PuSH - Publication Server of Helmholtz Zentrum München

Export: TXT Text RIS Endnote (RIS) BIB BibTeX
Buchner, J.A.* ; Peeken, J.C. ; Etzel, L.* ; Ezhov, I.* ; Mayinger, M.* ; Christ, S.M.* ; Brunner, T.B.* ; Wittig, A.* ; Menze, B.H.* ; Zimmer, C.* ; Meyer, B.* ; Guckenberger, M.* ; Andratschke, N.* ; El Shafie, R.A.* ; Debus, J.* ; Rogers, S.* ; Riesterer, O.* ; Schulze, K.* ; Feldmann, H.J.* ; Blanck, O.* ; Zamboglou, C.* ; Ferentinos, K.* ; Bilger, A.* ; Grosu, A.L.* ; Wolff, R.* ; Kirschke, J.S.* ; Eitz, K.A. ; Combs, S.E. ; Bernhardt, D.* ; Rueckert, D.* ; Piraud, M. ; Wiestler, B.* ; Kofler, F.

Identifying core MRI sequences for reliable automatic brain metastasis segmentation.

Radiother. Oncol. 188:109901 (2023)
Publ. Version/Full Text DOI PMC
Open Access Hybrid
Creative Commons Lizenzvertrag
Background: Many automatic approaches to brain tumor segmentation employ multiple magnetic resonance imaging (MRI) sequences. The goal of this project was to compare different combinations of input sequences to determine which MRI sequences are needed for effective automated brain metastasis (BM) segmentation. Methods: We analyzed preoperative imaging (T1-weighted sequence ± contrast-enhancement (T1/T1-CE), T2-weighted sequence (T2), and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequence) from 339 patients with BMs from seven centers. A baseline 3D U-Net with all four sequences and six U-Nets with plausible sequence combinations (T1-CE, T1, T2-FLAIR, T1-CE + T2-FLAIR, T1-CE + T1 + T2-FLAIR, T1-CE + T1) were trained on 239 patients from two centers and subsequently tested on an external cohort of 100 patients from five centers. Results: The model based on T1-CE alone achieved the best segmentation performance for BM segmentation with a median Dice similarity coefficient (DSC) of 0.96. Models trained without T1-CE performed worse (T1-only: DSC = 0.70 and T2-FLAIR-only: DSC = 0.73). For edema segmentation, models that included both T1-CE and T2-FLAIR performed best (DSC = 0.93), while the remaining four models without simultaneous inclusion of these both sequences reached a median DSC of 0.81–0.89. Conclusions: A T1-CE-only protocol suffices for the segmentation of BMs. The combination of T1-CE and T2-FLAIR is important for edema segmentation. Missing either T1-CE or T2-FLAIR decreases performance. These findings may improve imaging routines by omitting unnecessary sequences, thus allowing for faster procedures in daily clinical practice while enabling optimal neural network-based target definitions.
Impact Factor
Scopus SNIP
Altmetric
5.700
1.715
Tags
Annotations
Special Publikation
Hide on homepage

Edit extra information
Edit own tags
Private
Edit own annotation
Private
Hide on publication lists
on hompage
Mark as special
publikation
Publication type Article: Journal article
Document type Scientific Article
Keywords Brain Metastases ; Cnn ; Deep Learning ; Mri Sequences ; Segmentation ; U-net
Language english
Publication Year 2023
HGF-reported in Year 2023
ISSN (print) / ISBN 0167-8140
e-ISSN 1879-0887
Journal Radiotherapy and Oncology
Quellenangaben Volume: 188, Issue: , Pages: , Article Number: 109901 Supplement: ,
Publisher Elsevier
Publishing Place Elsevier House, Brookvale Plaza, East Park Shannon, Co, Clare, 00000, Ireland
Reviewing status Peer reviewed
Institute(s) Helmholtz Artifical Intelligence Cooperation Unit (HAICU)
Institute of Radiation Medicine (IRM)
POF-Topic(s) 30205 - Bioengineering and Digital Health
30203 - Molecular Targets and Therapies
Research field(s) Enabling and Novel Technologies
Radiation Sciences
PSP Element(s) G-530001-001
G-501300-001
Grants Deutsche Forschungsgemeinschaft (DFG, German Research foundation)
DOI 10.1016/j.radonc.2023.109901
WOS ID 001081473200001
Scopus ID 85171787912
PubMed ID 37678623
Erfassungsdatum 2023-10-18
[➜Report correction]