Author: Amine Amyar; Romain Modzelewski; Su Ruan
Title: Multi-task Deep Learning Based CT Imaging Analysis For COVID-19: Classification and Segmentation Document date: 2020_4_21
ID: hiac6ur7_45
Snippet: We have developed a new deep learning multi-task model to jointly detect COVID-19 CT images and segment the regions of infection. We have also evaluated several the state of the art algorithms such as U-NET and CNNs. To obtain our best model, we tested the different combinations of tasks 2 by 2 and all the 3 tasks simultaneously with different images resolutions. Our motivation was to leverage useful information contained in multiple related task.....
Document: We have developed a new deep learning multi-task model to jointly detect COVID-19 CT images and segment the regions of infection. We have also evaluated several the state of the art algorithms such as U-NET and CNNs. To obtain our best model, we tested the different combinations of tasks 2 by 2 and all the 3 tasks simultaneously with different images resolutions. Our motivation was to leverage useful information contained in multiple related tasks to help improve both segmentation and classification performances.
Search related documents:
Co phrase search for related documents- classification segmentation and image resolution: 1, 2
- classification segmentation and multi task model: 1
- classification segmentation performance and image resolution: 1
- classification segmentation performance improve and image resolution: 1
- CT image and deep learn: 1, 2
- CT image and good model: 1, 2
- CT image and image resolution: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11
- CT image and multi task model: 1
- deep learn and image resolution: 1, 2
- deep learn and multi task model: 1
- different image resolution and image resolution: 1
- good model and infection region: 1, 2, 3
- image resolution and infection region: 1
Co phrase search for related documents, hyperlinks ordered by date