TY  - JOUR
AU  - Nachbar, Marcel
AU  - Lo Russo, Monica
AU  - Gani, Cihan
AU  - Boeke, Simon
AU  - Wegener, Daniel
AU  - Paulsen, Frank
AU  - Zips, Daniel
AU  - Roque, Thais
AU  - Paragios, Nikos
AU  - Thorwarth, Daniela
TI  - Automatic AI-based contouring of prostate MRI for online adaptive radiotherapy.
JO  - Zeitschrift für medizinische Physik
VL  - 34
IS  - 2
SN  - 0939-3889
CY  - Amsterdam [u.a.]
PB  - Elsevier
M1  - DKFZ-2023-01087
SP  - 197-207
PY  - 2024
N1  - 2024 May;34(2):197-207
AB  - MR-guided radiotherapy (MRgRT) online plan adaptation accounts for tumor volume changes, interfraction motion and thus allows daily sparing of relevant organs at risk. Due to the high interfraction variability of bladder and rectum, patients with tumors in the pelvic region may strongly benefit from adaptive MRgRT. Currently, fast automatic annotation of anatomical structures is not available within the online MRgRT workflow. Therefore, the aim of this study was to train and validate a fast, accurate deep learning model for automatic MRI segmentation at the MR-Linac for future implementation in a clinical MRgRT workflow.For a total of 47 patients, T2w MRI data were acquired on a 1.5 T MR-Linac (Unity, Elekta) on five different days. Prostate, seminal vesicles, rectum, anal canal, bladder, penile bulb, body and bony structures were manually annotated. These training data consisting of 232 data sets in total was used for the generation of a deep learning based autocontouring model and validated on 20 unseen T2w-MRIs. For quantitative evaluation the validation set was contoured by a radiation oncologist as gold standard contours (GSC) and compared in MATLAB to the automatic contours (AIC). For the evaluation, dice similarity coefficients (DSC), and 95
KW  - Adaptive radiotherapy (Other)
KW  - Automatic annotations (Other)
KW  - Deep learning (Other)
KW  - MR-Linac (Other)
KW  - MR-only (Other)
LB  - PUB:(DE-HGF)16
C6  - pmid:37263911
DO  - DOI:10.1016/j.zemedi.2023.05.001
UR  - https://inrepo02.dkfz.de/record/276390
ER  -