Metal Artifact Reduction and Intra Cochlear Anatomy Segmentation in CT Images of the Ear with a Multi-Resolution Multi-Task 3D Network

This video program is a part of the Premium package:

Metal Artifact Reduction and Intra Cochlear Anatomy Segmentation in CT Images of the Ear with a Multi-Resolution Multi-Task 3D Network


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Metal Artifact Reduction and Intra Cochlear Anatomy Segmentation in CT Images of the Ear with a Multi-Resolution Multi-Task 3D Network

0 views
  • Share
Create Account or Sign In to post comments
Segmenting the intra-cochlear anatomy structures (ICAs) in post-implantation CT (Post-CT) images of the cochlear implant (CI) recipients is challenging due to the strong artifacts produced by the metallic CI electrodes. We propose a multi-resolution multi-task deep network which synthesizes an artifact-free image and segments the ICAs in the Post-CT images simultaneously. The output size of the synthesis branch is 1/64 of that of the segmentation branch. This reduces and the memory usage for training, while generating segmentation labels at a high resolution. In this preliminary study, we use the segmentation results of an automatic method as the ground truth to provide supervision to train our model, and we achieve a median Dice index value of 0.792. Our experiments also confirm the usefulness of the multi-task learning.
Segmenting the intra-cochlear anatomy structures (ICAs) in post-implantation CT (Post-CT) images of the cochlear implant (CI) recipients is challenging due to the strong artifacts produced by the metallic CI electrodes. We propose a multi-resolution multi-task deep network which synthesizes an artifact-free image and segments the ICAs in the Post-CT images simultaneously. The output size of the synthesis branch is 1/64 of that of the segmentation branch. This reduces and the memory usage for training, while generating segmentation labels at a high resolution. In this preliminary study, we use the segmentation results of an automatic method as the ground truth to provide supervision to train our model, and we achieve a median Dice index value of 0.792. Our experiments also confirm the usefulness of the multi-task learning.