| 1. |
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Coimbra, M, et al.
(author)
-
Segmentation for classification of gastroenterology images
- 2010
-
In: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference. - 2375-7477. ; 2010, s. 4744-7
-
Journal article (peer-reviewed)
|
|
| 10. |
|
|
| 11. |
|
|
| 12. |
|
|
| 13. |
|
|
| 14. |
|
|
| 15. |
|
|
| 16. |
|
|
| 17. |
- Pereira, JP, et al.
(author)
-
When needles are not enough, forceps delivers!
- 2022
-
In: Revista espanola de enfermedades digestivas : organo oficial de la Sociedad Espanola de Patologia Digestiva. - 1130-0108. ; 114:11, s. 671-673
-
Journal article (peer-reviewed)
|
|
| 18. |
- Pereira, JP, et al.
(author)
-
When needles are not enough, forceps delivers!
- 2022
-
In: Revista espanola de enfermedades digestivas. - : Sociedad Espanola de Patologia Digestiva (SEPD). - 1130-0108. ; 114:11, s. 671-673
-
Journal article (peer-reviewed)
|
|
| 19. |
|
|
| 20. |
|
|
| 21. |
- van der Putten, J, et al.
(author)
-
Endoscopy-Driven Pretraining for Classification of Dysplasia in Barrett's Esophagus with Endoscopic Narrow-Band Imaging Zoom Videos
- 2020
-
In: APPLIED SCIENCES-BASEL. - : MDPI AG. - 2076-3417. ; 10:10
-
Journal article (other academic/artistic)abstract
- Endoscopic diagnosis of early neoplasia in Barrett’s Esophagus is generally a two-step process of primary detection in overview, followed by detailed inspection of any visible abnormalities using Narrow Band Imaging (NBI). However, endoscopists struggle with evaluating NBI-zoom imagery of subtle abnormalities. In this work, we propose the first results of a deep learning system for the characterization of NBI-zoom imagery of Barrett’s Esophagus with an accuracy, sensitivity, and specificity of 83.6%, 83.1%, and 84.0%, respectively. We also show that endoscopy-driven pretraining outperforms two models, one without pretraining as well as a model with ImageNet initialization. The final model outperforms absence of pretraining by approximately 10% and the performance is 2% higher in terms of accuracy compared to ImageNet pretraining. Furthermore, the practical deployment of our model is not hampered by ImageNet licensing, thereby paving the way for clinical application.
|
|
| 22. |
|
|
| 23. |
|
|
| 24. |
|
|
| 25. |
|
|
