Deep learning-enabled quantification of simultaneous PET/MRI for cell transplantation monitoring

Hasaan Hayat; Rui Wang; Aixia Sun; Christiane L Mallett; Saumya Nigam; Nathan Redman; Demarcus Bunn; Elvira Gjelaj; Nazanin Talebloo; Adam Alessio; Anna Moore; Kurt Zinn; Guo-Wei Wei; Jinda Fan; Ping Wang

doi:10.1016/j.isci.2023.107083

Deep learning-enabled quantification of simultaneous PET/MRI for cell transplantation monitoring

iScience. 2023 Jun 9;26(7):107083. doi: 10.1016/j.isci.2023.107083. eCollection 2023 Jul 21.

Authors

Hasaan Hayat^{1

2

3}, Rui Wang⁴, Aixia Sun^{1

2}, Christiane L Mallett^{2

5}, Saumya Nigam^{1

2}, Nathan Redman^{5

6}, Demarcus Bunn^{5

6}, Elvira Gjelaj^{1

7}, Nazanin Talebloo^{1

8}, Adam Alessio^{2

5

6

9}, Anna Moore^{1

2}, Kurt Zinn^{2

5}, Guo-Wei Wei^{4

9

10}, Jinda Fan^{2

5

8}, Ping Wang^{1

2}

Affiliations

¹ Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA.
² Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA.
³ College of Human Medicine, Michigan State University, East Lansing, MI, USA.
⁴ Department of Mathematics, College of Natural Science, Michigan State University, East Lansing, MI, USA.
⁵ Institute for Quantitative Health Science and Engineering, Department of Biomedical Engineering, Michigan State University, East Lansing, MI, USA.
⁶ Department of Biomedical Engineering, College of Engineering, Michigan State University, East Lansing, MI, USA.
⁷ Lyman Briggs College, Michigan State University, East Lansing, MI, USA.
⁸ Department of Chemistry, College of Natural Science, Michigan State University, East Lansing, MI, USA.
⁹ Departments of Computational Mathematics, Science, and Engineering (CMSE), College of Natural Science, Michigan State University, East Lansing, MI, USA.
¹⁰ Department of Electrical and Computer Engineering, College of Engineering, Michigan State University, East Lansing, MI, USA.

Abstract

Current methods of in vivo imaging islet cell transplants for diabetes using magnetic resonance imaging (MRI) are limited by their low sensitivity. Simultaneous positron emission tomography (PET)/MRI has greater sensitivity and ability to visualize cell metabolism. However, this dual-modality tool currently faces two major challenges for monitoring cells. Primarily, the dynamic conditions of PET such as signal decay and spatiotemporal change in radioactivity prevent accurate quantification of the transplanted cell number. In addition, selection bias from different radiologists renders human error in segmentation. This calls for the development of artificial intelligence algorithms for the automated analysis of PET/MRI of cell transplantations. Here, we combined K-means++ for segmentation with a convolutional neural network to predict radioactivity in cell-transplanted mouse models. This study provides a tool combining machine learning with a deep learning algorithm for monitoring islet cell transplantation through PET/MRI. It also unlocks a dynamic approach to automated segmentation and quantification of radioactivity in PET/MRI.

Keywords: Artificial intelligence applications; Cell biology.

Grants and funding

R01 AI164266/AI/NIAID NIH HHS/United States