Weight Encode Reconstruction Network for Computed Tomography in a Semi-Case-Wise and Learning-Based Way

by   Hujie Pan, et al.

Classic algebraic reconstruction technology (ART) for computed tomography requires pre-determined weights of the voxels for projecting pixel values. However, such weight cannot be accurately obtained due to the limitation of the physical understanding and computation resources. In this study, we propose a semi-case-wise learning-based method named Weight Encode Reconstruction Network (WERNet) to tackle the issues mentioned above. The model is trained in a self-supervised manner without the label of a voxel set. It contains two branches, including the voxel weight encoder and the voxel attention part. Using gradient normalization, we are able to co-train the encoder and voxel set numerically stably. With WERNet, the reconstructed result was obtained with a cosine similarity greater than 0.999 with the ground truth. Moreover, the model shows the extraordinary capability of denoising comparing to the classic ART method. In the generalization test of the model, the encoder is transferable from a voxel set with complex structure to the unseen cases without the deduction of the accuracy.


page 5

page 9

page 10


Self-Supervised Learning for Physiologically-Based Pharmacokinetic Modeling in Dynamic PET

Dynamic positron emission tomography imaging (dPET) provides temporally ...

An Unsupervised Learning Model for Medical Image Segmentation

For the majority of the learning-based segmentation methods, a large qua...

Computed tomography coronary angiogram images, annotations and associated data of normal and diseased arteries

Computed Tomography Coronary Angiography (CTCA) is a non-invasive method...

SnakeVoxFormer: Transformer-based Single Image Voxel Reconstruction with Run Length Encoding

Deep learning-based 3D object reconstruction has achieved unprecedented ...

Learning Multi-Modal Volumetric Prostate Registration with Weak Inter-Subject Spatial Correspondence

Recent studies demonstrated the eligibility of convolutional neural netw...

Unsupervised 4D LiDAR Moving Object Segmentation in Stationary Settings with Multivariate Occupancy Time Series

In this work, we address the problem of unsupervised moving object segme...

Cutting Voxel Projector a New Approach to Construct 3D Cone Beam CT Operator

In this paper, we introduce a new class of projectors for 3D cone beam t...

Please sign up or login with your details

Forgot password? Click here to reset