Neural Network for Data Preprocessing in Computed Tomography

Autor:	Dmitry P. Nikolaev, Marina Chukalina, Alexey I. Chulichkov, A. V. Yamaev, Aleksander V. Sheshkus
Rok vydání:	2021
Předmět:	Tomographic reconstruction Artificial neural network Control and Systems Engineering Computer science Physics::Medical Physics Detector Metric (mathematics) Network performance Data pre-processing Electrical and Electronic Engineering Algorithm Synthetic data Convolution
Zdroj:	Automation and Remote Control. 82:1752-1762
ISSN:	1608-3032 0005-1179
DOI:	10.1134/s000511792110012x
Popis:	We propose a lightweight noise-canceling filtering neural network that implements the filtering stage in the algorithm for tomographic reconstruction of convolution and backprojection (Filtered BackProjection—FBP). We substantiate the neural network architecture, selected on the basis of the possibility of approximating the ramp filtering operation with sufficient accuracy. The network performance has been demonstrated using synthetic data that mimics low-exposure tomographic projections. The quantum nature of X-ray radiation, the exposure time of one frame, and the nonlinear response of the ionizing radiation detector are taken into account when generating the synthetic data. The reconstruction time using the proposed network is 11 times shorter than that of the heavy networks selected for comparison, with the reconstruction quality in the $$SSIM$$ metric above 0.9.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::5c7cfb279bdda9c52adde69fd9c3b0bd https://doi.org/10.1134/s000511792110012x Zobrazit plný text záznamu Plný text ve formátu PDF