Segmentation of post-operative glioblastoma

Ragnhild Holden Helland, David Bouget, Alexandros Ferles, Roelant S. Eijgelaar, Ole Solheim, Philip C. De Witt Hamer, Ingerid Reinertsen

Keywords: Post-operative segmentation, Glioblastoma, MRI, Deep Learning

TL;DR: Training of neural networks on a new dataset for segmentation of glioblastoma in early post-operative MRI.

Abstract: Extent Of Resection (EOR) after surgery is one of the main prognostic factors for patients diagnosed with glioblastoma. The current standard method for estimating EOR is subject to high inter- and intra-rater variability, and an automated method for segmentation of residual tumor in early post-operative MRI could lead to a more accurate estimation of EOR. In this study we trained neural networks for segmentation of residual tumor tissue in early post-operative MRI. We introduce a new dataset for this task, consisting of data from 645 patients from 13 hospitals in Europe and the US. The segmentation performance of the best model is similar to that of human expert raters, and the results be used to classify cases of gross total resection and residual tumor with high recall and precision.

Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: novel methodological ideas without extensive validation

Primary Subject Area: Segmentation

Secondary Subject Area: Application: Radiology

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.