Related Experiment Video
Updated: Aug 16, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.9K
Breast tumor localization and segmentation using machine learning techniques: Overview of datasets, findings, and
Ramin Ranjbarzadeh1, Shadi Dorosti2, Saeid Jafarzadeh Ghoushchi2
1School of Computing, Faculty of Engineering and Computing, Dublin City University, Ireland.
Computers in Biology and Medicine
|December 23, 2022
Summary
Early breast cancer (BC) detection is crucial for reducing mortality. This study overviews segmentation techniques in computer-aided diagnosis (CAD) systems, comparing supervised, unsupervised, and deep learning (DL) methods for medical image analysis.
Area of Science:
- Medical Imaging Analysis
- Artificial Intelligence in Healthcare
Background:
- Breast cancer (BC) is the most common cancer diagnosis globally.
- Early detection of BC significantly reduces mortality rates.
- Breast imaging techniques are vital for identifying cancerous cells and lesions.
Purpose of the Study:
- To provide a comprehensive overview of segmentation techniques used in computer-aided diagnosis (CAD) systems.
- To compare supervised, unsupervised, and deep learning (DL) segmentation methods.
- To assist researchers in selecting appropriate segmentation techniques for medical image analysis.
Main Methods:
- Review of segmentation procedures in CAD systems.
- Classification of segmentation techniques into supervised, unsupervised, and DL categories.
- Discussion of the advantages and disadvantages of each segmentation class.
Main Results:
- Segmentation is a key image processing technique in CAD systems for extracting regions of interest (ROI).
- Supervised, unsupervised, and DL methods offer distinct approaches to medical image segmentation.
- Each method presents unique benefits and drawbacks influencing their applicability.
Conclusions:
- Understanding different segmentation techniques is essential for advancing CAD systems in breast cancer detection.
- This overview aids researchers in choosing optimal methods for specific medical imaging use cases.
- Improved segmentation accuracy can enhance diagnostic capabilities and decision-making for radiologists.
