Interpretable deep learning analysis on correction of motion blur X-ray images to ensure the efficiency and reliability of clinical decisions

Abstract

Motion blur X-rays often lead to repeated imaging and extra radiation exposure. This study introduces an interpretable deep learning method to ensure AI prediction efficiency and reliability and uses the correction of motion blur X-ray images as a case study. A deep learning model that integrates Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) and EfficientNet-B3 is trained to correct motion-blurred images with interpretable analysis. ESRGAN corrects motion-blurred images and EfficientNet-B3 tackles the disease recognition. The accuracy on public datasets reaches 0.97 and clinical motion blur X-rays improves from 0.4 to 0.74 with an 85% increase. The results are analyzed using image quality metrics and interpretative methods to confirm the effectiveness and reliability of the proposed method. The proposed method ensures accuracy and reliability in disease recognition and improves the quality of X-ray images, which are verified with actual clinical data. This approach alleviates the workload of radiologists, reduces radiation exposure risks for patients, and holds promise for wider applications in medical imaging. To the best of our knowledge, this is the first study combining deep learning with interpretability to ensure the deblurring task of medical images with potential applications in CT and MRI.