Related Experiment Video
Updated: Dec 22, 2025
06:08
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
Published on: May 5, 2011
17.1K
Detecting anomalous growth of skin lesion using threshold-based segmentation algorithm and Fuzzy K-Nearest Neighbor
S Sivaraj1, R Malmathanraj1, P Palanisamy1
1Department of Electronics and Communication Engineering, National Institute of Technology, Tiruchirappalli, Tamil Nadu, India.
Journal of Cancer Research and Therapeutics
|May 5, 2020
Summary
This study introduces a novel hybrid Firefly with K-Nearest Neighbor (FKNN) algorithm for skin cancer image classification. The FKNN method efficiently recognizes skin cancer, reducing the need for biopsies.
Area of Science:
- Dermatology
- Medical Imaging
- Computational Biology
Background:
- Skin cancer is a serious disease driven by genetic instability.
- Early detection and accurate classification are crucial for effective treatment.
- Quantitative analysis of skin lesions aids clinical diagnosis.
Purpose of the Study:
- To develop a non-invasive method for skin cancer classification using image processing.
- To introduce a hybrid Firefly with K-Nearest Neighbor (FKNN) algorithm for enhanced accuracy.
- To provide a quantitative tool for skin lesion analysis.
Main Methods:
- A hybrid FKNN classifier was developed for skin image classification.
- Image preprocessing included homomorphic filtering to remove illumination variations.
- Threshold-based segmentation and ABCD feature extraction were employed.
Main Results:
- The proposed FKNN method demonstrated efficient skin cancer recognition.
- Performance was compared with existing methods, showing superior results.
- The technique offers a quantitative approach to skin lesion assessment.
Conclusions:
- The FKNN algorithm provides efficient and accurate skin cancer recognition.
- This hybrid approach offers a valuable tool for clinical decision-making.
- The method reduces computational complexity and time compared to other techniques.
