View it like a radiologist: Shifted windows for deep learning augmentation of CT images

Abstract

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.

arXiv comment6 pages, 3 figures, accepted to MLSP 2023

References in corpus (6)

• Automated Design of Deep Learning Methods for Biomedical Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• The Medical Segmentation Decathlon
• The Liver Tumor Segmentation Benchmark (LiTS)
• Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method
• Domain specific cues improve robustness of deep learning based segmentation of ct volumes