Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 10, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Mammographic mass detection using wavelets as input to neural networks.

Niyazi Kilic¹, Pelin Gorgel, Osman N Ucan

¹Electrical & Electronics Department, Istanbul University, Avcilar, Istanbul, Turkey. niyazik@istanbul.edu.tr

Journal of Medical Systems

|August 13, 2010

Summary

Artificial neural networks combined with wavelet transforms effectively detect malignant or benign mammogram masses. The Levenberg-Marquardt algorithm achieved 89.2% sensitivity in classifying breast masses.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Brain Inspired Cortical Coding Method for Fast Clustering and Codebook Generation.

Entropy (Basel, Switzerland)·2022

Same author

An Efficient and Reliable Routing Method for Hybrid Mobile Ad Hoc Networks Using Deep Reinforcement Learning.

Applied bionics and biomechanics·2020

Same author

An Efficient Big Data Anonymization Algorithm Based on Chaos and Perturbation Techniques.

Entropy (Basel, Switzerland)·2020

Same author

Classification of Resting-State Status Based on Sample Entropy and Power Spectrum of Electroencephalography (EEG).

Applied bionics and biomechanics·2020

Same author

Social Touch Gesture Recognition Using Convolutional Neural Network.

Computational intelligence and neuroscience·2018

Same author

Automatic Estimation of Osteoporotic Fracture Cases by Using Ensemble Learning Approaches.

Journal of medical systems·2015

Area of Science:

Medical Imaging
Artificial Intelligence
Biomedical Signal Processing

Background:

Mammography is crucial for breast cancer screening.
Accurate differentiation of benign and malignant masses is essential.
Computational methods can aid in mass classification.

Purpose of the Study:

To evaluate artificial neural networks (ANNs) with wavelet transforms for mammogram mass classification.
To determine the efficacy of different ANN training algorithms.

Main Methods:

Wavelet transform was used for feature extraction from mammogram masses.
Multilayer ANNs were trained using Backpropagation, Conjugate Gradient, and Levenberg-Marquardt algorithms.
A ten-fold cross-validation procedure was employed.

More Related Videos

Clinical Imaging of Microwave Mammography

Clinical Imaging of Microwave Mammography

Published on: November 14, 2025

Related Experiment Videos

Last Updated: Jun 10, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

Clinical Imaging of Microwave Mammography

Clinical Imaging of Microwave Mammography

Published on: November 14, 2025

Main Results:

The Levenberg-Marquardt algorithm achieved a sensitivity of 89.2%.
This algorithm demonstrated fast convergence for desired results.
The combined approach showed utility in detecting mammogram masses.

Conclusions:

Artificial neural networks coupled with wavelet transforms are effective for mammogram mass detection.
The Levenberg-Marquardt algorithm offers a robust and efficient method for classification.
This technique shows promise in improving diagnostic accuracy for breast masses.