Synthesizing Multi-Tracer PET Images for Alzheimer's Disease Patients using a 3D Unified Anatomy-aware Cyclic Adversarial Network

Positron Emission Tomography (PET) is an important tool for studying Alzheimer’s disease (AD). PET scans can be used as diagnostics tools, and to provide molecular characterization of patients with cognitive disorders. However, multiple tracers are needed to measure glucose metabolism (F-FDG), synaptic vesicle protein (C-UCBJ), and β-amyloid (C-PiB). Administering multiple tracers to patient will lead to high radiation dose and cost. In addition, access to PET scans using new or less-available tracers with sophisticated production methods and short half-life isotopes may be very limited. Thus, it is desirable to develop an efficient multi-tracer PET synthesis model that can generate multi-tracer PET from single-tracer PET. Previous works on medical image synthesis focus on one-to-one fixed domain translations, and cannot simultaneously learn the feature from multi-tracer domains. Given 3 or more tracers, relying on previous methods will also create heavy burden on the number of models to be trained. To tackle these issues, we propose a 3D unified anatomy-aware cyclic adversarial network (UCAN) for translating multi-tracer PET volumes with one unified generative model, where MR with anatomical information is incorporated. Evaluations on a multi-tracer PET dataset demonstrate the feasibility that our UCAN can generate high-quality multi-tracer PET volumes, with NMSE less than 15% for all PET tracers. Our code is available at https://github.com/bbbbbbzhou/UCAN.

[1]  D. Spencer,et al.  Imaging synaptic density in the living human brain , 2016, Science Translational Medicine.

[2]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  W. Klunk,et al.  Imaging brain amyloid in Alzheimer's disease with Pittsburgh Compound‐B , 2004, Annals of neurology.

[4]  Apoorva Sikka,et al.  MRI to FDG-PET: Cross-Modal Synthesis Using 3D U-Net For Multi-Modal Alzheimer's Classification , 2018, SASHIMI@MICCAI.

[5]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[6]  Patrick Kwan,et al.  Treatment Outcomes in Patients With Newly Diagnosed Epilepsy Treated With Established and New Antiepileptic Drugs: A 30-Year Longitudinal Cohort Study , 2017, JAMA neurology.

[7]  Ann D. Cohen,et al.  Early detection of Alzheimer's disease using PiB and FDG PET , 2014, Neurobiology of Disease.

[8]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[9]  Michael A Yassa,et al.  Neuroimaging Biomarkers for Alzheimer’s Disease , 2019, Molecular Neurodegeneration.

[10]  John A. Onofrey,et al.  Generation of Synthetic PET Images of Synaptic Density and Amyloid from 18 F-FDG Images Using Deep Learning. , 2021, Medical Physics (Lancaster).

[11]  Ioannis Tsougos,et al.  SPECT and PET imaging in Alzheimer’s disease , 2018, Annals of Nuclear Medicine.

[12]  Farshad Falahati Asrami.  Neuroimaging biomarkers in Alzheimer’s disease , 2017 .

[13]  Jonathon Shlens,et al.  Conditional Image Synthesis with Auxiliary Classifier GANs , 2016, ICML.

[14]  Denise C. Park,et al.  Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease , 2011, Alzheimer's & Dementia.

[15]  Nassir Navab,et al.  Recalibrating Fully Convolutional Networks With Spatial and Channel “Squeeze and Excitation” Blocks , 2018, IEEE Transactions on Medical Imaging.

[16]  Thomas Brox,et al.  3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation , 2016, MICCAI.

[17]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Bo Zhou,et al.  Generation of Virtual Dual Energy Images from Standard Single-Shot Radiographs using Multi-scale and Conditional Adversarial Network , 2018, ACCV.