Share Email Print

Proceedings Paper

On the impact of input feature selection in deep scatter estimation for positron emission tomography
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Deep scatter estimation (DSE) for X-ray computed tomography or positron emission tomography (PET) uses convolutional neural networks (CNNs) to estimate scatter distributions. We investigate the impact of physically motivated transformations and combinations of emission and attenuation input features on PET-DSE performance. Therefore, we decompose the analytical expression of a convolutional scatter model into different feature sets as a function of measured prompts and attenuation correction factors, and propose to use individual attenuation sinograms of central slabs and peripheral regions. Data from 20 patients ( 71 bed positions, 17 892 direct views) were collected and used to train CNNs to estimate the single scatter simulation (SSS) from various feature sets. Adding redundant attenuation features improved the convergence of validation metrics. Slab-wise attenuation sinograms improved training mean absolute errors by 10% and early-epoch validation metrics, yet without improvement in later epochs. In conclusion, physically motivated transformation of input features can help improve training and estimation performance in PET-DSE.

Paper Details

Date Published: 28 May 2019
PDF: 5 pages
Proc. SPIE 11072, 15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine, 110720S (28 May 2019); doi: 10.1117/12.2534281
Show Author Affiliations
Yannick Berker, Deutsches Krebsforschungszentrum (Germany)
Marc Kachelrieß, Deutsches Krebsforschungszentrum (Germany)

Published in SPIE Proceedings Vol. 11072:
15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine
Samuel Matej; Scott D. Metzler, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?