Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A deeply supervised convolutional neural network ensemble for multilabel segmentation of pelvic OARs

Lempart, Michael LU ; Nilsson, Martin LU ; Scherman, Jonas ; Nilsson, Mikael LU ; Jamtheim Gustafsson, Christian LU ; Munck Af Rosenschöld, Per LU orcid and Olsson, Lars E LU orcid (2021) European Society Radiation Oncology 2021 In Radiotherapy and Oncology 161(Suppl 1). p.1417-1418
Abstract
Accurate delineation of organs at risk (OAR) is a crucial step in radiation therapy (RT) treatment planning but is a manual and time-consuming process. Deep learning-based methods have shown promising results for medical image segmentation and can be used to accelerate this task. Nevertheless, it is rarely applied to complex structures found in the pelvis region, where manual segmentation can be difficult, costly and is not always feasible. The aim of this study was to train and validate a model, based on a modified U-Net architecture, for automated and improved multilabel segmentation of 10 pelvic OAR structures (total bone marrow, lower pelvis bone marrow, iliac bone marrow, lumosacral bone marrow, bowel cavity, bowel, small bowel,... (More)
Accurate delineation of organs at risk (OAR) is a crucial step in radiation therapy (RT) treatment planning but is a manual and time-consuming process. Deep learning-based methods have shown promising results for medical image segmentation and can be used to accelerate this task. Nevertheless, it is rarely applied to complex structures found in the pelvis region, where manual segmentation can be difficult, costly and is not always feasible. The aim of this study was to train and validate a model, based on a modified U-Net architecture, for automated and improved multilabel segmentation of 10 pelvic OAR structures (total bone marrow, lower pelvis bone marrow, iliac bone marrow, lumosacral bone marrow, bowel cavity, bowel, small bowel, large bowel, rectum, and bladder). (Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Deep Learning, Radiation therapy, Semantic segmentation, Anal cancer
in
Radiotherapy and Oncology
volume
161
issue
Suppl 1
article number
PO-1691
pages
1417 - 1418
publisher
Elsevier
conference name
European Society Radiation Oncology 2021
conference location
Madrid, Spain
conference dates
2021-08-26 - 2021-08-31
ISSN
1879-0887
DOI
10.1016/S0167-8140(21)08142-1
language
English
LU publication?
yes
id
33ec4dae-b7e8-4737-a943-f6b363eae7e8
date added to LUP
2021-10-28 10:06:31
date last changed
2023-07-20 03:08:01
@misc{33ec4dae-b7e8-4737-a943-f6b363eae7e8,
  abstract     = {{Accurate delineation of organs at risk (OAR) is a crucial step in radiation therapy (RT) treatment planning but is a manual and time-consuming process. Deep learning-based methods have shown promising results for medical image segmentation and can be used to accelerate this task. Nevertheless, it is rarely applied to complex structures found in the pelvis region, where manual segmentation can be difficult, costly and is not always feasible.  The aim of this study was to train and validate a model, based on a modified U-Net architecture, for automated and improved multilabel segmentation of 10 pelvic OAR structures (total bone marrow, lower pelvis bone marrow, iliac bone marrow, lumosacral bone marrow, bowel cavity, bowel, small bowel, large bowel, rectum, and bladder).}},
  author       = {{Lempart, Michael and Nilsson, Martin and Scherman, Jonas and Nilsson, Mikael and Jamtheim Gustafsson, Christian and Munck Af Rosenschöld, Per and Olsson, Lars E}},
  issn         = {{1879-0887}},
  keywords     = {{Deep Learning; Radiation therapy; Semantic segmentation; Anal cancer}},
  language     = {{eng}},
  note         = {{Conference Abstract}},
  number       = {{Suppl 1}},
  pages        = {{1417--1418}},
  publisher    = {{Elsevier}},
  series       = {{Radiotherapy and Oncology}},
  title        = {{A deeply supervised convolutional neural network ensemble for multilabel segmentation of pelvic OARs}},
  url          = {{http://dx.doi.org/10.1016/S0167-8140(21)08142-1}},
  doi          = {{10.1016/S0167-8140(21)08142-1}},
  volume       = {{161}},
  year         = {{2021}},
}