Related Experiment Video
Updated: May 9, 2026
05:24
Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
Published on: January 10, 2025
[Study on multi-level fractal features extraction method of breast mass]
1Institute of Biomedical and Electromagnetic Engineering, Shenyang University of Technology, Shenyang 110870, China. ke.l@live.cn
Summary
This study introduces a novel multi-level fractal analysis for detecting breast masses. The method achieved 90% accuracy in classifying 110 mammograms, aiding early breast cancer diagnosis.
Area of Science:
- Medical Imaging
- Biomedical Engineering
- Radiology
Background:
- Breast mass detection is crucial for women's health.
- Accurate mass identification improves diagnostic precision.
- Texture features, including organizational structure and surface roughness, are key for distinguishing masses.
Purpose of the Study:
- To propose a multi-level fractal feature extraction method for mammary gland analysis.
- To establish a fractal feature vector for suspicious lesions.
- To evaluate the effectiveness of this method in mass detection and classification.
Main Methods:
- A multi-level fractal feature extraction technique was developed.
- Fractal feature vectors were created for suspicious lesions.
- Support Vector Machine (SVM) classification was employed on 110 mammograms.
Main Results:
- The proposed method successfully extracted and analyzed fractal features of mammary glands.
- Classification using SVM achieved an accuracy of 90% on the dataset.
- The fractal feature analysis demonstrated effectiveness in mass detection.
Conclusions:
- The multi-level fractal features extraction and classification methods enhance mass detection accuracy.
- This approach shows promise for the early diagnosis of breast diseases.
- Fractal analysis is a valuable tool for improving mammogram interpretation.
