DEEP LEARNING-BASED MELANOMA CLASSIFICATION ENHANCED BY FRACTAL DIMENSION ANALYSIS
DOI:
https://doi.org/10.20535/kpisn.2025.4.343191Keywords:
deep learning, vision transformer, fractal dimension, melanoma, skin cancer, XAIAbstract
Background. Melanoma is a malignant skin lesion that is prone to metastasize aggressively, leading to an almost guaranteed lethal outcome if left unchecked. In contrast, early-stage detection allows for the tumor to be removed via a harmless surgical procedure that may not even leave a scar. However, the availability of competent diagnostics are often limited due to a shortage of healthcare specialists and technologies. Deep Learning models such as Visual Transformer (ViT) have demonstrated strong performance, but researchers continuously seek to improve the results by incorporating new features. Since human skin exhibits fractal-like characteristics, it is theorized that metrics quantifying this complexity can act as valuable supplementary features for DL models, leading to increased classification accuracy.
Objective. We investigated the impact of the integration of fractal dimension (FD) on a Vision Transformer deep learning model used for melanoma classification. A comparison was made on models that received random noise vs. the estimation of FD value.
Methods. Vision Transformer was used as a feature-extracting backbone pre-trained on ImageNet dataset. Fine-tuning was done on this backbone in combination with a classification head targeted to distinguish melanoma vs. nevus classes. Along with extracted features, the classification head received FD value. An identical model received random noise instead of FD. Statistical testing and FD impact analysis were done to confirm the significance of the new feature.
Results. Integrating FD into ViT showed noticeable improvement in test metrics. SHAP analysis confirmed the meaningfulness of the new feature. McNemar's test validated that the difference in model predictions was statistically significant.
Conclusions. The results suggest that FD can serve as a valuable supplementary feature for DL models, and the integration of biomarkers such as FD provides a basis for more robust melanoma classification.
References
World Cancer Research Fund International, "Skin cancer statistics," 2022. [Online]. Available: https://www.wcrf.org/cancer-trends/skin-cancer-statistics/. [Accessed: Nov. 7, 2025].
International Skin Imaging Collaboration (ISIC), "ISIC Archive." [Online]. Available: https://www.isic-archive.com/. [Accessed: Nov. 7, 2025]
P. Popecki et al., "Fractal dimension analysis of melanocytic nevi and melanomas in normal and polarized light-A preliminary report," Life, vol. 12, no. 7, p. 1008, 2022. doi: 10.3390/life12071008.
A. Dosovitskiy et al., "An image is worth 16x16 words: Transformers for image recognition at scale," arXiv preprint arXiv:2010.11929, 2021. [Online]. Available: https://doi.org/10.48550/arXiv.2010.11929.
S. Khan, H. Ali, and Z. Shah, “Identifying the role of vision transformer for skin cancer—A scoping review,” Frontiers in Artificial Intelligence, vol. 6, Jul. 2023, doi: 10.3389/frai.2023.1202990.
S. Moldovanu et al., "Skin lesion classification based on surface fractal dimensions and statistical color cluster features using an ensemble of Machine Learning Techniques," Cancers, vol. 13, no. 21, p. 5256, 2021. doi: 10.3390/cancers13215256.
V. Nikitin and V. Danilov, "Integration of fractal dimension in vision transformer for skin cancer classification," Electronics and Control Systems, no. 76, 2023. doi: 10.18372/1990-5548.76.17662.
V. Nikitin and V. Danilov, "Fractal dimension calculation techniques for skin lesion characterisation," in Матеріали конференцій МЦНД, 2024. doi: 10.62731/mcnd-26.07.2024.005.
G. M. S. Himel et al., "Skin cancer segmentation and classification using vision transformer for automatic analysis in dermatoscopy-based non-invasive digital system," arXiv preprint arXiv:2401.04746, 2024. [Online]. Available: https://doi.org/10.48550/arXiv.2401.04746.
T. Khater et al., "Skin cancer classification using explainable artificial intelligence on pre-extracted image features," Intelligent Systems with Applications, vol. 21, p. 200275, Feb. 2024. doi: 10.1016/j.iswa.2023.200275.
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, p. 180161, 2018. doi: 10.1038/sdata.2018.161.
M. Combalia et al., "BCN20000: Dermoscopic lesions in the wild," arXiv preprint arXiv:1908.02288, 2019. [Online]. Available: https://doi.org/10.48550/arXiv.1908.02288. [Accessed: Nov. 8, 2025].
J. Wu, X. Jin, S. Mi, and J. Tang, "An effective method to compute the box-counting dimension based on the mathematical definition and intervals," Results in Engineering, vol. 6, p. 100106, 2020. doi: 10.1016/j.rineng.2020.100106.
T. Lee, V. Ng, R. Gallagher, A. Coldman, and D. McLean, "Dullrazor®: A software approach to hair removal from images," Computers in Biology and Medicine, vol. 27, no. 6, pp. 533–543, Nov. 1997. doi: 10.1016/s0010-4825(97)00020-6.
J. Canny, "A Computational Approach to Edge Detection," IEEE Trans. Pattern Anal. Mach. Intell., vol. 8, no. 6, pp. 679–698, Nov. 1986.
S. Suzuki and K. Abe, "Topological structural analysis of digitized binary images by border following," Computer Vision, Graphics, and Image Processing, vol. 30, no. 1, pp. 32–46, Apr. 1985.
S. Spasić, "On 2D generalization of Higuchi’s fractal dimension," Chaos, Solitons & Fractals, vol. 69, pp. 179–187, Dec. 2014. doi: 10.1016/j.chaos.2014.09.015.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Vladyslav Nikitin, Valerii Danilov
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under CC BY 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
