Jonathan Fisher

All Publications

• Generative deep learning synthesizes high signal-to-noise ratio sensitivity maps for PET from low count direct normalization data. Physics in medicine and biology Jafaritadi, M., Groll, A., Chin, M., Chinn, G., Fisher, J., Innes, D. R., Levin, C. S. 2026

  Abstract

  An accurate and precise normalization procedure is essential to correct for variations in detector efficiency in reconstructed positron emission tomography (PET) images. Direct normalization is a conventional approach that requires a large number of counts per line of response (LOR) from a known normalization source, which is time-consuming due to the use of relatively low-activity sources. We present a deep learning framework that generates high signal-to-noise ratio (SNR) normalization factors and sensitivity maps from low-count direct normalization data acquired with a PET insert for MRI. We developed an attention-guided Pix2Pix, a conditional generative adversarial network (cGAN), to maximize detector efficiencies and remove detector block patterns and associated ring artifacts in the resulting PET images. Quantitative evaluations were performed by testing the model on the unseen direct normalization data to reconstruct images of a Hoffman brain phantom, a contrast phantom, and a uniform cylinder phantom using high-count, low-count (1-15% of full scan), and synthetic high-count sensitivity maps. The Hoffman brain image volume normalized using a synthetic sensitivity map with 15% count statistics as input produced results that closely matched that using the high count normalization data, with peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and normalized root mean square error (NRMSE) values (mean±standard error) of 30.68±0.31, 0.95±0.002, and 0.35±0.003, respectively. In comparison, the unprocessed sensitivity map with 15% count statistics yielded substantially worse PSNR, SSIM, and NRMSE values of 15.93±0.426, 0.54±0.013, and 1.843±0.0280, respectively. This novel, fast, and effective approach enables high SNR direct normalization of PET image volumes through deep learning using synthetic correction factors obtained from a short normalization scan.

  View details for DOI 10.1088/1361-6560/ae3ec6

  View details for PubMedID 41604704

• Image SNR Enhancement for a Short Axial FOV Brain PET System Using Generative Deep Learning IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES Nazari-Farsani, S., Jafaritadi, M., Fisher, J., Chin, M., Chinn, G., Khalighi, M., Zaharchuk, G., Levin, C. S. 2026; 10 (1): 41-50

  View details for DOI 10.1109/TRPMS.2025.3560667

  View details for Web of Science ID 001652366100006

• Pseudo CT Image Synthesis and Bone Segmentation From MR Images Using Adversarial Networks With Residual Blocks for MR-Based Attenuation Correction of Brain PET Data IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES Tao, L., Fisher, J., Anaya, E., Li, X., Levin, C. S. 2021; 5 (2): 193–201

  View details for DOI 10.1109/TRPMS.2020.2989073

  View details for Web of Science ID 000626319500004

• Motion Correction for Simultaneous PET/MR Brain Imaging Using a Radiofrequency-Penetrable PET Insert. Fisher, J., Groll, A., Levin, C. SOC NUCLEAR MEDICINE INC. 2020

  View details for Web of Science ID 000568290500327

• Motion Correction for Simultaneous PET/MR Brain Imaging Using a RF-Penetrable PET Insert Fisher, J., Groll, A., Levin, C. S., IEEE IEEE. 2019

  View details for Web of Science ID 000569982800245

• Application of Conditional Adversarial Networks for Automatic Generation of MR-based Attenuation Map in PET/MR Tao, L., Li, X., Fisher, J., Levin, C. S., IEEE IEEE. 2018

  View details for Web of Science ID 000601256000178