
Acceptance date: 08/09/2023
Date deposited: 01/11/2023
ISSN (electronic): 2296-424X
Publisher: Frontiers Media SA
URL: https://doi.org/10.3389/fphy.2023.1236792
DOI: 10.3389/fphy.2023.1236792
Data Access Statement: The datasets presented in this article are not readily available because data contracts with clinical partners state that 3rd party access is prohibited.
Altmetrics provided by Altmetric