EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Lightweight Hybrid Feature Extraction for Real-Time Skin Lesion Classification on HAM10000 and MSK10000

Fallah H. Najjar, Farhan Mohamed, Ali Hilal Ali, Chan Vei Siang, Mohd Shafry Mohd Rahim, Alfian Ma'arif, Karrar Kadhim

Journal of Robotics and Control (JRC) · 01.05.2026 · 7 (3) · 3724-3734

DOI: 10.18196/jrc.v7i3.26906 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Robotics and Control (JRC), online erschienen am 01.05.2026. Verfasst von Fallah H. Najjar und 6 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Skin cancer is one of the most prevalent, and in some cases deadly, cancers globally, underscoring the importance of early and precise diagnosis upon which successful disease management is dependent. Conventional diagnosis procedures are time-consuming and prone to varying routines requiring automated and consistent classification systems. In this paper, we propose a hybrid feature extraction method for binary and multi-class skin-lesion classification by integrating Local Binary Pattern (LBP) and Gray Level Run Length Matrix (GLRLM). The approach is benchmarked on two public dermoscopic image datasets (HAM10000, seven classes and MSK10000, binary classification). Twenty-one features are calculated for each image (10 LBP and 11 GLRLM), and their classification is done using five machine learning algorithms: k-Nearest Neighbor (kNN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF) and AdaBoost. The proposed system achieves a maximum 99.52% accuracy and a maximum 99.25% F1-score in the binary classification, outperforming many deep learning based benchmarks. In multi-class problems, it reaches 97.63% accuracy and presents high scores in precision, sensitivity, and specificity. Cross-validation verifies the stability of the model. Feature extraction requires only 0.011 seconds per image, revealing computational efficiency. Analysis of feature importance shows a consistent contribution by all the features extracted. The technique exhibits high performance, minimal computational burden, and is deployable in a real-time clinical setup. This method provides a convenient solution for early and accurate skin lesion classification in both clinical and resource-constrained environments.

Zitieren

APA

Najjar, F. H., Mohamed, F., Ali, A. H., Siang, C. V., Rahim, M. S. M., Ma'arif, A., & Kadhim, K. (2026). Lightweight Hybrid Feature Extraction for Real-Time Skin Lesion Classification on HAM10000 and MSK10000. Journal of Robotics and Control (JRC), 7(3), 3724-3734. https://doi.org/10.18196/jrc.v7i3.26906

Vancouver

Najjar FH, Mohamed F, Ali AH, Siang CV, Rahim MSM, Ma'arif A, et al. Lightweight Hybrid Feature Extraction for Real-Time Skin Lesion Classification on HAM10000 and MSK10000. Journal of Robotics and Control (JRC). 2026;7(3):3724-3734. doi:10.18196/jrc.v7i3.26906

BibTeX
@article{Najjar2026,
  author = {Najjar, Fallah H. and Mohamed, Farhan and Ali, Ali Hilal and Siang, Chan Vei and Rahim, Mohd Shafry Mohd and Ma'arif, Alfian and Kadhim, Karrar},
  title = {Lightweight Hybrid Feature Extraction for Real-Time Skin Lesion Classification on HAM10000 and MSK10000},
  journal = {Journal of Robotics and Control (JRC)},
  year = {2026},
  volume = {7},
  number = {3},
  pages = {3724--3734},
  doi = {10.18196/jrc.v7i3.26906}
}
Kostenlos starten →