Alis, DenizYergin, MertAlis, CerenTopel, CagdasAsmakutlu, OzanBagcilar, OmerSenli, Yeseren DenizUstundag, AhmetSalt, VefaDogan, Sebahat NacarVelioglu, MuratSelcuk, Hakan HatemKara, BatuhanOksuz, IlkayKizilkilic, OsmanKaraarslan, Ercan2023-02-212023-02-212021-01-0110.1038/s41598-021-91467-xhttps://hdl.handle.net/11443/2635http://dx.doi.org/10.1038/s41598-021-91467-xThere is little evidence on the applicability of deep learning (DL) in the segmentation of acute ischemic lesions on diffusion-weighted imaging (DWI) between magnetic resonance imaging (MRI) scanners of different manufacturers. We retrospectively included DWI data of patients with acute ischemic lesions from six centers. Dataset A (n=2986) and B (n=3951) included data from Siemens and GE MRI scanners, respectively. The datasets were split into the training (80\%), validation (10\%), and internal test (10\%) sets, and six neuroradiologists created ground-truth masks. Models A and B were the proposed neural networks trained on datasets A and B. The models subsequently fine-tuned across the datasets using their validation data. Another radiologist performed the segmentation on the test sets for comparisons. The median Dice scores of models A and B were 0.858 and 0.857 for the internal tests, which were non-inferior to the radiologist's performance, but demonstrated lower performance than the radiologist on the external tests. Fine-tuned models A and B achieved median Dice scores of 0.832 and 0.846, which were non-inferior to the radiologist's performance on the external tests. The present work shows that the inter-vendor operability of deep learning for the segmentation of ischemic lesions on DWI might be enhanced via transfer learningthereby, their clinical applicability and generalizability could be improved.ArticleWOS:000696753700029