Variational Autoencoders with a Structural Similarity Loss in Time of Flight MRAs

Kimberley Timmins, Irene van der Schaaf, BK Velthuis, Ynte Ruigrok, Hugo Kuijf

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Time-of-Flight Magnetic Resonance Angiographs (TOF-MRAs) enable visualization and analysis of cerebral arteries. This analysis may indicate normal variation of the configuration of the cerebrovascular system or vessel abnormalities, such as aneurysms. A model would be useful to represent normal cerebrovascular structure and variabilities in a healthy population and to differentiate from abnormalities. Current anomaly detection using autoencoding convolutional neural networks usually use a voxelwise mean-error for optimization. We propose optimizing a variational-autoencoder (VAE) with structural similarity loss (SSIM) for TOF-MRA reconstruction.
A patch-trained 2D fully-convolutional VAE was optimized for TOF-MRA reconstruction by comparing vessel segmentations of original and reconstructed MRAs. The method was trained and tested on two datasets: the IXI dataset, and a subset from the ADAM challenge. Both trained networks were tested on a dataset including subjects with aneurysms. We compared VAE optimization with L2-loss and SSIM-loss. Performance was evaluated between original and reconstructed MRAs using mean square error, mean-SSIM, peak-signal-to-noise-ratio and dice similarity index (DSI) of segmented vessels.
The L2-optimized VAE outperforms SSIM, with improved reconstruction metrics and DSIs for both datasets. Optimization using SSIM performed best for visual image quality, but with discrepancy in quantitative reconstruction and vascular segmentation. The IXI dataset had overall better performance, potentially due to the larger, more diverse training data. Reconstruction metrics, including SSIM, were lower for MRAs including aneurysms.
A SSIM-optimized VAE improved the visual perceptive image quality of TOF-MRA reconstructions. A L2-optimized VAE performed best for TOF-MRA reconstruction, where the vascular segmentation is important. SSIM is a potential metric for anomaly detection of MRAs.
Original languageEnglish
Title of host publicationProceedings SPIE 11596, Medical Imaging 2021: Image Processing, 115963A
Subtitle of host publicationImage Processing
EditorsIvana Isgum, Bennett A. Landman
PublisherSPIE
Volume11596
ISBN (Electronic)9781510640214
DOIs
Publication statusPublished - 15 Feb 2021

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume11596
ISSN (Print)1605-7422

Keywords

  • Angiography
  • Deep learning
  • Segmentation
  • Structural similarity

Fingerprint

Dive into the research topics of 'Variational Autoencoders with a Structural Similarity Loss in Time of Flight MRAs'. Together they form a unique fingerprint.

Cite this