Automatic kidney segmentation in ultrasound images using subsequent boundary distance regression and pixelwise classification networks
This work addresses the challenge of accurate kidney segmentation in clinical ultrasound images, which is crucial for medical diagnosis, but it is incremental as it builds on existing deep learning techniques.
The authors tackled automatic kidney segmentation in ultrasound images by proposing a method using boundary distance regression and pixel classification networks, achieving significant performance improvements over existing deep learning-based pixel classification networks.
It remains challenging to automatically segment kidneys in clinical ultrasound (US) images due to the kidneys' varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we propose subsequent boundary distance regression and pixel classification networks to segment the kidneys, informed by the fact that the kidney boundaries have relatively homogenous texture patterns across images. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from US images, then these features are used as input to learn kidney boundary distance maps using a boundary distance regression network, and finally the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixel classification network in an end-to-end learning fashion. We also adopted a data-augmentation method based on kidney shape registration to generate enriched training data from a small number of US images with manually segmented kidney labels. Experimental results have demonstrated that our method could effectively improve the performance of automatic kidney segmentation, significantly better than deep learning-based pixel classification networks.