Material Decomposition in Spectral CT Using Deep Learning: A Sim2Real Transfer Approach

IEEE Access

Thomas Broussaud¹  Nicolas Ducros¹  Simon Rit¹  Simon Arridge¹  Philippe C. Douek¹  Valeriya Pronina²  Juan F. P. J. Abascal²  Andreas Hauptmann²  Francoise Peyrin²  Suzanne Bussod²  Pierre-Antoine Rodesch² 

[1] Claude Bernard Lyon 1, UJM-Saint Etienne, CNRS, Inserm CREATIS UMR 5220, U1206, LYON, France;Univ Lyon, INSA-Lyon, Universit&x00E9;

关键词: Spectral CT;    inverse problem;    deep learning;    transfer learning;   

DOI  :  10.1109/ACCESS.2021.3056150

来源: DOAJ

【 摘 要 】

The state-of-the art for solving the nonlinear material decomposition problem in spectral computed tomography is based on variational methods, but these are computationally slow and critically depend on the particular choice of the regularization functional. Convolutional neural networks have been proposed for addressing these issues. However, learning algorithms require large amounts of experimental data sets. We propose a deep learning strategy for solving the material decomposition problem based on a U-Net architecture and a Sim2Real transfer learning approach where the knowledge that we learn from synthetic data is transferred to a real-world scenario. In order for this approach to work, synthetic data must be realistic and representative of the experimental data. For this purpose, numerical phantoms are generated from human CT volumes of the KiTS19 Challenge dataset, segmented into specific materials (soft tissue and bone). These volumes are projected into sinogram space in order to simulate photon counting data, taking into account the energy response of the scanner. We compared projection- and image-based decomposition approaches where the network is trained to decompose the materials either in the projection or in the image domain. The proposed Sim2Real transfer strategies are compared to a regularized Gauss-Newton (RGN) method on synthetic data, experimental phantom data and human thorax data.

【 授权许可】

Unknown