1
|
Hayat H, Wang R, Sun A, Mallett CL, Nigam S, Redman N, Bunn D, Gjelaj E, Talebloo N, Alessio A, Moore A, Zinn K, Wei GW, Fan J, Wang P. Deep learning-enabled quantification of simultaneous PET/MRI for cell transplantation monitoring. iScience 2023; 26:107083. [PMID: 37416468 PMCID: PMC10319838 DOI: 10.1016/j.isci.2023.107083] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2022] [Revised: 02/10/2023] [Accepted: 06/06/2023] [Indexed: 07/08/2023] Open
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.
Collapse
Affiliation(s)
- Hasaan Hayat
- Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
- College of Human Medicine, Michigan State University, East Lansing, MI, USA
| | - Rui Wang
- Department of Mathematics, College of Natural Science, Michigan State University, East Lansing, MI, USA
| | - Aixia Sun
- Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
| | - Christiane L. Mallett
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
- Institute for Quantitative Health Science and Engineering, Department of Biomedical Engineering, Michigan State University, East Lansing, MI, USA
| | - Saumya Nigam
- Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
| | - Nathan Redman
- Institute for Quantitative Health Science and Engineering, Department of Biomedical Engineering, Michigan State University, East Lansing, MI, USA
- Department of Biomedical Engineering, College of Engineering, Michigan State University, East Lansing, MI, USA
| | - Demarcus Bunn
- Institute for Quantitative Health Science and Engineering, Department of Biomedical Engineering, Michigan State University, East Lansing, MI, USA
- Department of Biomedical Engineering, College of Engineering, Michigan State University, East Lansing, MI, USA
| | - Elvira Gjelaj
- Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA
- Lyman Briggs College, Michigan State University, East Lansing, MI, USA
| | - Nazanin Talebloo
- Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA
- Department of Chemistry, College of Natural Science, Michigan State University, East Lansing, MI, USA
| | - Adam Alessio
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
- Institute for Quantitative Health Science and Engineering, Department of Biomedical Engineering, Michigan State University, East Lansing, MI, USA
- Department of Biomedical Engineering, College of Engineering, Michigan State University, East Lansing, MI, USA
- Departments of Computational Mathematics, Science, and Engineering (CMSE), College of Natural Science, Michigan State University, East Lansing, MI, USA
| | - Anna Moore
- Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
| | - Kurt Zinn
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
- Institute for Quantitative Health Science and Engineering, Department of Biomedical Engineering, Michigan State University, East Lansing, MI, USA
| | - Guo-Wei Wei
- Department of Mathematics, College of Natural Science, Michigan State University, East Lansing, MI, USA
- Departments of Computational Mathematics, Science, and Engineering (CMSE), College of Natural Science, Michigan State University, East Lansing, MI, USA
- Department of Electrical and Computer Engineering, College of Engineering, Michigan State University, East Lansing, MI, USA
| | - Jinda Fan
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
- Institute for Quantitative Health Science and Engineering, Department of Biomedical Engineering, Michigan State University, East Lansing, MI, USA
- Department of Chemistry, College of Natural Science, Michigan State University, East Lansing, MI, USA
| | - Ping Wang
- Precision Health Program, Michigan State University, 766 Service Road, Rm. 2020, East Lansing, MI 48823, USA
- Department of Radiology, College of Human Medicine, Michigan State University, East Lansing, MI, USA
| |
Collapse
|
2
|
van den Wyngaert T, de Schepper S, Elvas F, Seyedinia SS, Beheshti M. Positron emission tomography-magnetic resonance imaging as a research tool in musculoskeletal conditions. THE QUARTERLY JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING : OFFICIAL PUBLICATION OF THE ITALIAN ASSOCIATION OF NUCLEAR MEDICINE (AIMN) [AND] THE INTERNATIONAL ASSOCIATION OF RADIOPHARMACOLOGY (IAR), [AND] SECTION OF THE SOCIETY OF... 2022; 66:15-30. [PMID: 35005878 DOI: 10.23736/s1824-4785.22.03434-3] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/14/2023]
Abstract
Compared to positron emission tomography/computed tomography (PET/CT), the uptake of PET- magnetic resonance imaging (MRI) has been slow, even more so in clinical practice compared to the (pre-)clinical research setting. However, for applications in musculoskeletal (MSK) research, the combination of PET and MRI into a single modality offers attractive advantages over other imaging modalities. Most importantly, MRI has exquisite soft-tissue detail without the use of contrast agents or ionizing radiation, superior bone marrow visualization, and an extensive spectrum of distinct multiparametric assessment methods. In the preclinical setting, the introduction of PET inserts for small-animal MRI machines has proven to be a successful concept in bringing this technology to the lab. Initial hurdles in quantification have been mainly overcome in this setting. In parallel, a promising range of radiochemistry techniques has been developed to create multimodality probes that offer the possibility of simultaneously querying different metabolic pathways. Not only will these applications help in elucidating disease mechanisms, but they can also facilitate drug development. The clinical applications of PET/MRI in MSK are still limited, but encouraging initial results with novel radiotracers suggest a high potential for use in various MSK conditions, including osteoarthritis, rheumatoid arthritis, ankylosing spondylitis and inflammation and infection. Further innovations will be required to bring down the cost of PET/MRI to justify a broader clinical implementation, and remaining issues with quality control and standardization also need to be addressed. Nevertheless, PET/MRI is a powerful platform for MSK research with distinct qualities that are not offered by other techniques.
Collapse
Affiliation(s)
- Tim van den Wyngaert
- Department of Nuclear Medicine, Antwerp University Hospital, Edegem, Belgium -
- Faculty of Medicine and Health Sciences (MICA), University of Antwerp, Wilrijk, Belgium -
- Integrated Personalized and Precision Oncology Network (IPPON), University of Antwerp, Wilrijk, Belgium -
| | - Stijn de Schepper
- Department of Nuclear Medicine, Antwerp University Hospital, Edegem, Belgium
- Faculty of Medicine and Health Sciences (MICA), University of Antwerp, Wilrijk, Belgium
| | - Filipe Elvas
- Department of Nuclear Medicine, Antwerp University Hospital, Edegem, Belgium
- Faculty of Medicine and Health Sciences (MICA), University of Antwerp, Wilrijk, Belgium
| | - Seyedeh S Seyedinia
- Division of Molecular Imaging and Theranostics, Department of Nuclear Medicine and Endocrinology, University Hospital Salzburg, Paracelsus Medical University, Salzburg, Austria
| | - Mohsen Beheshti
- Division of Molecular Imaging and Theranostics, Department of Nuclear Medicine and Endocrinology, University Hospital Salzburg, Paracelsus Medical University, Salzburg, Austria
| |
Collapse
|
5
|
Oldan JD, Shah SN, Brunken RC, DiFilippo FP, Obuchowski NA, Bolen MA. Do myocardial PET-MR and PET-CT FDG images provide comparable information? J Nucl Cardiol 2016; 23:1102-1109. [PMID: 26071114 DOI: 10.1007/s12350-015-0159-7] [Citation(s) in RCA: 17] [Impact Index Per Article: 2.1] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2015] [Accepted: 04/11/2015] [Indexed: 02/05/2023]
Abstract
INTRODUCTION Although positron emission tomography PET-MR imaging is emerging into clinical practice, many aspects of this imaging technique such as attenuation correction have yet to be validated for myocardial imaging. Thus, it is uncertain whether PET-MR FDG images provide clinical information which is comparable to PET-CT FDG images. The study goal was to systematically compare relative myocardial FDG concentrations obtained from cardiac PET-MR images to those derived from same day PET-CT images. METHODS Myocardial FDG images of 27 patients undergoing PET-CT imaging, followed by PET-MR imaging 42 ± 13 minutes later as part of a prospective oncology study were analyzed. Mean segmental standardized uptake measurements (SUVmean) were obtained in each of the 17 standard myocardial segments and normalized to the brightest segment. RESULTS Normalized segmental SUVmean values did not differ significantly between the PET-MR and PET-CT images (mean difference 0.002, P = .826). The specific segment was a marginally significant predictor of the differences (P = .057), with the largest difference in the anteroseptal basal segment. CONCLUSIONS PET-MR, vis-à-vis PET-CT, does not significantly raise segmental uptake relative to the brightest segment, suggesting that PET-MR can be used similarly to PET-CT for applications where relative uptake is important.
Collapse
Affiliation(s)
- Jorge D Oldan
- Department of Cardiovascular Imaging, Cleveland Clinic Foundation, 9500 Euclid Ave.-J14, Cleveland, OH, 44195, USA.
| | - Shetal N Shah
- Departments of Radiology and Nuclear Medicine, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Richard C Brunken
- Department of Nuclear Medicine, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Frank P DiFilippo
- Department of Nuclear Medicine, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Nancy A Obuchowski
- Department of Quantitative Health Sciences, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Michael A Bolen
- Department of Cardiovascular Imaging, Cleveland Clinic Foundation, 9500 Euclid Ave.-J14, Cleveland, OH, 44195, USA
| |
Collapse
|
6
|
Wehrl HF, Wiehr S, Divine MR, Gatidis S, Gullberg GT, Maier FC, Rolle AM, Schwenck J, Thaiss WM, Pichler BJ. Preclinical and Translational PET/MR Imaging. J Nucl Med 2014; 55:11S-18S. [PMID: 24833493 DOI: 10.2967/jnumed.113.129221] [Citation(s) in RCA: 50] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022] Open
Abstract
Combined PET and MR imaging (PET/MR imaging) has progressed tremendously in recent years. The focus of current research has shifted from technologic challenges to the application of this new multimodal imaging technology in the areas of oncology, cardiology, neurology, and infectious diseases. This article reviews studies in preclinical and clinical translation. The common theme of these initial results is the complementary nature of combined PET/MR imaging that often provides additional insights into biologic systems that were not clearly feasible with just one modality alone. However, in vivo findings require ex vivo validation. Combined PET/MR imaging also triggers a multitude of new developments in image analysis that are aimed at merging and using multimodal information that ranges from better tumor characterization to analysis of metabolic brain networks. The combination of connectomics information that maps brain networks derived from multiparametric MR data with metabolic information from PET can even lead to the formation of a new research field that we would call cometomics that would map functional and metabolic brain networks. These new methodologic developments also call for more multidisciplinarity in the field of molecular imaging, in which close interaction and training among clinicians and a variety of scientists is needed.
Collapse
Affiliation(s)
- Hans F Wehrl
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Stefan Wiehr
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Mathew R Divine
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Sergios Gatidis
- Department of Diagnostic and Interventional Radiology, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Grant T Gullberg
- Department of Radiotracer Development and Imaging Technology, Ernest Orlando Lawrence Berkeley National Laboratory, Berkeley, California Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, California; and
| | - Florian C Maier
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Anna-Maria Rolle
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Johannes Schwenck
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany Department of Nuclear Medicine, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Wolfgang M Thaiss
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany Department of Diagnostic and Interventional Radiology, Eberhard Karls University Tuebingen, Tuebingen, Germany
| | - Bernd J Pichler
- Werner Siemens Imaging Center, Department for Preclinical Imaging and Radiopharmacy, Eberhard Karls University Tuebingen, Tuebingen, Germany
| |
Collapse
|
8
|
Jadvar H, Colletti PM. Competitive advantage of PET/MRI. Eur J Radiol 2013; 83:84-94. [PMID: 23791129 DOI: 10.1016/j.ejrad.2013.05.028] [Citation(s) in RCA: 92] [Impact Index Per Article: 8.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2013] [Revised: 05/20/2013] [Accepted: 05/20/2013] [Indexed: 02/08/2023]
Abstract
Multimodality imaging has made great strides in the imaging evaluation of patients with a variety of diseases. Positron emission tomography/computed tomography (PET/CT) is now established as the imaging modality of choice in many clinical conditions, particularly in oncology. While the initial development of combined PET/magnetic resonance imaging (PET/MRI) was in the preclinical arena, hybrid PET/MR scanners are now available for clinical use. PET/MRI combines the unique features of MRI including excellent soft tissue contrast, diffusion-weighted imaging, dynamic contrast-enhanced imaging, fMRI and other specialized sequences as well as MR spectroscopy with the quantitative physiologic information that is provided by PET. Most evidence for the potential clinical utility of PET/MRI is based on studies performed with side-by-side comparison or software-fused MRI and PET images. Data on distinctive utility of hybrid PET/MRI are rapidly emerging. There are potential competitive advantages of PET/MRI over PET/CT. In general, PET/MRI may be preferred over PET/CT where the unique features of MRI provide more robust imaging evaluation in certain clinical settings. The exact role and potential utility of simultaneous data acquisition in specific research and clinical settings will need to be defined. It may be that simultaneous PET/MRI will be best suited for clinical situations that are disease-specific, organ-specific, related to diseases of the children or in those patients undergoing repeated imaging for whom cumulative radiation dose must be kept as low as reasonably achievable. PET/MRI also offers interesting opportunities for use of dual modality probes. Upon clear definition of clinical utility, other important and practical issues related to business operational model, clinical workflow and reimbursement will also be resolved.
Collapse
Affiliation(s)
- Hossein Jadvar
- Division of Nuclear Medicine, Department of Radiology, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA.
| | - Patrick M Colletti
- Division of Nuclear Medicine, Department of Radiology, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA
| |
Collapse
|