Related Experiment Video
Updated: Dec 11, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.2K
Esophagus segmentation from planning CT images using an atlas-based deep learning approach.
João Otávio Bandeira Diniz1, Jonnison Lima Ferreira2, Pedro Henrique Bandeira Diniz3
1Federal University of Maranho, Brazil; Federal Institute of Maranho, Brazil.
Computer Methods and Programs in Biomedicine
|August 18, 2020
Summary
This study presents a fully automatic method for esophagus segmentation in CT scans, improving radiotherapy planning. The new approach significantly enhances accuracy and efficiency for specialists.
Area of Science:
- Medical Imaging
- Radiotherapy Planning
- Computational Anatomy
Background:
- Accurate segmentation of organs at risk (OARs), such as the esophagus, is crucial for radiotherapy planning.
- Manual esophagus segmentation in Computed Tomography (CT) is time-consuming, requires expertise, and is prone to errors due to ill-defined boundaries and slice variations.
- Automated segmentation methods are being developed to overcome the challenges of manual segmentation.
Purpose of the Study:
- To propose a fully automatic method for esophagus segmentation in CT images.
- To improve the efficiency and accuracy of radiotherapy planning by addressing the difficulties in manual esophagus segmentation.
Main Methods:
- The proposed method involves five key steps: image acquisition, volume of interest (VOI) segmentation, preprocessing, esophagus segmentation, and segmentation refinement.
- This automated approach aims to streamline the segmentation process.
Main Results:
- The method was evaluated on 36 CT scans from three institutions.
- Achieved state-of-the-art results with a Dice coefficient of 82.15%, Jaccard Index of 70.21%, accuracy of 99.69%, sensitivity of 90.61%, specificity of 99.76%, and Hausdorff Distance of 6.1030 mm.
Conclusions:
- The developed method shows significant promise for automated esophagus segmentation.
- This automated technique can greatly assist specialists in medical centers by simplifying the arduous task of esophagus segmentation for radiotherapy planning.
