Slicer Networks

In medical imaging, scans often reveal objects with varied contrasts but consistent internal intensities or textures. This characteristic enables the use of low-frequency approximations for tasks such as segmentation and deformation field estimation. Yet, integrating this concept into neural network...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Zhang, Hang, Chen, Xiang, Wang, Rongguang, Hu, Renjiu, Liu, Dongdong, Li, Gaolei
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 18.01.2024
Subjects
Approximation
Blurring
Feature extraction
Feature maps
Image analysis
Image registration
Image segmentation
Medical imaging
Neural networks
Online AccessGet full text

Cover

More Information
Summary:In medical imaging, scans often reveal objects with varied contrasts but consistent internal intensities or textures. This characteristic enables the use of low-frequency approximations for tasks such as segmentation and deformation field estimation. Yet, integrating this concept into neural network architectures for medical image analysis remains underexplored. In this paper, we propose the Slicer Network, a novel architecture designed to leverage these traits. Comprising an encoder utilizing models like vision transformers for feature extraction and a slicer employing a learnable bilateral grid, the Slicer Network strategically refines and upsamples feature maps via a splatting-blurring-slicing process. This introduces an edge-preserving low-frequency approximation for the network outcome, effectively enlarging the effective receptive field. The enhancement not only reduces computational complexity but also boosts overall performance. Experiments across different medical imaging applications, including unsupervised and keypoints-based image registration and lesion segmentation, have verified the Slicer Network's improved accuracy and efficiency.
ISSN:2331-8422