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.
Background. Financial time series are characterized by nonlinearity, non-stationarity, and a high level of noise, which significantly complicates their modeling and…
Background . Modern industrial control systems are characterized by a high level of integration between information and physical processes and the use of distributed…
Background. Zoom optical systems utilising mechanically fixed, electrically controlled varifocal lenses cannot be regarded as having fixed optical components. The…
You may also start an advanced similarity search for this article.