GuidedRec: Guiding Ill-Posed Unsupervised Volumetric Recovery
This could enable reduced radiation exposure in medical treatments like surgery and radiotherapy, but it is incremental as it builds on existing methods that use prior volumes.
The paper tackles the problem of reconstructing a 3D volume from only two planar projections in medical imaging by using a previously captured volume and a generative model to constrain deformations, outperforming state-of-the-art methods on a challenging dataset.
We introduce a novel unsupervised approach to reconstructing a 3D volume from only two planar projections that exploits a previous\-ly-captured 3D volume of the patient. Such volume is readily available in many important medical procedures and previous methods already used such a volume. Earlier methods that work by deforming this volume to match the projections typically fail when the number of projections is very low as the alignment becomes underconstrained. We show how to use a generative model of the volume structures to constrain the deformation and obtain a correct estimate. Moreover, our method is not bounded to a specific sensor calibration and can be applied to new calibrations without retraining. We evaluate our approach on a challenging dataset and show it outperforms state-of-the-art methods. As a result, our method could be used in treatment scenarios such as surgery and radiotherapy while drastically reducing patient radiation exposure.