View it like a radiologist: Shifted windows for deep learning augmentation of CT images
This work addresses a domain-specific problem for medical imaging by enhancing segmentation accuracy in CT scans, though it is incremental as it builds on existing augmentation methods.
The paper tackled the problem of deep learning models using inappropriate augmentation techniques for medical CT images by proposing a novel preprocessing and intensity augmentation scheme called window shifting, which improved liver lesion segmentation performance and robustness on multiple datasets.
Deep learning has the potential to revolutionize medical practice by automating and performing important tasks like detecting and delineating the size and locations of cancers in medical images. However, most deep learning models rely on augmentation techniques that treat medical images as natural images. For contrast-enhanced Computed Tomography (CT) images in particular, the signals producing the voxel intensities have physical meaning, which is lost during preprocessing and augmentation when treating such images as natural images. To address this, we propose a novel preprocessing and intensity augmentation scheme inspired by how radiologists leverage multiple viewing windows when evaluating CT images. Our proposed method, window shifting, randomly places the viewing windows around the region of interest during training. This approach improves liver lesion segmentation performance and robustness on images with poorly timed contrast agent. Our method outperforms classical intensity augmentations as well as the intensity augmentation pipeline of the popular nn-UNet on multiple datasets.