Analysis of Learned Feature Similarities to Diagnostic Criteria in Deep Learning-Based 12-Lead ECG Classification

Information Science, Artificial Intelligence, Medicine, Medical Imaging, Cardiovascular System,
deep learning   ECG   explainable AI   feature attribution   atrial fibrillation   left bundle branch block   biosignal processing  

Interpretability Research of Deep Learning in Automated ECG Diagnosis —— Progress Overview Based on Explainable AI 1. Academic Background and Problem Statement Electrocardiogram (ECG) is an important physiological signal acquisition method for clinical diagnosis of heart diseases, with a history of over a hundred years. In recent years, with the ra...

Towards Boosting Out-of-Distribution Detection from a Spatial Feature Importance Perspective

Information Science, Artificial Intelligence,
out-of-distribution detection   spatial feature   AI safety   feature attribution   model reliability  

Boosting Out-of-Distribution Detection Performance from the Perspective of Spatial Feature Importance Research Background and Problem Statement In practical applications of deep learning models, ensuring that models can reliably reject predictions when faced with inputs from unknown categories is crucial for system safety and robustness. This need ...