NA-MIC Project Weeks

Back to Projects List

Synthetic CT evaluation

Key Investigators

• Paolo Zaffino (Magna Graecia University of Catanzaro, Italy)
• Maria Francesca Spadea (Magna Graecia University of Catanzaro, Italy)
• Everyone else wants to join

Project Description

Several algorithms for MRI to synthetic CT have been proposed. Each group quantifies conversion accuracy in different ways, making difficult to compare algorithms. We want to create a Slicer module for stardazied conversion accuracy assessment.

Objective

1. Implement in 3D Slicer the validation workflow proposed in Spadea, M.F., Pileggi, G., Zaffino, P., Salome, P., Catana, C., Izquierdo-Garcia, D., Amato, F. and Seco, J., 2019. Deep Convolution Neural Network (DCNN) Multiplane Approach to Synthetic CT Generation From MR images—Application in Brain Proton Therapy. International Journal of Radiation Oncology* Biology* Physics, 105(3), pp.495-503.

Approach and Plan

1. Write an extension that will quantify conversion accuracy. The code will be written in python.

Progress and Next Steps

1. The extension “ImageCompare” was created. For the moment is contains just a module for synthetic CT evaluation. More modules could be add later.

2. The extension in already available in the nigthly build (thanks JC and Andras!)

Illustrations

Background and References

1. Spadea, M.F., Pileggi, G., Zaffino, P., Salome, P., Catana, C., Izquierdo-Garcia, D., Amato, F. and Seco, J., 2019. Deep Convolution Neural Network (DCNN) Multiplane Approach to Synthetic CT Generation From MR images—Application in Brain Proton Therapy. International Journal of Radiation Oncology* Biology* Physics, 105(3), pp.495-503.

2. https://github.com/pzaffino/SlicerImageCompare

3. https://www.slicer.org/wiki/Documentation/Nightly/Extensions/ImageCompare