Related Experiment Video
Updated: Aug 26, 2026
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
Published on: May 24, 2022
Segmentation of vessels from mammograms using a deformable model
Francisco L Valverde1, Nicolás Guil, Jose Muñoz
1Department of Computer Science, ETSI Informatica, University of Málaga, Malaga 29071, Spain. valverde@lcc.uma.es
Insights
This study introduces a fully automatic algorithm for extracting vessels from noisy medical images, specifically mammograms. The novel two-stage approach effectively reduces noise, improving vessel detection accuracy and enabling real-time clinical applications.
Area of Science:
- Medical Imaging
- Image Processing
- Biomedical Engineering
Background:
- Vessel extraction is crucial for medical imaging analysis, including angiograms.
- Existing segmentation methods often require manual input or are sensitive to image noise.
- Challenges in mammography include noise, variable backgrounds, and low vessel contrast, hindering reliable automated detection.
Purpose of the Study:
- To develop a fully automatic algorithm for vessel extraction in noisy medical images.
- To address the negative impact of noise on segmentation accuracy.
- To validate the algorithm's performance on mammograms for clinical applicability.
Main Methods:
- A two-stage noise reduction procedure was implemented.
- The first stage employed global edge detection and thresholding.
- The second stage utilized a deformable model with a novel energy term for refined vessel segmentation.
Main Results:
- The algorithm demonstrated excellent accuracy, sensitivity, and specificity in experimental results on mammograms.
- The method effectively reduced noise, a significant challenge in medical image segmentation.
- The computational time proved suitable for real-time clinical applications.
Conclusions:
- The proposed fully automatic algorithm offers a robust solution for vessel extraction in noisy medical images.
- The two-stage noise reduction and deformable model approach significantly enhances segmentation performance.
- This method holds promise for improving diagnostic capabilities in mammography and other medical imaging fields.
Abstract:
Vessel extraction is a fundamental step in certain medical imaging applications such as angiograms. Different methods are available to segment vessels in medical images, but they are not fully automated (initial vessel points are required) or they are very sensitive to noise in the image. Unfortunately, the presence of noise, the variability of the background, and the low and varying contrast of vessels in many imaging modalities such as mammograms, makes it quite difficult to obtain reliable fully automatic or even semi-automatic vessel detection procedures. In this paper a fully automatic algorithm for the extraction of vessels in noisy medical images is presented and validated for mammograms. The main issue in this research is the negative influence of noise on segmentation algorithms. A two-stage procedure was designed for noise reduction. First, a global approach phase including edge detection and thresholding is applied. Then, the local approach phase performs vessel segmentation using a deformable model with a new energy term that reduces the noise still remaining in the image from the first stage. Experimental results on mammograms show that this method has an excellent performance level in terms of accuracy, sensitivity, and specificity. The computation time also makes it suitable for real-time applications within a clinical environment.
