An Improved Multiclass Skin Cancer Identification Approach with Random Forest Algorithm over HAM10000 Data set using Color Analysis
Main Article Content
Abstract
Initial diagnosis of melanoma is disapprovingly important, as it significantly improves the patient’s chances of survival. Identification of melanoma from dermoscopic images is an inspiring task due to the similarity of different lesion appearances. The majority of current research studies focus on developing methods for binary classification, while being incomplete in addressing multi-class classification and the challenge of unfair data. This paper proposes a different approach that routines color analysis using RGB and HSV change and implements color-based data matching and model joint to perform multi-class melanoma classification and achieve higher accuracy in noticing skin cancer types. The current research ranges the understanding of melanoma finding by implementing color-based detection of skin cancer type, using advanced oversampling methods, such as SMOTE and ADASYN and improving the accuracy of melanoma discovery by grouping color analysis with class matching using the SMOTE algorithm. Notably, the paper reports an accuracy of 98% in melanoma detection using a random forest classifier and color analysis. Interestingly, the melanoma sensitivity score increases to 95% when using the SMOTE algorithm as compared to 80-85% without class balancing. Overall, the current study is a significant contribution to the early detection of melanoma, as it both increases the accuracy of detection and implements innovative methods for improving early diagnosis of skin cancer. The novelty of this approach is related to the unique application of color analysis in detecting melanoma. The current article provides an advanced framework for automatic detection of skin cancer type, thus supplying medical professionals with a valuable tool for early diagnosis of melanoma and ultimately saving lives
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
B. Shetty, R. Fernandes, A. P. Rodrigues, R. Chengoden, S. Bhattacharya and
K. Lakshmanna, “Skin lesion classification of dermoscopic images using machine learning and convolutional neural network,” Scientific Reports, vol. 12, no. 1, 2022.
P. Tschandl, C. Rosendahl, and H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Scientific Data, vol. 5, Aug. 2018.
B. Ozdemir and I. Pacal, “A robust deep learning framework for multiclass skin cancer classification,” Scientific Reports, vol. 15, Feb. 2025.
M. A. Sarker, M. A. Kabir, and M. S. Hossain, “Lggc-net: a local-global graph and color attention-based lightweight CNN for skin cancer classification,” Scientific Reports, vol. 16, Apr. 2026.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002.
J. S M, M. P, C. Aravindan, and R. Appavu, “Classification of skin cancer from dermoscopic images using deep neural network architectures,” Multimedia Tools and Applications, vol. 82, pp. 15763–15778, Oct. 2022.
X. He, Y. Wang, S. Zhao, and C. Yao, “Deep metric attention learning for skin lesion classification in dermoscopy images,” Complex and Intelligent Systems, vol. 8, pp. 1487–1504, Jan. 2022.
X. He, E.-L. Tan, H. Bi, X. Zhang, S. Zhao, and B. Lei, “Fully transformer network for skin lesion analysis,” Medical Image Analysis, vol. 77, p. 102357, Apr. 2022.
Sarker, C. F. Moreno-García, J. Ren, and E. Elyan, “TransSLC: Skin Lesion Classification in Dermatoscopic Images Using Transformers,” pp. 651–660, Springer International Publishing, 2022
K. Nakai, Y.-W. Chen, and X.-H. Han, “Enhanced deep bottleneck transformer model for skin lesion classification,” Biomedical Signal Processing and Control, vol. 78, p. 103997, 2022.
C. Xin, Z. Liu, K. Zhao, L. Miao, Y. Ma, X. Zhu, Q. Zhou, S. Wang, L. Li, F. Yang, S. Xu, and H. Chen, “An improved transformer network for skin cancer classification,” Computers in Biology and Medicine, vol. 149, p. 105939, Oct. 2022.
S. Khan and A. Khan, “SkinViT: A transformer based method for melanoma and nonmelanoma classification,” PLOS ONE, vol. 18, p. e0295151, Dec. 2023.
Y. Nie, P. Sommella, M. Carratù, M. O’Nils, and J. Lundgren, “A deep CNN transformer hybrid model for skin lesion classification of dermoscopic images using focal loss,” Diagnostics, vol. 13, p. 72, Dec. 2022.
G. Yang, S. Luo, and P. Greer, “A novel vision transformer model for skin cancer classification,” Neural Processing Letters, vol. 55, pp. 9335–9351, Mar. 2023.
Q. Abbas, Y. Daadaa, U. Rashid, and M. Ibrahim, “Assist-Dermo: A lightweight separable vision transformer model for multiclass skin lesion classification,” Diagnostics, vol. 13, no. 15, p. 2531, 2023.
Y. Ding, Z. Yi, J. Xiao, M. Hu, Y. Guo, Z. Liao, and Y. Wang, “CTH-Net: A CNN and transformer hybrid network for skin lesion segmentation,” iScience, vol. 27, p. 109442, Apr. 2024.
K. Tang, J. Su, R. Chen, R. Huang, M. Dai, and Y. Li, “SkinSwinViT: A lightweight transformer-based method for multiclass skin lesion classification with enhanced generalization capabilities,” Applied Sciences, vol. 14, p. 4005, May 2024.
K. Rezaee and H. G. Zadeh, “Self-attention transformer unit-based deep learning framework for skin lesions classification in smart healthcare,” Discover Applied Sciences, vol. 6, Jan. 2024.
Y. Yang, F. Xie, H. Zhang, J. Wang, J. Liu, Y. Zhang, and H. Ding, “Skin lesion classification based on two-modal images using a multi-scale fully-shared fusion network,” Computer Methods and Programs in Biomedicine, vol. 229, p. 107315, Feb. 2023.
Z. Hu, W. Mei, H. Chen, and W. Hou, “Multi-scale feature fusion and class weight loss for skin lesion classification,” Computers in Biology and Medicine, vol. 176, p. 108594, 2024.
K. Ramamurthy, I. Thayumanaswamy, M. Radhakrishnan, D. Won, and S. Lingaswamy, “Integration of localized, contextual, and hierarchical features in deep learning for improved skin lesion classification,” Diagnostics, vol. 14, no. 13, p. 1338, 2024.
S. M. Thwin and H.-S. Park, “Skin lesion classification using a deep ensemble model,” Applied Sciences, vol. 14, no. 13, p. 5599, 2024.
H. Erbay, Y. M. Abulgasim, D. E. Özer, and F. Ertürk, “Enhancing multi-class skin lesion diagnosis through ensemble learning of CNN and transformer architectures,” Engineering Science and Technology, an International Journal, vol. 70, p. 102145, Oct. 2025.
N. Ahmad, J. H. Shah, M. A. Khan, J. Baili, G. J. Ansari, U. Tariq, Y. J. Kim, and J.-H. Cha, “A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI,” Frontiers in Oncology, vol. 13, 2023.
M. Arshad, M. A. Khan, N. A. Almujally, A. Alasiry, M. Marzougui, and Y. Nam, “Multiclass skin lesion classification and localziation from dermoscopic images using a novel network-level fused deep architecture and explainable artificial intelligence,” BMC Medical Informatics and Decision Making, vol. 25, no. 1, 2025.
T. G. Debelee, “Skin lesion classification and detection using machine learning techniques: A systematic review,” Diagnostics, vol. 13, p. 3147, Oct. 2023.
N. Sravani and S. Koppu, “Explainable ensemble transfer learning for skin lesion classification with multi-method explainability validation,” Frontiers in Public Health, vol. 14, p. 1847649, 2026.
M. G, C. Baskar, and S. A, “Hybrid deep feature fusion and ensemble learning for multi-class skin lesion classification,” Frontiers in Artificial Intelligence, vol. 9, 2026.
S. Faizal, C. A. Rajput, and M. R. Prusty, “An automated framework to classify skin lesions using multi-head self attention layer-based vision transformers,” Frontiers in Artificial Intelligence, vol. 9, May 2026.
S. S. Waseem, S. Iftikhar, A. Rafiq, K. Lee, and S. R. Hassan, “Image-driven multimodal deep learning for skin cancer diagnosis: Cross-attention fusion of dermoscopic imaging clinical data and knowledge graphs,” Sensors, vol. 26, no. 15,p. 4728, 2026.
E. Sonuç, Q. Saihood, Y. Yargı Baydilli, and E. Özcan, “Interpretable multimodal fusion for skin lesion classification using dermoscopic images and patient metadata,” Frontiers in Medicine, vol. 13, 2026