Work

Enhancing skin cancer detection through category representation and fusion of pre-trained models

Year: 2025

Type: article

Abstract: The use of pre-trained models in medical image classification has gainedsignificant attention due to their ability to handle complex datasetsand improve accuracy. However, challenges such as domain-specificcustomization, interpretability, and computational efficiency remaincritical, especially in high-stakes applications such as skin cancerdetection. In this paper, we introduce a novel interpretability-assistedfine-tuning framework that leverages category representation to enhanceboth model accuracy and transparency.Using the widely known HAM10000 dataset, which includes seven imbalancedcategories of skin cancer, we demonstrate that our method improves theclassification accuracy by 2.6\% compared to standard pre-trained models.In addition to precision, we also achieve significant improvements ininterpretability, with our category representation framework providingmore understandable insights into the model’s decision-making process.Key metrics, such as precision and recall, show enhanced performance,particularly for underrepresented skin cancer types such as Melanocytic Nevi (F1 score of 0.94) and Actinic Keratosis (F1 score of 0.66).Furthermore, the prediction accuracy of the proposed model of the top-3 reaches 98. 21\%, which is highly significant for medical decision making.This observation in interpredibility underscores the value of top-$n$ predictions, especially in challenging cases, to support more informed and accurate decisions. The proposed fusion framework not only enhances predictive accuracy, but also offers an interpretable model output that can assist clinicians in making informed decisions. This makes our approach particularly relevant in medical applications, where both accuracy and transparency are crucial. Our results highlight the potential of fusing pretrained models with category representation techniques to bridge the gap between performance and interpretability in AI-driven healthcare solutions.

Source: Information Fusion

DOI: 10.1016/j.inffus.2025.103369

Authors: Lingping Kong, Juan D. Velasquez, Václav Snášel, Millie Pant, Jeng-Shyang Pan, Jana Nowakova