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


An Unsupervised Learning Model for Medical Image Segmentation

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

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

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

Photoacoustic Image Reconstruction Beyond Supervised to Compensate Limit-view and Remove Artifacts

Photoacoustic computed tomography (PACT) reconstructs the initial pressu...

Numerically robust tetrahedron-based tomographic forward and backward projectors on parallel architectures

X-ray tomographic reconstruction typically uses voxel basis functions to...

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...

Alternating Minimization Algorithm with Automatic Relevance Determination for Transmission Tomography under Poisson Noise

We propose a globally convergent alternating minimization (AM) algorithm...

Fast Hybrid Cascade for Voxel-based 3D Object Classification

Voxel-based 3D object classification has been frequently studied in rece...