4.7 Article

Mars Shot for Nuclear Medicine, Molecular Imaging, and Molecularly Targeted Radiopharmaceutical Therapy

期刊

JOURNAL OF NUCLEAR MEDICINE
卷 62, 期 1, 页码 6-14

出版社

SOC NUCLEAR MEDICINE INC
DOI: 10.2967/jnumed.120.253450

关键词

radiopharmaceutical therapy; artificial intelligence; theranostics; molecular imaging; neuroimaging

向作者/读者索取更多资源

The Society of Nuclear Medicine and Molecular Imaging's Value Initiative focuses on demonstrating the value of molecular imaging and molecularly targeted radiopharmaceutical therapy, with the research and discovery domain being crucial for advancing diagnostic and therapeutic nuclear medicine. Leaders have identified 5 broad areas of opportunity for future growth and clinical impact in this field.
The Society of Nuclear Medicine and Molecular Imaging created the Value Initiative in 2017 as a major component of its strategic plan to further demonstrate the value of molecular imaging and molecularly targeted radiopharmaceutical therapy to patients, physicians, payers, and funding agencies. The research and discovery domain, 1 of 5 under the Value Initiative, has a goal of advancing the research and development of diagnostic and therapeutic nuclear medicine. Research and discovery efforts and achievements are essential to ensure a bright future for NM and to translate science to practice. Given the remarkable progress in the field, leaders from the research and discovery domain and society councils identified 5 broad areas of opportunity with potential for substantive growth and clinical impact. This article discusses these 5 growth areas, identifying specific areas of particularly high importance for future study and development. As there was an understanding that goals should be both visionary yet achievable, this effort was called the Mars shot for nuclear medicine.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

Article Psychology, Clinical

Impaired self-awareness of cognitive deficits in Parkinson's disease relates to cingulate cortex dysfunction

Franziska Maier, Andrea Greuel, Marius Hoock, Rajbir Kaur, Masoud Tahmasian, Frank Schwartz, Ilona Csoti, Frank Jessen, Alexander Drzezga, Thilo van Eimeren, Lars Timmermann, Carsten Eggers

Summary: This study investigated impaired self-awareness of cognitive deficits in Parkinson's disease (PD) and its associations with clinical-behavioral and neuroimaging markers. The results showed that PD patients with mild cognitive impairment (PD-MCI) had significantly higher impaired self-awareness than healthy controls and PD patients without MCI. Neuroimaging analysis revealed that glucose metabolism in the cingulate cortex was negatively correlated with impaired self-awareness. In PD-MCI patients, impaired self-awareness was associated with decreased metabolism in the right temporal lobe, insula, and midcingulate cortex. These findings suggest that impaired self-awareness of cognitive deficits in PD may be related to disruptions in the cognitive network and metabolic changes in specific brain regions.

PSYCHOLOGICAL MEDICINE (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

The RSNA QIBA Profile for Amyloid PET as an Imaging Biomarker for Cerebral Amyloid Quantification

Anne M. Smith, Nancy A. Obuchowski, Norman L. Foster, Gregory Klein, P. David Mozley, Adriaan A. Lammertsma, Richard L. Wahl, John J. Sunderland, Jean-Luc Vanderheyden, Tammie L. S. Benzinger, Paul E. Kinahan, Dean F. Wong, Eric S. Perlman, Satoshi Minoshima, Dawn Matthews

Summary: Standardized approach in acquiring amyloid PET images increases their value as disease and drug response biomarkers. The Quantitative Imaging Biomarkers Alliance amyloid PET biomarker committee developed and validated a profile to characterize and reduce the variability of SUVRs, increasing statistical power for these assessments.

JOURNAL OF NUCLEAR MEDICINE (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

Decentralized collaborative multi-institutional PET attenuation and scatter correction using federated deep learning

Isaac Shiri, Alireza Vafaei Sadr, Azadeh Akhavan, Yazdan Salimi, Amirhossein Sanaat, Mehdi Amini, Behrooz Razeghi, Abdollah Saberi, Hossein Arabi, Sohrab Ferdowsi, Slava Voloshynovskiy, Deniz Gunduz, Arman Rahmim, Habib Zaidi

Summary: This study developed a deep learning (DL) model using federated learning (FL) for the attenuation correction and scatter compensation (AC/SC) of PET images in a multicenter setting. The FL-based models showed excellent performance in terms of relative error and image prediction accuracy, comparable to centralized and center-based models.

EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

Artificial Intelligence in Nuclear Medicine: Opportunities, Challenges, and Responsibilities Toward a Trustworthy Ecosystem

Babak Saboury, Tyler Bradshaw, Ronald Boellaard, Irene Buvat, Joyita Dutta, Mathieu Hatt, Abhinav K. Jha, Quanzheng Li, Chi Liu, Helena McMeekin, Michael A. Morris, Peter J. H. Scott, Eliot Siegel, John J. Sunderland, Neeta Pandit-Taskar, Richard L. Wahl, Sven Zuehlsdorff, Arman Rahmim

Summary: Trustworthiness is crucial in medicine as the patient-physician relationship evolves in the era of artificial intelligence. This report provides a roadmap for establishing trustworthy AI ecosystems in nuclear medicine, discussing both the opportunities and challenges associated with AI applications in this field. The plan emphasizes the importance of engaging stakeholders while ensuring the rational and safe deployment of AI technology in order to protect patients and society.

JOURNAL OF NUCLEAR MEDICINE (2023)

Article Engineering, Biomedical

Application of novel hybrid machine learning systems and radiomics features for non-motor outcome prediction in Parkinson's disease

Mohammad R. Salmanpour, Mahya Bakhtiyari, Mahdi Hosseinzadeh, Mehdi Maghsudi, Fereshteh Yousefirizi, Mohammad M. Ghaemi, Arman Rahmim

Summary: This study aims to investigate the use of machine learning systems to improve the prediction performance of Montreal Cognitive Assessment (MoCA) in Parkinson's disease patients. The study used clinical features, conventional imaging features, and radiomics features for prediction, and found that using larger datasets and optimized machine learning systems can significantly improve the prediction performance.

PHYSICS IN MEDICINE AND BIOLOGY (2023)

Article Pharmacology & Pharmacy

Stimuli-sensitive nano-drug delivery with programmable size changes to enhance accumulation of therapeutic agents in tumors

Mohammad Souri, Mohammad Kiani Shahvandi, Mohsen Chiani, Farshad Moradi Kashkooli, Ali Farhangi, Mohammad Reza Mehrabi, Arman Rahmim, Van M. Savage, M. Soltani

Summary: This study introduces an efficient nanosized drug delivery system with programmable size changes, which improves the accumulation of drug-carrying nanoparticles in tumors and achieves higher penetration depths. Reducing the size of nanoparticles leads to higher cell death rate and longer inhibition of tumor growth. This drug delivery system shows great promise in clinical applications.

DRUG DELIVERY (2023)

Article Biology

Radiomics and dosiomics-based prediction of radiotherapy-induced xerostomia in head and neck cancer patients

Hamid Abdollahi, Tania Dehesh, Neda Abdalvand, Arman Rahmim

Summary: This study aimed to develop xerostomia predictive models based on radiomics-dosiomics features. The results showed that the models combining CT and dose (Delta CT2-1 + Dose, CT3) and the dose-volume histogram model (DVH) had the highest predictive accuracy. These predictive models provide prospects for personalized therapy.

INTERNATIONAL JOURNAL OF RADIATION BIOLOGY (2023)

Editorial Material Radiology, Nuclear Medicine & Medical Imaging

FDG PET/CT-based Response Assessment in Malignancies

Prabhakar Shantha Rajiah, Maria Jose Sarda, Ravi Ashwath, Harold Goerne

RADIOGRAPHICS (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

Multicenter quantitative 18F-fluorodeoxyglucose positron emission tomography performance harmonization: use of hottest voxels towards more robust quantification

Habibeh Vosoughi, Mehdi Momennezhad, Farshad Emami, Mohsen Hajizadeh, Arman Rahmim, Parham Geramifar

Summary: This study explores harmonization strategies for comparable and robust quantitative metrics in a multicenter setting. The results show that harmonizing PET/CT systems improves the reproducibility of quantification. RC10V and RCpeak outperform other indices in terms of accuracy and reproducibility.

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY (2023)

Article Medicine, General & Internal

Deep versus Handcrafted Tensor Radiomics Features: Prediction of Survival in Head and Neck Cancer Using Machine Learning and Fusion Techniques

Mohammad R. Salmanpour, Seyed Masoud Rezaeijo, Mahdi Hosseinzadeh, Arman Rahmim

Summary: This study demonstrated that the utilization of deep features extracted from deep learning algorithms, combined with appropriate machine learning approaches, improved the accuracy of survival prediction compared to conventional deep features, tensor and conventional radiomics features, and end-to-end CNN frameworks.

DIAGNOSTICS (2023)

Article Radiology, Nuclear Medicine & Medical Imaging

177Lu SPECT imaging in the presence of 90Y: does 90Y degrade image quantification? a simulation study

Cassandra Miller, Carlos Uribe, Xinchi Hou, Arman Rahmim, Anna Celler

Summary: This study investigates the accuracy of quantitative SPECT imaging of Lu-177 in the presence of Y-90 in dual-isotope radiopharmaceutical therapy. Phantom simulations were conducted using the GATE Monte Carlo simulation toolkit, and multiple configurations and combinations were simulated. The results show that the quantification error is within +/- 6% of the no-Y-90 case, and quantitative accuracy may slightly improve when Y-90 is present. Lesion detectability is not degraded by the presence of Y-90.

BIOMEDICAL PHYSICS & ENGINEERING EXPRESS (2023)

Article Computer Science, Interdisciplinary Applications

Assessing privacy leakage in synthetic 3-D PET imaging using transversal GAN

Robert V. Bergen, Jean-Francois Rajotte, Fereshteh Yousefirizi, Arman Rahmim, Raymond T. Ng

Summary: This article introduces a 3D generative model called TrGAN, which can generate medical images with important features and statistical properties while protecting privacy. By evaluating through a membership inference attack, the fidelity, utility, and privacy trade-offs of the model were studied.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2024)

Review Radiology, Nuclear Medicine & Medical Imaging

Machine learning in the positron emission tomography imaging of Alzheimer's disease

Cyrus Ayubcha, Shashi B. Singh, Krishna H. Patel, Arman Rahmim, Jareed Hasan, Litian Liu, Thomas Werner, Abass Alavi

Summary: The utilization of machine learning techniques in medicine has exponentially increased over the last decades. Applications of machine learning techniques to neuroimaging have unveiled various hidden interactions, structures, and mechanisms related to neurological disorders. This review article provides an overview of the diverse applications of machine learning to PET imaging of Alzheimer's disease.

NUCLEAR MEDICINE COMMUNICATIONS (2023)

Review Radiology, Nuclear Medicine & Medical Imaging

Animal Models and Their Role in Imaging-Assisted Co-Clinical Trials

Donna M. Peehl, Cristian T. Badea, Thomas L. Chenevert, Heike E. Daldrup-Link, Li Ding, Lacey E. Dobrolecki, A. McGarry Houghton, Paul E. Kinahan, John Kurhanewicz, Michael T. Lewis, Shunqiang Li, Gary D. Luker, Cynthia X. Ma, H. Charles Manning, Yvonne M. Mowery, Peter J. O'Dwyer, Robia G. Pautler, Mark A. Rosen, Raheleh Roudi, Brian D. Ross, Kooresh I. Shoghi, Renuka Sriram, Moshe Talpaz, Richard L. Wahl, Rong Zhou

Summary: The availability of high-fidelity animal models has increased, allowing for preclinical studies relevant to cancer research. Co-clinical trials conducted on animal models that mirror patients' tumors have seen increased opportunities. However, quantitative imaging in co-clinical trials still needs optimization.

TOMOGRAPHY (2023)

暂无数据