EVALUATION AND COMPARISON OF TWO DEEP-LEARNING STRATEGIES FOR ON-LINE X-RAY COMPUTED TOMOGRAPHY

Romain Vo (1, 2) , Julie Escoda (2) , Caroline Vienne (2) , Etienne Decencière (1)

1 CMM - Centre de Morphologie Mathématique
2 LIST (CEA) - Laboratoire d'Intégration des Systèmes et des Technologies

X-ray Computed Tomography (CT) has been increasingly used in many industrial domains for its unique capability of con- trolling both the integrity and dimensional conformity of parts. Still, it fails to be adopted as a standard technique for on-line mon- itoring due to its excessive cost in terms of acquisition time. The reduction of the number of projections, leading to the so-called sparse-view CT strategy, while maintaining a sufficient recon- struction quality is therefore one of the main challenges in this field. This work aims to evaluate and compare the performances of two deep learning strategies for the sparse-view reconstruction problem. As such, we propose an extensive study of these meth- ods, both in terms of data regime and angular sparsity during training. The two strategies present quantitative improvements over a classical FBP/FDK approach with a PSNR improvement varying between 11 and 16 dB (depending on the angular spar- sity) ; showing that efficient CT inspection can be performed from only few dozens of images

Domaines: Intelligence artificielle [cs.AI]

Romain Vo, Julie Escoda, Caroline Vienne, Etienne Decencière. EVALUATION AND COMPARISON OF TWO DEEP-LEARNING STRATEGIES FOR ON-LINE X-RAY COMPUTED TOMOGRAPHY. X-ray CT, reconstruction, sparse view, sinogram interpolation, reconstruction denoising, deep learning, con- volutional neural networks, Jul 2022, San diego (Californie), United States. ⟨hal-03933448⟩