AI Article Synopsis

  • - Understanding the three-dimensional structure of organs is critical in endoscopic surgery for safety, especially for organs that deform significantly.
  • - Preoperative CT scans help with structure analysis, but deformation estimation is crucial for accurate organ representation during surgery, which relies on analyzing two-dimensional images.
  • - The paper presents a U-net based region segmentation method for lung tissues and enhances accuracy for smoker lungs using a CycleGAN to translate lung surface textures.

Article Abstract

In endoscopic surgery, it is necessary to understand the three-dimensional structure of the target region to improve safety. For organs that do not deform much during surgery, preoperative computed tomography (CT) images can be used to understand their three-dimensional structure, however, deformation estimation is necessary for organs that deform substantially. Even though the intraoperative deformation estimation of organs has been widely studied, two-dimensional organ region segmentations from camera images are necessary to perform this estimation. In this paper, we propose a region segmentation method using U-net for the lung, which is an organ that deforms substantially during surgery. Because the accuracy of the results for smoker lungs is lower than that for non-smoker lungs, we improved the accuracy by translating the texture of the lung surface using a CycleGAN.

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC44109.2020.9176214DOI Listing

Publication Analysis

Top Keywords

region segmentation
8
understand three-dimensional
8
three-dimensional structure
8
organs deform
8
deformation estimation
8
estimation organs
8
deep learning
4
learning based
4
based lung
4
region
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!