Inter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study
| Autor: | Omer Bagcilar, Sebahat Nacar Dogan, Yeseren Deniz Senli, Deniz Alis, Ilkay Oksuz, Osman Kizilkilic, Ahmet Ustundag, Murat Velioglu, Ozan Asmakutlu, Ercan Karaarslan, Mert Yergin, Cagdas Topel, Hakan Hatem Selcuk, Vefa Salt, Ceren Alis, Batuhan Kara |
|---|---|
| Přispěvatelé: | Acibadem University Dspace |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Male
medicine.medical_specialty Science education Datasets as Topic Brain imaging Article 030218 nuclear medicine & medical imaging 03 medical and health sciences Deep Learning Magnetic resonance imaging 0302 clinical medicine Segmentation Neuroimaging Image Interpretation Computer-Assisted Radiologists medicine Humans Generalizability theory Stroke Aged Ischemic Stroke Retrospective Studies Aged 80 and over Multidisciplinary Artificial neural network medicine.diagnostic_test business.industry Deep learning Brain Middle Aged medicine.disease Computer science Diffusion Magnetic Resonance Imaging Medicine Female Artificial intelligence Radiology business Software 030217 neurology & neurosurgery Diffusion MRI |
| Zdroj: | Scientific Reports, Vol 11, Iss 1, Pp 1-10 (2021) Scientific Reports |
| Popis: | There 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; thereby, their clinical applicability and generalizability could be improved. TUBITAKTurkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK) [118C353] Ilkay Oksuz has been benefiting from the 2232 International Fellowship for Outstanding Researchers Program of TUBITAK (Project No: 118C353). However, the entire responsibility of the publication/paper belongs to the owner of the paper. The financial support received from TUBITAK does not mean that the content of the publication is approved in a scientific sense by TUBITAK. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|