Related Experiment Video
Updated: Apr 28, 2026
08:40
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
Published on: April 8, 2016
12.4K
Prostate segmentation based on variant scale patch and local independent projection.
IEEE Transactions on Medical Imaging
|June 4, 2014
Summary
This study introduces an automated prostate segmentation method for CT images using a novel variant scale patch feature and local independent projection. The approach enhances accuracy for image-guided radiotherapy.
Area of Science:
- Medical Imaging
- Radiotherapy
- Computer Vision
Background:
- Accurate prostate segmentation in computed tomography (CT) images is crucial for effective image-guided radiotherapy.
- Existing segmentation methods face challenges, necessitating advanced automated solutions.
Purpose of the Study:
- To develop an automatic framework for precise prostate segmentation in CT images.
- To introduce a novel image feature extraction method and segmentation criterion.
Main Methods:
- Proposed a variant scale patch method for rich, low-dimensional feature extraction.
- Introduced local independent projection (LIP) segmentation criterion emphasizing locality.
- Utilized an online updated dictionary and local anchor embedding for dictionary coefficients.
- Incorporated morphological operations to refine segmentation results.
Main Results:
- The method was evaluated on 330 3-D CT images from 24 patients.
- Demonstrated robust and effective performance in segmenting the prostate.
- The variant scale patch and LIP approach showed significant potential.
Conclusions:
- The developed automatic framework offers a robust and effective solution for prostate segmentation in CT images.
- This advancement can improve the precision of image-guided radiotherapy.
- The novel feature extraction and segmentation techniques show promise for medical image analysis.
