Inter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study

dc.contributor.authorAlis, Deniz
dc.contributor.authorYergin, Mert
dc.contributor.authorAlis, Ceren
dc.contributor.authorTopel, Cagdas
dc.contributor.authorAsmakutlu, Ozan
dc.contributor.authorBagcilar, Omer
dc.contributor.authorSenli, Yeseren Deniz
dc.contributor.authorUstundag, Ahmet
dc.contributor.authorSalt, Vefa
dc.contributor.authorDogan, Sebahat Nacar
dc.contributor.authorVelioglu, Murat
dc.contributor.authorSelcuk, Hakan Hatem
dc.contributor.authorKara, Batuhan
dc.contributor.authorOksuz, Ilkay
dc.contributor.authorKizilkilic, Osman
dc.contributor.authorKaraarslan, Ercan
dc.date.accessioned2023-02-21T12:40:37Z
dc.date.available2023-02-21T12:40:37Z
dc.date.issued2021-01-01
dc.description.abstractThere 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 learning
dc.description.abstractthereby, their clinical applicability and generalizability could be improved.
dc.description.issue1
dc.description.issueJUN 14
dc.description.volume11
dc.identifier.doi10.1038/s41598-021-91467-x
dc.identifier.urihttps://hdl.handle.net/11443/2635
dc.identifier.urihttp://dx.doi.org/10.1038/s41598-021-91467-x
dc.identifier.wosWOS:000696753700029
dc.publisherNATURE PORTFOLIO
dc.relation.ispartofSCIENTIFIC REPORTS
dc.titleInter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study
dc.typeArticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
10.1038s41598-.pdf
Size:
1.58 MB
Format:
Adobe Portable Document Format

Collections