Higher Chest X-ray Resolution Improves Classification Performance
This addresses the need for better diagnostic accuracy in medical imaging for clinicians, though it is incremental as it focuses on optimizing an existing method for a known bottleneck.
The study tackled the problem of suboptimal chest X-ray classification due to low-resolution training images, finding that using a higher resolution of 1024 x 1024 pixels improved mean AUC to 84.2% compared to 82.7% at 256 x 256 pixels.
Deep learning models for image classification are often trained at a resolution of 224 x 224 pixels for historical and efficiency reasons. However, chest X-rays are acquired at a much higher resolution to display subtle pathologies. This study investigates the effect of training resolution on chest X-ray classification performance, using the chest X-ray 14 dataset. The results show that training with a higher image resolution, specifically 1024 x 1024 pixels, results in the best overall classification performance with a mean AUC of 84.2 % compared to 82.7 % when trained with 256 x 256 pixel images. Additionally, comparison of bounding boxes and GradCAM saliency maps suggest that low resolutions, such as 256 x 256 pixels, are insufficient for identifying small pathologies and force the model to use spurious discriminating features. Our code is publicly available at https://gitlab.lrz.de/IP/cxr-resolution