Tomographic image reconstruction from incomplete data via a hybrid GAN

Ishak Ayad (1, 2) , Cécilia Tarpau (3, 4) , Mai K Nguyen (1)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
2 AGM - UMR 8088 - Analyse, Géométrie et Modélisation
3 Maxwell Institute for Mathematical Sciences
4 MATHEMATICS DEPARTMENT OF HERIOT-WATT UNIVERSITY - School of Mathematical and Computer Sciences

Limited data tomographic reconstruction has been widely used in medical imaging to reduce the radiation dose or shorten the data acquisition time. This is achieved by truncating the scanning angular range or increasing the angular sampling rate. However, the use of classical reconstruction methods with such incomplete data involves severe streaking artifacts, blurred edges, distorted boundaries, contrast loss, and decreased intensities in the reconstructed images. In this work, we propose a generative adversarial network made of a V-net generator with modified skip connections that simulates the algebraic reconstruction and a discriminator combining both information from the image and projection domains which only penalizes structure at the scale of image patches. The proposed method obtains promising results for data coming from both limitedangle and sparse-view projections, that is, data acquired from an angular range of 90 degrees and an angular sampling step of 10 degrees.

Domaines: Informatique [cs]; Mathématiques [math]; Physique [physics]

Ishak Ayad, Cécilia Tarpau, Mai K Nguyen. Tomographic image reconstruction from incomplete data via a hybrid GAN. Nuclear Science Symposium, Medical Imaging Conference and Room Temperature Semiconductor Detector Conference, Nov 2022, Milano, Italy. ⟨hal-03780132⟩