Related Experiment Video
Updated: Dec 16, 2025
10:35
Multimodal Imaging and Spectroscopy Fiber-bundle Microendoscopy Platform for Non-invasive, In Vivo Tissue Analysis
Published on: October 17, 2016
8.2K
An embedded novel compact feature profile image in speech signal for teledermoscopy system
Amira S Ashour1, Maram A Wahba1, Basant S Abd El-Wahab1
1Department of Electronics and Electrical Communications Engineering, Faculty of Engineering, Tanta University, Tanta, Egypt.
Health Information Science and Systems
|July 7, 2020
Summary
This study introduces a secure teledermoscopy system using compact feature profiles (CFP) watermarked in speech signals. The novel method enables efficient and accurate remote diagnosis of skin conditions like melanoma and nevus.
Area of Science:
- Medical Imaging
- Telemedicine
- Digital Signal Processing
Background:
- Teledermoscopy enables remote skin disease diagnosis but requires efficient, secure image transmission.
- Challenges include large image sizes, bandwidth limitations, and data security.
Purpose of the Study:
- To develop an improved teledermoscopy system for efficient and secure dermoscopy image transmission.
- To enable automated classification of malignant melanoma and benign nevus at the receiver.
Main Methods:
- A novel compact feature profile (CFP) representation for dermoscopy images was proposed.
- CFP was watermarked into speech signals using Singular Value Decomposition (SVD) for secure transmission.
- A modified SVD technique and wavelet denoising were used for reconstruction and diagnosis at the receiver.
Main Results:
- The CFP diagnostic system demonstrated high accuracy, sensitivity, specificity, and F-measure.
- Effective classification was achieved even with signal-to-noise ratios from 10 to 25 dB.
Conclusions:
- The proposed CFP watermarking system offers an efficient and secure solution for teledermoscopy.
- The DWT-based modified SVD with wavelet denoising enhances diagnostic capabilities in telemedicine.
