A Neural Network Approach for Image Reconstruction from a Single X-Ray Projection

Samiha Rouf, Chenyang Shen, Yan Cao, Conner Davis, Xun Jia, Yifei Lou

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Time-resolved imaging becomes popular in radiotherapy in that it significantly reduces blurring artifacts in volumetric images reconstructed from a set of 2D X-ray projection data. We aim at developing a neural network (NN) based machine learning algorithm that allows for reconstructing an instantaneous image from a single projection. In our approach, each volumetric image is represented as a deformation of a chosen reference image, in which the deformation is modeled as a linear combination of a few basis functions through principal component analysis (PCA). Based on this PCA deformation model, we train an ensemble of neural networks to find a mapping from a projection image to PCA coefficients. For image reconstruction, we apply the learned mapping on an instantaneous projection image to obtain the PCA coefficients, thus getting a deformation. Then, a volumetric image can be reconstructed by applying the deformation on the reference image. Experimentally, we show promising results on a set of simulated data.

Original languageEnglish (US)
Title of host publicationMedical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings
EditorsYalin Zheng, Bryan M. Williams, Ke Chen
PublisherSpringer
Pages208-219
Number of pages12
ISBN (Print)9783030393427
DOIs
StatePublished - Jan 1 2020
Event23rd Conference on Medical Image Understanding and Analysis, MIUA 2019 - Liverpool, United Kingdom
Duration: Jul 24 2019Jul 26 2019

Publication series

NameCommunications in Computer and Information Science
Volume1065 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference23rd Conference on Medical Image Understanding and Analysis, MIUA 2019
CountryUnited Kingdom
CityLiverpool
Period7/24/197/26/19

Keywords

  • Neural network
  • Principal component analysis
  • Time-resolved volumetric imaging
  • X-ray projection

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'A Neural Network Approach for Image Reconstruction from a Single X-Ray Projection'. Together they form a unique fingerprint.

  • Cite this

    Rouf, S., Shen, C., Cao, Y., Davis, C., Jia, X., & Lou, Y. (2020). A Neural Network Approach for Image Reconstruction from a Single X-Ray Projection. In Y. Zheng, B. M. Williams, & K. Chen (Eds.), Medical Image Understanding and Analysis - 23rd Conference, MIUA 2019, Proceedings (pp. 208-219). (Communications in Computer and Information Science; Vol. 1065 CCIS). Springer. https://doi.org/10.1007/978-3-030-39343-4_18