Decoding Decision Reasoning: A Counterfactual-Powered Model for Knowledge Discovery
This work addresses the need for reliable AI explanations in healthcare, particularly for early disease detection and prognosis, though it appears incremental in improving feature identification.
The authors tackled the problem of explaining AI model predictions in medical imaging, where subtle features make conventional methods ineffective, by proposing a model that identifies and visualizes decisive features, validated in a medical prognosis task.
In medical imaging, particularly in early disease detection and prognosis tasks, discerning the rationale behind an AI model's predictions is crucial for evaluating the reliability of its decisions. Conventional explanation methods face challenges in identifying discernible decisive features in medical image classifications, where discriminative features are subtle or not immediately apparent. To bridge this gap, we propose an explainable model that is equipped with both decision reasoning and feature identification capabilities. Our approach not only detects influential image patterns but also uncovers the decisive features that drive the model's final predictions. By implementing our method, we can efficiently identify and visualise class-specific features leveraged by the data-driven model, providing insights into the decision-making processes of deep learning models. We validated our model in the demanding realm of medical prognosis task, demonstrating its efficacy and potential in enhancing the reliability of AI in healthcare and in discovering new knowledge in diseases where prognostic understanding is limited.