Multimodal Analysis of Unbalanced Dermatological Data for Skin Cancer Recognition

Abstract

To date, skin cancer is the most commonly diagnosed form of cancer in humans and is one of the leading causes of death in cancer patients. AI technologies can match and exceed visual analysis methods in accuracy, but they carry the risk of a false negative response when a malignant pigmented lesion can be recognized as benign. Possible ways to improve accuracy and reduce the risk of false negatives are to analyze heterogeneous data, combine different preprocessing methods, and use modified loss functions to eliminate the negative impact of unbalanced dermatological data. The article proposes a multimodal neural network system with a modified cross-entropy loss function that is sensitive to unbalanced heterogeneous dermatological data. The novelty of the proposed system lies in the emerging synergy when using methods to improve the quality of intelligent systems, due to which there is a significant reduction in the number of false negative predictions and an increase in the accuracy of skin cancer recognition. Preliminary cleaning of hair structures on visual data, as well as parallel analysis of heterogeneous dermatological data using a multimodal neural network system sensitive to unbalanced data, were used as methods to improve accuracy. The recognition accuracy for 10 diagnostic categories for the proposed intelligent system was 85.20%. The introduction of weighting factors made it possible to reduce the number of false negative forecasts, as well as increase the accuracy by 1.99-4.28 percentage points compared to the original multimodal systems.