Related Experiment Video
Updated: May 16, 2026
06:34
SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
Published on: August 8, 2025
Segmentation of dermoscopy images using wavelet networks.
Amir Reza Sadri1, Maryam Zekri, Saeed Sadri
1Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan, Iran. ar.sadri@ec.iut.ac.ir
IEEE Transactions on Bio-Medical Engineering
|November 30, 2012
Summary
This study presents a novel, training-free wavelet network (WN) for segmenting skin lesions in dermoscopic images. The method accurately identifies lesion boundaries, outperforming existing techniques in medical image analysis.
Area of Science:
- Medical Imaging
- Computer Vision
- Dermatology
Background:
- Accurate segmentation of skin lesions is crucial for diagnosis.
- Existing methods often require extensive training data and computational resources.
Purpose of the Study:
- To introduce a novel, training-free wavelet network (WN) for automated skin lesion segmentation.
- To improve the accuracy and efficiency of skin lesion boundary detection in dermoscopic images.
Main Methods:
- A fixed-grid wavelet network (WN) is constructed without prior training.
- A two-stage screening process optimizes wavelet parameters (shift and scale).
- Orthogonal least squares algorithm calculates network weights and optimizes structure.
Main Results:
- The proposed WN method achieved effective segmentation of skin lesions.
- The algorithm demonstrated superior performance compared to several modern medical imaging techniques.
- Evaluation on 30 dermoscopic images using 11 metrics confirmed its efficacy.
Conclusions:
- The training-free wavelet network offers a promising approach for skin lesion segmentation.
- The method provides accurate boundary determination and enhances diagnostic capabilities.
- This technique represents an advancement in automated medical image analysis for dermatology.
