Features of using EXPLAINABLE AI in biomedical image processing: transparency and interpretability of models

Artificial intelligence (AI) has become deeply integrated into numerous scientific fields, including biomedical image and signal processing. The growing interest in this field has led to a surge in research, as evidenced by the sharp increase in scientific activity. Using large and diverse biomedical datasets, machine learning and deep learning models have transformed a variety of tasks - such as modeling, segmentation, registration, classification, and synthesis - often outperforming traditional methods. However, a major challenge remains: the difficulty of translating AI-derived results into clinically or biologically meaningful solutions, which limits the practical utility of these models. Explainable AI (XAI) seeks to bridge this gap by improving the interpretability of AI systems and offering transparent explanations for their decisions. More and more approaches are being developed to address this problem, and interest in the topic in the scientific community continues to grow.