Difference between revisions of "Publications/khoudli.18.seminar"
From LRDE
(Created page with "{{CSIReport | authors = Younes Khoudli | title = Automatic Hearth Segmentation | year = 2018 | number = 1807 | abstract = Atrial fibrillation is a common illness, which can be...") |
|||
| Line 1: | Line 1: | ||
{{CSIReport |
{{CSIReport |
||
| authors = Younes Khoudli |
| authors = Younes Khoudli |
||
| − | | title = Automatic |
+ | | title = Automatic Heart Segmentation |
| year = 2018 |
| year = 2018 |
||
| number = 1807 |
| number = 1807 |
||
Latest revision as of 17:47, 6 June 2018
- Authors
- Younes Khoudli
- Type
- techreport
- Year
- 2018
- Number
- 1807
Abstract
Atrial fibrillation is a common illness, which can be detected easily if you can localize the human atria in a MRI image. Manual segmentation is labor intensivetherefore here we adapt an automatic method developped for brain image segmentation. Using transfer learning, we retrain a convolutional neural network used for natural image categorization (VGG), and compare the advantages of using a pseudo-3D technique. We also explore ways to preprocess input data to improve final results.