Cargando…

Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network

PURPOSE: Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft‐tissue contrast. However, the delineation...

Descripción completa

Detalles Bibliográficos
Autores principales: Zabihollahy, Fatemeh, Viswanathan, Akila N., Schmidt, Ehud J., Lee, Junghoon
Formato: Online Artículo Texto
Lenguaje:English
Publicado: John Wiley and Sons Inc. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9512359/
https://www.ncbi.nlm.nih.gov/pubmed/35894782
http://dx.doi.org/10.1002/acm2.13725
_version_ 1784797833515237376
author Zabihollahy, Fatemeh
Viswanathan, Akila N.
Schmidt, Ehud J.
Lee, Junghoon
author_facet Zabihollahy, Fatemeh
Viswanathan, Akila N.
Schmidt, Ehud J.
Lee, Junghoon
author_sort Zabihollahy, Fatemeh
collection PubMed
description PURPOSE: Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft‐tissue contrast. However, the delineation of CTV is challenging as CTV contains microscopic extensions that are not clearly visible even in MR images, resulting in significant contour variability among radiation oncologists depending on their knowledge and experience. In this study, we propose a fully automated deep learning–based method to segment CTV from MR images. METHODS: Our method begins with the bladder segmentation, from which the CTV position is estimated in the axial view. The superior–inferior CTV span is then detected using an Attention U‐Net. A CTV‐specific region of interest (ROI) is determined, and three‐dimensional (3‐D) blocks are extracted from the ROI volume. Finally, a CTV segmentation map is computed using a 3‐D U‐Net from the extracted 3‐D blocks. RESULTS: We developed and evaluated our method using 213 MRI scans obtained from 125 patients (183 for training, 30 for test). Our method achieved (mean ± SD) Dice similarity coefficient of 0.85 ± 0.03 and the 95th percentile Hausdorff distance of 3.70 ± 0.35 mm on test cases, outperforming other state‐of‐the‐art methods significantly (p‐value < 0.05). Our method also produces an uncertainty map along with the CTV segmentation by employing the Monte Carlo dropout technique to draw physician's attention to the regions with high uncertainty, where careful review and manual correction may be needed. CONCLUSIONS: Experimental results show that the developed method is accurate, fast, and reproducible for contouring CTV from MRI, demonstrating its potential to assist radiation oncologists in alleviating the burden of tedious contouring for RT planning in cervical cancer.
format Online
Article
Text
id pubmed-9512359
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher John Wiley and Sons Inc.
record_format MEDLINE/PubMed
spelling pubmed-95123592022-09-30 Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network Zabihollahy, Fatemeh Viswanathan, Akila N. Schmidt, Ehud J. Lee, Junghoon J Appl Clin Med Phys Radiation Oncology Physics PURPOSE: Contouring clinical target volume (CTV) from medical images is an essential step for radiotherapy (RT) planning. Magnetic resonance imaging (MRI) is used as a standard imaging modality for CTV segmentation in cervical cancer due to its superior soft‐tissue contrast. However, the delineation of CTV is challenging as CTV contains microscopic extensions that are not clearly visible even in MR images, resulting in significant contour variability among radiation oncologists depending on their knowledge and experience. In this study, we propose a fully automated deep learning–based method to segment CTV from MR images. METHODS: Our method begins with the bladder segmentation, from which the CTV position is estimated in the axial view. The superior–inferior CTV span is then detected using an Attention U‐Net. A CTV‐specific region of interest (ROI) is determined, and three‐dimensional (3‐D) blocks are extracted from the ROI volume. Finally, a CTV segmentation map is computed using a 3‐D U‐Net from the extracted 3‐D blocks. RESULTS: We developed and evaluated our method using 213 MRI scans obtained from 125 patients (183 for training, 30 for test). Our method achieved (mean ± SD) Dice similarity coefficient of 0.85 ± 0.03 and the 95th percentile Hausdorff distance of 3.70 ± 0.35 mm on test cases, outperforming other state‐of‐the‐art methods significantly (p‐value < 0.05). Our method also produces an uncertainty map along with the CTV segmentation by employing the Monte Carlo dropout technique to draw physician's attention to the regions with high uncertainty, where careful review and manual correction may be needed. CONCLUSIONS: Experimental results show that the developed method is accurate, fast, and reproducible for contouring CTV from MRI, demonstrating its potential to assist radiation oncologists in alleviating the burden of tedious contouring for RT planning in cervical cancer. John Wiley and Sons Inc. 2022-07-27 /pmc/articles/PMC9512359/ /pubmed/35894782 http://dx.doi.org/10.1002/acm2.13725 Text en © 2022 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, LLC on behalf of The American Association of Physicists in Medicine. https://creativecommons.org/licenses/by/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by/4.0/ (https://creativecommons.org/licenses/by/4.0/) License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.
spellingShingle Radiation Oncology Physics
Zabihollahy, Fatemeh
Viswanathan, Akila N.
Schmidt, Ehud J.
Lee, Junghoon
Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
title Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
title_full Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
title_fullStr Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
title_full_unstemmed Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
title_short Fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
title_sort fully automated segmentation of clinical target volume in cervical cancer from magnetic resonance imaging with convolutional neural network
topic Radiation Oncology Physics
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9512359/
https://www.ncbi.nlm.nih.gov/pubmed/35894782
http://dx.doi.org/10.1002/acm2.13725
work_keys_str_mv AT zabihollahyfatemeh fullyautomatedsegmentationofclinicaltargetvolumeincervicalcancerfrommagneticresonanceimagingwithconvolutionalneuralnetwork
AT viswanathanakilan fullyautomatedsegmentationofclinicaltargetvolumeincervicalcancerfrommagneticresonanceimagingwithconvolutionalneuralnetwork
AT schmidtehudj fullyautomatedsegmentationofclinicaltargetvolumeincervicalcancerfrommagneticresonanceimagingwithconvolutionalneuralnetwork
AT leejunghoon fullyautomatedsegmentationofclinicaltargetvolumeincervicalcancerfrommagneticresonanceimagingwithconvolutionalneuralnetwork