ABSTRACT
Artificial intelligence holds great promise in medical imaging and machine learning. However, artificial intelligence algorithms cannot completely explain decision-making cognitive processes. This circumstance has raised the explainability, sometimes known as the black box, in challenges of XAI in applications: an algorithm merely answers without explaining why the provided pictures were chosen. Explainable artificial intelligence (XAI) has emerged as a solution to this challenge and has grabbed the interest of many academics. In this review, we share our thoughts on current and future machine learning and possible next steps for the veterinary and animal sciences field. First, we discuss the explainable artificial intelligence in biomedical applications. Following that, we will discuss how AI-powered models 34may play a more sustainable role in the animal scientific environment. Lastly, we provide recommendations for XAI future perspective in animal field on how to support themselves, the dairy farmers, poultry farmers, and challenges to using XAI in veterinary and animal sciences, considering the opportunities and challenges of XAI in applications.
