Search: onr:"swepub:oai:DiVA.org:uu-364355" >
Fully convolutional...
-
Langner, TaroUppsala universitet,Radiologi
(author)
Fully convolutional networks for automated segmentation of abdominal adipose tissue depots in multicenter water–fat MRI
- Article/chapterEnglish2019
Publisher, publication year, extent ...
-
2018-10-12
-
Wiley,2019
-
printrdacarrier
Numbers
-
LIBRIS-ID:oai:DiVA.org:uu-364355
-
https://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-364355URI
-
https://doi.org/10.1002/mrm.27550DOI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:ref swepub-contenttype
-
Subject category:art swepub-publicationtype
Notes
-
Purpose: An approach for the automated segmentation of visceral adipose tissue (VAT) and subcutaneous adipose tissue (SAT) in multicenter water–fat MRI scans of the abdomen was investigated, using 2 different neural network architectures.Methods: The 2 fully convolutional network architectures U‐Net and V‐Net were trained, evaluated, and compared using the water–fat MRI data. Data of the study Tellus with 90 scans from a single center was used for a 10‐fold cross‐validation in which the most successful configuration for both networks was determined. These configurations were then tested on 20 scans of the multicenter study beta‐cell function in JUvenile Diabetes and Obesity (BetaJudo), which involved a different study population and scanning device.Results: The U‐Net outperformed the used implementation of the V‐Net in both cross‐validation and testing. In cross‐validation, the U‐Net reached average dice scores of 0.988 (VAT) and 0.992 (SAT). The average of the absolute quantification errors amount to 0.67% (VAT) and 0.39% (SAT). On the multicenter test data, the U‐Net performs only slightly worse, with average dice scores of 0.970 (VAT) and 0.987 (SAT) and quantification errors of 2.80% (VAT) and 1.65% (SAT).Conclusion: The segmentations generated by the U‐Net allow for reliable quantification and could therefore be viable for high‐quality automated measurements of VAT and SAT in large‐scale studies with minimal need for human intervention. The high performance on the multicenter test data furthermore shows the robustness of this approach for data of different patient demographics and imaging centers, as long as a consistent imaging protocol is used.
Subject headings and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Hedström, AndersBioVenture Hub, Antaros Med, Molndal, Sweden
(author)
-
Mörwald, KatharinaParacelsus Med Univ, Dept Pediat, Salzburg, Austria; Paracelsus Med Univ, Obes Res Unit, Salzburg, Austria
(author)
-
Weghuber, DanielParacelsus Med Univ, Dept Pediat, Salzburg, Austria; Paracelsus Med Univ, Obes Res Unit, Salzburg, Austria
(author)
-
Forslund, Anders,1961-Uppsala universitet,Pediatrisk inflammationsforskning(Swepub:uu)andeforsl
(author)
-
Bergsten, PeterUppsala universitet,Institutionen för medicinsk cellbiologi,Pediatrisk inflammationsforskning(Swepub:uu)peteberg
(author)
-
Ahlström, Håkan,1953-Uppsala universitet,Radiologi,BioVenture Hub, Antaros Med, Mölndal, Sweden(Swepub:uu)hakanahl
(author)
-
Kullberg, Joel,1979-Uppsala universitet,Radiologi,BioVenture Hub, Antaros Med, Mölndal, Sweden(Swepub:uu)jokul377
(author)
-
Uppsala universitetRadiologi
(creator_code:org_t)
Related titles
-
In:Magnetic Resonance in Medicine: Wiley81:4, s. 2736-27450740-31941522-2594
Internet link
Find in a library
To the university's database
- By the author/editor
-
Langner, Taro
-
Hedström, Anders
-
Mörwald, Kathari ...
-
Weghuber, Daniel
-
Forslund, Anders ...
-
Bergsten, Peter
-
show more...
-
Ahlström, Håkan, ...
-
Kullberg, Joel, ...
-
show less...
- About the subject
-
- MEDICAL AND HEALTH SCIENCES
-
MEDICAL AND HEAL ...
-
and Clinical Medicin ...
-
and Radiology Nuclea ...
- Articles in the publication
-
Magnetic Resonan ...
- By the university
-
Uppsala University