Share Email Print
cover

Proceedings Paper • new

The impact of MRI-CT registration errors on deep learning-based synthetic CT generation
Format Member Price Non-Member Price
PDF $17.00 $21.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Purpose To investigate the impact of image registration on deep learning-based synthetic CT (sCT) generation. Methods Paired MR images and CT scans of the pelvic region of radiotherapy patients were obtained and non-rigidly registered. After a manual verification of the registrations, the dataset was split into two groups containing either well-registered or poorly-registered MR-CT pairs. In three scenarios, a patch-based U-Net deep learning architecture was trained for sCT generation on (i) exclusively well-registered data, (ii) mixtures of well-registered and poorly-registered data or on (iii) poorly-registered data only. Furthermore, a failure case was designed by introducing a single misregistered subject in the training set of six well-registered subjects. Reconstruction quality was assessed using mean absolute error (MAE) in the entire body and specifically in bone and Dice similarity coefficient (DSC) evaluated cortical bone geometric fidelity. Results The model trained on well registered data had an average MAE of 27.6 ± 2.6HU on the entire body contour and 79.1 ± 16.1HU on the bone. The average cortical bone DSC was 0.89. When patients with registration errors were added to the training, MAE’s were higher and DSC lower with variations by up to 36HU for the average MAEbone. The failure mode demonstrated the potential far-reaching consequences of a single misregistered subject in the training set with variations by up to 38HU for MAEbone. Conclusion Poor registration quality of the training set had a negative impact on paired, deep learning-based sCT generation. Notably, as low as one poorly-registered MR-CT pair in the training phase was capable of drastically altering a model.

Paper Details

Date Published: 15 March 2019
PDF: 7 pages
Proc. SPIE 10949, Medical Imaging 2019: Image Processing, 1094938 (15 March 2019); doi: 10.1117/12.2512747
Show Author Affiliations
Mateusz C. Florkow, Univ. Medical Ctr. Utrecht (Netherlands)
Frank Zijlstra, Univ. Medical Ctr. Utrecht (Netherlands)
Linda G. W. Kerkmeijer M.D., Univ. Medical Ctr. Utrecht (Netherlands)
Matteo Maspero, Univ. Medical Ctr. Utrecht (Netherlands)
Cornelis A. T. van den Berg, Univ. Medical Ctr. Utrecht (Netherlands)
Marijn van Stralen, Univ. Medical Ctr. Utrecht (Netherlands)
MRIguidance B. V. (Netherlands)
Peter R. Seevinck, Univ. Medical Ctr. Utrecht (Netherlands)


Published in SPIE Proceedings Vol. 10949:
Medical Imaging 2019: Image Processing
Elsa D. Angelini; Bennett A. Landman, Editor(s)

© SPIE. Terms of Use
Back to Top