all AI news
Differentiable Topology-Preserved Distance Transform for Pulmonary Airway Segmentation. (arXiv:2209.08355v1 [cs.CV])
cs.CV updates on arXiv.org arxiv.org
Detailed pulmonary airway segmentation is a clinically important task for
endobronchial intervention and treatment of peripheral lung cancer lesions.
Convolutional Neural Networks (CNNs) are promising tools for medical image
analysis but have been performing poorly for cases when there is a
significantly imbalanced feature distribution, which is true for the airway
data as the trachea and principal bronchi dominate most of the voxels whereas
the lobar bronchi and distal segmental bronchi occupy only a small proportion.
In this paper, we …