Published January 1, 2021
| Version v1
Journal article
Open
Inter-vendor performance of deep learning in segmenting acute ischemic lesions on diffusion-weighted imaging: a multicenter study
Creators
- 1. Acibadem Mehmet Ali Aydinlar Univ, Dept Radiol, Sch Med, Istanbul, Turkey
- 2. Bahcesehir Univ, Dept Software Engn & Appl Sci, Istanbul, Turkey
- 3. Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Neurol Dept, Istanbul, Turkey
- 4. Istanbul Mehmet Akif Ersoy Thorac & Cardiovasc Su, Dept Radiol, Halkali Istanbul, Turkey
- 5. Istanbul Silivri State Hosp, Radiol Dept, Istanbul, Turkey
- 6. Istanbul Univ Cerrahpasa, Cerrahpasa Med Fac, Radiol Dept, Istanbul, Turkey
- 7. Istanbul Gaziosmanpasa Training & Res Hosp, Radiol Dept, Istanbul, Turkey
- 8. Istanbul Fatih Sultan Mehmet Training & Res Hosp, Radiol Dept, Istanbul, Turkey
- 9. Istanbul Bakirkoy Sadi Konuk Training & Res Hosp, Radiol Dept, Istanbul, Turkey
- 10. Istanbul Tech Univ, Dept Software Engn & Appl Sci, Istanbul, Turkey
Description
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.
Files
bib-8326fc8e-93bb-4f53-af51-4a1e138bb756.txt
Files
(362 Bytes)
| Name | Size | Download all |
|---|---|---|
|
md5:7c272da89c28a153cdc5790e988cb97e
|
362 Bytes | Preview Download |