Related Experiment Video
Updated: Mar 13, 2026
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
3.6K
Computer Based Melanocytic and Nevus Image Enhancement and Segmentation.
Uzma Jamil1, M Usman Akram2, Shehzad Khalid3
1Department of Computer Engineering, Bahria University, Islamabad, Pakistan; Government College University, Faisalabad, Pakistan.
Biomed Research International
|October 25, 2016
Summary
This study introduces a new method for segmenting skin lesions in dermoscopy images, improving early melanoma detection. The approach effectively preprocesses images and accurately segments cancerous areas for better classification.
Area of Science:
- Dermatology and Medical Imaging
- Computer Vision and Image Processing
Background:
- Digital dermoscopy is crucial for monitoring skin lesions, particularly melanoma, the most dangerous form of skin cancer.
- Early detection of melanoma significantly improves curability.
- Accurate segmentation of skin lesions is a critical prerequisite for reliable automated classification.
Purpose of the Study:
- To develop a novel automated approach for preprocessing and segmenting cancerous skin lesions from dermoscopic images.
- To enhance the accuracy of lesion classification by improving segmentation quality.
Main Methods:
- A novel image preprocessing technique to remove artifacts like hairs, gel, bubbles, and specular reflections.
- Utilizing wavelets for hair detection and inpainting within dermoscopic images.
- Employing an adaptive sigmoidal function to enhance lesion contrast against the skin.
- Implementing a precise segmentation algorithm to delineate lesions from the background.
Main Results:
- The proposed system successfully filters artifacts and enhances lesion contrast.
- The novel segmentation approach accurately isolates cancerous lesions.
- Comparative analysis on a European dermoscopic image database demonstrates the superiority of the proposed method over existing approaches.
Conclusions:
- The developed automated preprocessing and segmentation method significantly improves the accuracy of skin lesion analysis.
- This approach holds promise for enhancing the reliability of computer-aided diagnosis systems for melanoma detection.
