Related Experiment Video
Updated: Jun 26, 2026
13:44
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
Published on: August 30, 2013
Automatic detection of clustered microcalcifications in digital mammograms: Study on applying adaboost with SVM-based
F Dehghan1, H Abrishami-Moghaddam, M Giti
1Electrical Engineering Department, K. N. Toosi University of Technology, 16315-1355 Tehran, Iran. dehghan_faramarz@ieee.org
Summary
This study introduces a computer-aided diagnosis (CAD) system for detecting clustered microcalcifications (MCs) in mammograms. The system achieved an 89.55% true positive rate with a low false positive rate, showing promising results for early breast cancer detection.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Breast Cancer Screening
Background:
- Early detection of breast cancer is crucial for improving patient outcomes.
- Microcalcifications are common indicators of breast cancer in mammograms.
- Automating the detection of microcalcifications can aid radiologists and improve diagnostic accuracy.
Purpose of the Study:
- To develop and evaluate a computer-aided diagnosis (CAD) system for the automatic detection of clustered microcalcifications (MCs) in digitized mammograms.
- To assess the performance of the proposed CAD system using a standard dataset and FROC analysis.
Main Methods:
- A two-step CAD system was developed: pixel segmentation using wavelet and statistical features, followed by object detection.
- The first step employed a multilayer feedforward neural network, while the second step used Adaboost with SVM classifiers (RBF kernel).
- The system was tested on the Nijmegen database, comprising 40 mammograms with 105 MC clusters.
Main Results:
- The CAD system demonstrated satisfactory performance in detecting clustered microcalcifications.
- Achieved a mean true positive detection rate of 89.55%.
- Maintained a low false positive rate of 0.921 per image.
Conclusions:
- The proposed computer-aided diagnosis system effectively detects clustered microcalcifications in mammograms.
- The system's high true positive rate and low false positive rate indicate its potential utility in breast cancer screening.
- Further validation on larger datasets could enhance its clinical applicability.
