Difference between revisions of "Publications/buatois.20.seminar"
From LRDE
(Created page with "{{CSIReport | authors = Thibault Buatois | title = Smart and robust segmentation of medical images using neural networks | year = 2020 | number = 2017 | abstract = Gliomas are...") |
|||
| Line 4: | Line 4: | ||
| year = 2020 |
| year = 2020 |
||
| number = 2017 |
| number = 2017 |
||
| − | | abstract = Gliomas are a category of brain tumors that have different degrees of malignancy, shapes and textures. Manual segmentation by experts is a challenging task because of the heterogeneity of these tumors. Several methods of automated gliomas segmentation have been studied at MICCAI 2019 BraTS Challenge. We want to improve the segmentation results submitted last year by LRDE's team, using a 2-step VGG architecture. This convolutional neural |
+ | | abstract = Gliomas are a category of brain tumors that have different degrees of malignancy, shapes and textures. Manual segmentation by experts is a challenging task because of the heterogeneity of these tumors. Several methods of automated gliomas segmentation have been studied at MICCAI 2019 BraTS Challenge. We want to improve the segmentation results submitted last year by LRDE's team, using a 2-step VGG architecture. This convolutional neural networkclassically used for natural image categorization, has been adapted for medical image segmentation through transfert learning and pseudo-3D techniques. Improvements are done through robustness assessment, study of image features, and new method. |
| type = techreport |
| type = techreport |
||
| id = buatois.20.seminar |
| id = buatois.20.seminar |
||
Latest revision as of 18:22, 9 November 2020
- Authors
- Thibault Buatois
- Type
- techreport
- Year
- 2020
- Number
- 2017
Abstract
Gliomas are a category of brain tumors that have different degrees of malignancy, shapes and textures. Manual segmentation by experts is a challenging task because of the heterogeneity of these tumors. Several methods of automated gliomas segmentation have been studied at MICCAI 2019 BraTS Challenge. We want to improve the segmentation results submitted last year by LRDE's team, using a 2-step VGG architecture. This convolutional neural networkclassically used for natural image categorization, has been adapted for medical image segmentation through transfert learning and pseudo-3D techniques. Improvements are done through robustness assessment, study of image features, and new method.