Related Experiment Video
Updated: Feb 3, 2026
08:16
Comparative Lesions Analysis Through a Targeted Sequencing Approach
Published on: November 5, 2019
7.3K
A novel cumulative level difference mean based GLDM and modified ABCD features ranked using eigenvector centrality
Maram A Wahba1, Amira S Ashour1, Yanhui Guo2
1Department of Electronics and Electrical Communications Engineering, Faculty of Engineering, Tanta University, Tanta, Egypt.
Computer Methods and Programs in Biomedicine
|October 20, 2018
Summary
A new automated system accurately identifies four skin lesion types: melanoma, basal cell carcinoma (BCC), nevi, and benign keratoses (BKL). The system uses novel texture features and an enhanced ABCD rule, achieving 100% accuracy.
Area of Science:
- Dermatology and computational pathology.
- Medical image analysis and machine learning.
Background:
- Melanoma is a leading cause of cancer death, while basal cell carcinoma (BCC) is the most common skin lesion.
- Distinguishing early-stage melanoma, BCC, benign nevi, and benign keratoses (BKL) can be challenging for medical experts.
- Accurate automated systems are needed for reliable skin lesion identification.
Purpose of the Study:
- To develop an automated, user-friendly system for accurate identification of four skin lesion types: melanoma, BCC, nevi, and BKL.
- To introduce a novel texture feature, cumulative level-difference mean (CLDM), and a modified ABCD feature set for improved classification.
- To evaluate the system's performance using feature ranking and machine learning classifiers.
Main Methods:
- Extraction of a novel texture feature, cumulative level-difference mean (CLDM), based on the gray-level difference method.
- Modification of the ABCD rule to include individual border features (compact index, fractal dimension, edge abruptness) for enhanced classification.
- Feature ranking using Eigenvector Centrality (ECFS) and classification using a cubic support vector machine (SVM).
Main Results:
- The combination of CLDM texture features and ranked modified ABCD features achieved outstanding classification performance.
- The system demonstrated 100% sensitivity, accuracy, and specificity for all four targeted classes (melanoma, BCC, nevi, BKL).
- Superior performance was observed when using the top seven ranked features.
Conclusions:
- The developed system efficiently classifies melanoma, BCC, nevi, and BKL using cubic SVM with the novel feature set.
- Comparative analyses confirmed the superiority of the cubic SVM classifier for distinguishing these four skin lesion types.
- The proposed method offers a promising approach for automated skin lesion diagnosis.
Keywords:
Cumulative level-difference meanFeature rankingModified-ABCD feature vectorSkin lesion classificationSupport vector machineMore Related Videos
05:33Measuring Biophysical and Psychological Stress Levels Following Visitation to Three Locations with Differing Levels of Nature
Published on: June 19, 2019
9.0K
08:17Author Spotlight: Unveiling the Pathway Linking Obesity to Autoimmune Inflammation in Multiple Sclerosis
Published on: February 23, 2024
5.6K
Related Concept Videos
01:01Classification of Titrimetric Analysis Based on Reaction Types
1.8K
Titrimetric analysis in solution chemistry involves measuring the volume of solutions and is often called volumetric analysis. The standard solution of known concentration in the burette is called the titrant, whereas the solution of unknown concentration in the flask is called the analyte, or titrand. Titrimetric analyses can be classified into four types based on the reactions between the titrant and analyte.
Titrations between an acid and a base lead to neutralization reactions that form...
Titrations between an acid and a base lead to neutralization reactions that form...
1.8K
01:04Cumulative Frequency Distribution
8.4K
A cumulative frequency distribution is another type of frequency distribution. Instead of reporting how many data values fall in some classes, it reports how many data values are contained in either that class or any class to its left. Technically, it means the sum of frequencies of the class and all the classes below it in a frequency distribution. A cumulative frequency is calculated by adding the frequency of each class lower than the corresponding class interval or category. In general, a...
8.4K
01:02Ranks
505
Unlike parametric methods, nonparametric statistics are ideal for nominal and ordinal data, requiring fewer assumptions about the population's nature or distribution. This makes nonparametric methods easier to apply and interpret, as they do not depend on parameters like mean or standard deviation. One common approach in nonparametric analysis is to sort data according to a specific criterion. For instance, we might arrange weather data from hottest to coldest days in a month or rank cities...
505
01:20Accessory Structures of the Skin: Hair Growth and Types
2.4K
Hair growth begins with the production of keratinocytes by the basal cells of the hair bulb. As new cells are deposited at the hair bulb, the hair shaft is pushed through the follicle toward the surface. Keratinization is completed as the cells are pushed to the skin surface to form the shaft of hair that is externally visible. The external hair is completely dead and composed entirely of keratin. Hair can be cut or shaven without damaging the hair structure because the cut is superficial. Most...
2.4K
01:20Spearman's Rank Correlation Test
1.5K
Spearman's rank correlation test, also known as Spearman's rho, is a nonparametric method for assessing the strength and direction of association between two variables. This test is particularly valuable when the data distribution is unknown or when the assumption of normality does not hold. Named after the English psychologist and statistician Dr. Charles Edward Spearman, it serves as the nonparametric counterpart to Pearson's correlation coefficient.
Spearman's test calculates correlation by...
Spearman's test calculates correlation by...
1.5K
01:25The Central Dogma
139.8K
Overview
139.8K