Related Experiment Video
Updated: Dec 31, 2025
06:08
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
Published on: May 5, 2011
17.1K
Breast Cancer Identification via Thermography Image Segmentation with a Gradient Vector Flow and a Convolutional
Santiago Tello-Mijares1,2, Fomuy Woo3, Francisco Flores2
1Instituto Tecnológico Superior de Lerdo, Postgraduate Department, Lerdo 35150, Mexico.
Journal of Healthcare Engineering
|January 10, 2020
Summary
This study developed an automated system using mammary thermography to detect breast cancer. A convolutional neural network (CNN) achieved superior classification accuracy compared to other methods, aiding in early breast cancer diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Healthcare
- Oncology
Background:
- Breast cancer is a leading global health concern for women.
- Mammary thermography offers a low-cost, non-invasive method for early breast cancer detection.
- Automated image analysis can significantly enhance diagnostic efficiency in pathology.
Purpose of the Study:
- To develop an automated system for capturing and classifying breast thermographic images.
- To differentiate between normal and abnormal (cancerous) breast thermograms.
- To compare the performance of a convolutional neural network (CNN) against other classification techniques.
Main Methods:
- A segmentation method combining curvature function (k) and gradient vector flow (GVF) was employed.
- A convolutional neural network (CNN) was utilized for classifying segmented breast thermograms.
- Performance comparison included tree random forest (TRF), multilayer perceptron (MLP), and Bayes network (BN).
Main Results:
- The proposed CNN model demonstrated superior performance in classifying breast thermograms.
- CNN outperformed TRF, MLP, and BN in distinguishing between normal and abnormal breast tissue.
- Classification accuracy was based on breast shape, color, texture, and laterality (left/right).
Conclusions:
- The developed automated system shows promise for accurate and efficient breast cancer screening.
- CNNs are effective tools for analyzing thermographic images in breast cancer diagnosis.
- Automated thermography analysis can complement existing diagnostic workflows.
