A deep learning-based automated CT segmentation of prostate cancer anatomy for radiation therapy planning : a retrospective multicenter study |
|
Author: | Kiljunen, Timo1; Akram, Saad2; Niemelä, Jarkko2; |
Organizations: |
1Docrates Cancer Center, Saukonpaadenranta 2, FI-00180 Helsinki, Finland 2MVision Ai, c/o Terkko Health hub, Haartmaninkatu 4, FI-00290 Helsinki, Finland 3Department of Biostatistics, University of Turku, Kiinamyllynkatu 10, FI-20014 Turku, Finland
4Kuopio University Hospital, Center of Oncology, Kelkkailijantie 7, FI-70210 Kuopio, Finland
5Oulu University Hospital, Department of Oncology and Radiotherapy, Kajaanintie 50, FI-90220 Oulu, Finland 6University of Oulu, Research Unit of Medical Imaging, Physics and Technology, Aapistie 5 A, FI-90220 Oulu, Finland 7North Estonia Medical Centre, J. Sütiste tee 19, 13419 Tallinn, Estonia 8National Cancer Centre Singapore, Division of Radiation Oncology, 11 Hospital Crescent, Singapore 169610, Singapore 9Oncology Academic Programme, Duke-NUS Medical School, Singapore 169857, Singapore 10National Cancer Centre Singapore, Division of Medical Sciences, Singapore 169610, Singapore 11Turku University Hospital, Department of Oncology and Radiotherapy, Hämeentie 11, FI-20521 Turku, Finland 12Turku University Hospital, Department of Medical Physics, Hämeentie 11, FI-20521 Turku, Finland |
Format: | article |
Version: | published version |
Access: | open |
Online Access: | PDF Full Text (PDF, 1.4 MB) |
Persistent link: | http://urn.fi/urn:nbn:fi-fe202102154874 |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute,
2020
|
Publish Date: | 2021-02-15 |
Description: |
AbstractA commercial deep learning (DL)-based automated segmentation tool (AST) for computed tomography (CT) is evaluated for accuracy and efficiency gain within prostate cancer patients. Thirty patients from six clinics were reviewed with manual- (MC), automated- (AC) and automated and edited (AEC) contouring methods. In the AEC group, created contours (prostate, seminal vesicles, bladder, rectum, femoral heads and penile bulb) were edited, whereas the MC group included empty datasets for MC. In one clinic, lymph node CTV delineations were evaluated for interobserver variability. Compared to MC, the mean time saved using the AST was 12 min for the whole data set (46%) and 12 min for the lymph node CTV (60%), respectively. The delineation consistency between MC and AEC groups according to the Dice similarity coefficient (DSC) improved from 0.78 to 0.94 for the whole data set and from 0.76 to 0.91 for the lymph nodes. The mean DSCs between MC and AC for all six clinics were 0.82 for prostate, 0.72 for seminal vesicles, 0.93 for bladder, 0.84 for rectum, 0.69 for femoral heads and 0.51 for penile bulb. This study proves that using a general DL-based AST for CT images saves time and improves consistency. see all
|
Series: |
Diagnostics |
ISSN: | 2075-4418 |
ISSN-E: | 2075-4418 |
ISSN-L: | 2075-4418 |
Volume: | 10 |
Issue: | 11 |
Article number: | 959 |
DOI: | 10.3390/diagnostics10110959 |
OADOI: | https://oadoi.org/10.3390/diagnostics10110959 |
Type of Publication: |
A1 Journal article – refereed |
Field of Science: |
3126 Surgery, anesthesiology, intensive care, radiology 3122 Cancers |
Subjects: | |
Copyright information: |
© 2020 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/). |
https://creativecommons.org/licenses/by/4.0/ |