MR-Based Attenuation Correction for Brain PET Using 3-D Cycle-Consistent Adversarial Network

Kuang Gong, Jaewon Yang, Peder E.Z. Larson, Spencer C. Behr, Thomas A. Hope, Youngho Seo, Quanzheng Li

Research output: Contribution to journalArticlepeer-review

15 Scopus citations

Abstract

Attenuation correction (AC) is important for the quantitative merits of positron emission tomography (PET). However, attenuation coefficients cannot be derived from magnetic resonance (MR) images directly for PET/MR systems. In this work, we aimed to derive continuous AC maps from Dixon MR images without the requirement of MR and computed tomography (CT) image registration. To achieve this, a 3-D generative adversarial network with both discriminative and cycle-consistency loss (Cycle-GAN) was developed. The modified 3-D U-net was employed as the structure of the generative networks to generate the pseudo-CT/MR images. The 3-D patch-based discriminative networks were used to distinguish the generated pseudo-CT/MR images from the true CT/MR images. To evaluate its performance, datasets from 32 patients were used in the experiment. The Dixon segmentation and atlas methods provided by the vendor and the convolutional neural network (CNN) method which utilized registered MR and CT images were employed as the reference methods. Dice coefficients of the pseudo-CT images and the regional quantification in the reconstructed PET images were compared. Results show that the Cycle-GAN framework can generate better AC compared to the Dixon segmentation and atlas methods, and shows comparable performance compared to the CNN method.

Original languageEnglish (US)
Article number9133147
Pages (from-to)185-192
Number of pages8
JournalIEEE Transactions on Radiation and Plasma Medical Sciences
Volume5
Issue number2
DOIs
StatePublished - Mar 2021
Externally publishedYes

Keywords

  • Attenuation correction (AC)
  • cycle consistency
  • generative adversarial network (GAN)
  • positron emission tomography (PET)

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging
  • Instrumentation

Fingerprint

Dive into the research topics of 'MR-Based Attenuation Correction for Brain PET Using 3-D Cycle-Consistent Adversarial Network'. Together they form a unique fingerprint.

Cite this