Development and external validation of an MRI-based neural network for brain metastasis segmentation in the AURORA multicenter study. (January 2023)

• Record Type: Journal Article
• Authors: Buchner, Josef A.; Kofler, Florian; Etzel, Lucas; Mayinger, Michael; Christ, Sebastian M.; Brunner, Thomas B.; Wittig, Andrea; Menze, Björn; Zimmer, Claus; Meyer, Bernhard; Guckenberger, Matthias; Andratschke, Nicolaus; El Shafie, Rami A.; Debus, Jürgen; Rogers, Susanne; Riesterer, Oliver; Schulze, Katrin; Feldmann, Horst J.; Blanck, Oliver; Zamboglou, Constantinos; Ferentinos, Konstantinos; Wolff, Robert; Eitz, Kerstin A.; Combs, Stephanie E.; Bernhardt, Denise; Wiestler, Benedikt; Peeken, Jan C.
• Is Part Of: Radiotherapy and oncology. Volume 178(2023)
• Publication Date: 2023-01
• Subjects: Brain metastasis -- Neural network -- Stereotactic radiotherapy -- MRI -- External testing; Oncology -- Periodicals; Radiotherapy -- Periodicals; Tumors -- Periodicals; Medical Oncology -- Periodicals; Neoplasms -- radiotherapy -- Periodicals; Radiotherapy -- Periodicals; Radiothérapie -- Périodiques; Cancérologie -- Périodiques; Tumeurs -- Périodiques; Electronic journals; 616.9940642
• DOI: 10.1016/j.radonc.2022.11.014
• Languages: English
• ISSNs: 0167-8140

Abstract

Highlights: A deep learning model achieved effective segmentation results within a multicenter external testing cohort. Detection of brain metastases was possible with high effectiveness. Segmentation results were stable across medical centers. Brain metastasis volume did not affect segmentation performance. Automatic segmentation can function as a basis for treatment planning or computational analysis. 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.