Development and external validation of an MRI-based neural network for brain metastasis segmentation in the AURORA multicenter study

Buchner JA, Kofler F, Etzel L, Mayinger M, Christ SM, Brunner TB, Wittig A, Menze B, Zimmer C, Meyer B, Guckenberger M, Andratschke N, El Shafie RA, Debus J, Rogers S, Riesterer O, Schulze K, Feldmann HJ, Blanck O, Zamboglou C, Ferentinos K, Wolff R, Eitz KA, Combs SE, Bernhardt D, Wiestler B, Peeken JC (2023)

Publication Type: Journal article

Publication year: 2023

Journal

Radiotherapy and Oncology Elsevier

Book Volume: 178

Article Number: 109425

DOI: 10.1016/j.radonc.2022.11.014

Abstract

Background: Stereotactic radiotherapy is a standard treatment option for patients with brain metastases. The planning target volume is based on gross tumor volume (GTV) segmentation. The aim of this work is to develop and validate a neural network for automatic GTV segmentation to accelerate clinical daily routine practice and minimize interobserver variability. Methods: We analyzed MRIs (T1-weighted sequence ± contrast-enhancement, T2-weighted sequence, and FLAIR sequence) from 348 patients with at least one brain metastasis from different cancer primaries treated in six centers. To generate reference segmentations, all GTVs and the FLAIR hyperintense edematous regions were segmented manually. A 3D-U-Net was trained on a cohort of 260 patients from two centers to segment the GTV and the surrounding FLAIR hyperintense region. During training varying degrees of data augmentation were applied. Model validation was performed using an independent international multicenter test cohort (n = 88) including four centers. Results: Our proposed U-Net reached a mean overall Dice similarity coefficient (DSC) of 0.92 ± 0.08 and a mean individual metastasis-wise DSC of 0.89 ± 0.11 in the external test cohort for GTV segmentation. Data augmentation improved the segmentation performance significantly. Detection of brain metastases was effective with a mean F1-Score of 0.93 ± 0.16. The model performance was stable independent of the center (p = 0.3). There was no correlation between metastasis volume and DSC (Pearson correlation coefficient 0.07). Conclusion: Reliable automated segmentation of brain metastases with neural networks is possible and may support radiotherapy planning by providing more objective GTV definitions.

Involved external institutions

Klinikum rechts der Isar DE Germany (DE) University of Zurich / Universität Zürich (UZH) CH Switzerland (CH) Klinikum Fulda DE Germany (DE) Universitätsklinikum Schleswig-Holstein (UKSH) DE Germany (DE) Albert-Ludwigs-Universität Freiburg DE Germany (DE) Universitätsklinikum Magdeburg A.ö.R. DE Germany (DE) Friedrich-Schiller-Universität Jena DE Germany (DE) Technische Universität München (TUM) DE Germany (DE) Universitätsklinikum Heidelberg DE Germany (DE) Kantonsspital Aarau AG CH Switzerland (CH) European University Cyprus (EUC) / Ευρωπαϊκό Πανεπιστήμιο Κύπρου CY Cyprus (CY) Saphir Radiochirurgie Zentrum DE Germany (DE) Deutsches Konsortium für Translationale Krebsforschung (DKTK) DE Germany (DE)

How to cite

APA:

Buchner, J.A., Kofler, F., Etzel, L., Mayinger, M., Christ, S.M., Brunner, T.B.,... Peeken, J.C. (2023). Development and external validation of an MRI-based neural network for brain metastasis segmentation in the AURORA multicenter study. Radiotherapy and Oncology, 178. https://doi.org/10.1016/j.radonc.2022.11.014

MLA:

Buchner, Josef A., et al. "Development and external validation of an MRI-based neural network for brain metastasis segmentation in the AURORA multicenter study." Radiotherapy and Oncology 178 (2023).

BibTeX: Download