LIME-RAY: What Does a Neural Network See from X-Rays?

In the field of medical imaging, neural networks have significantly enhanced the analysis and interpretation of X-ray images, providing advanced capabilities in detecting patterns and anomalies. Despite their potential, challenges remain, particularly concerning the interpretability and reliability of these models. The LIME-RAY approach addresses these challenges by integrating Convolutional Neural Networks (CNN) with Long Short- Term Memory (LSTM) networks. This hybrid technique leverages CNNs for spatial feature extraction and LSTMs for temporal pattern recognition, improving the accuracy and interpretability of the model's predictions. Furthermore, Local Interpretable Model-agnostic Explanations (LIME) are used to provide transparent, interpretable results, crucial for gaining the trust of healthcare professionals. Our approach is validated using a diverse dataset of chest X-rays, including cases of Covid-19, Pneumonia, and Tuberculosis. The proposed method demonstrates superior performance in multi-class disease classification and offers valuable insights into the decision-making process, bridging the gap between complex neural network models and practical healthcare applications.