Related Experiment Videos
Technical report on semiautomatic segmentation using the Adobe Photoshop
Jin Seo Park1, Min Suk Chung, Sung Bae Hwang
1Department of Anatomy, Ajou University School of Medicine, 5 Woncheon-dong, Yeongtong-gu, Suwon, 443-749, South Korea.
Journal of Digital Imaging
|July 9, 2005
Summary
This study introduces a semiautomatic method for segmenting anatomical structures in medical images like MRIs and CTs using Adobe Photoshop. This technique aids in creating 3D visualizations for medical education and research.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Anatomical Visualization
Background:
- Accurate segmentation of anatomical structures is crucial for medical education, research, and 3D model creation.
- Existing segmentation methods can be time-consuming and require specialized expertise.
Purpose of the Study:
- To develop a user-friendly, semiautomatic method for segmenting anatomical structures in medical images on personal computers.
- To facilitate the creation of 3D visualizations from segmented medical image data.
Main Methods:
- Semiautomatic segmentation of 19 anatomical structures in 557 magnetic resonance images (MRIs) using Adobe Photoshop's MAGNETIC LASSO TOOL.
- Manual correction of contours using LASSO TOOL or DIRECT SELECTION TOOL.
- Segmentation of 13 anatomical structures across 8,590 additional anatomical images.
Main Results:
- Successfully generated 557 segmented MRI images and segmented 13 structures in 8,590 anatomical images.
- Verified segmentation accuracy by creating 3D images from the segmented datasets.
- Demonstrated the feasibility of using personal computers for medical image segmentation.
Conclusions:
- Semiautomatic segmentation using Adobe Photoshop is a viable and efficient method for anatomical structure segmentation.
- The developed technique is expected to find widespread application in medical education and research.
- This approach simplifies the process of creating 3D anatomical models from medical imaging data.