This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.
Manas Kumar Yogi,
- Assistant Professor, Computer Science and Engineering Department Pragati Engineering College (A), Surampalem, Andhra Pradesh, India
Abstract
Nuclear medicine, encompassing PET, SPECT, and targeted radionuclide therapy, generates high-dimensional, quantitative data uniquely suited for machine learning (ML) analysis. This review synthesizes current research applications of ML across six key domains. Positron emission tomography (PET), single-photon emission computed tomography (SPECT), and targeted radionuclide therapy are examples of nuclear medicine modalities that generate high- dimensional, quantitative datasets that are particularly well-suited for machine learning (ML)-driven analysis. These imaging methods provide a greater insight of disease processes at the cellular level by capturing not only morphological but also functional and molecular information. PET image reconstruction and denoising, automated lesion segmentation, motion correction, therapy dose planning, radiomics-based outcome prediction, and advanced dosimetry for targeted alpha therapy are the six main nuclear medicine research domains that this review summarises and critically assesses. PET image reconstruction and denoising, automated lesion segmentation, motion correction, therapy dose planning, radiomics-based outcome prediction, and dosimetry for targeted alpha therapy. We highlight how convolutional neural networks, generative adversarial networks, transformers, and ensemble methods enhance image quality, reduce radiation exposure, automate tumor delineation, personalize activity prescription, and predict patient responses. Technical advances in low- count imaging, direct reconstruction, and motion compensation are discussed alongside clinical translation challenges including data scarcity, model generalizability, and regulatory approval. The review concludes that ML is poised to transform nuclear medicine workflows, though prospective validation and standardized benchmarking remain critical next steps.
Keywords: PET, Radiomics, Dosimetry, Segmentation, Reconstruction
Manas Kumar Yogi. Machine Learning in Nuclear Medical Applications: A Review of Research Frontiers. Journal of Nuclear Engineering & Technology. 2026; 16(01):-.
Manas Kumar Yogi. Machine Learning in Nuclear Medical Applications: A Review of Research Frontiers. Journal of Nuclear Engineering & Technology. 2026; 16(01):-. Available from: https://journals.stmjournals.com/jonet/article=2026/view=243463
References
1. Duff LM, Shi K, Tsoumpas C. Nuclear medicine advances through artificial intelligence and intelligent informatics. Frontiers in Nuclear Medicine. 2025 Jan 7;4:1502419.
2. Visvikis D, Lambin P, Beuschau Mauridsen K, Hustinx R, Lassmann M, Rischpler C, Shi K, Pruim J. Application of artificial intelligence in nuclear medicine and molecular imaging: a review of current status and future perspectives for clinical translation. European journal of nuclear medicine and molecular imaging. 2022 Nov;49(13):4452-63.
3. Yin L, Cao Z, Wang K, Tian J, Yang X, Zhang J. A review of the application of machine learning in molecular imaging. Annals of Translational Medicine. 2021 May;9(9):825.
4. LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015 May 28;521(7553):436- 44.
5. Jung S, Lee BJ, Han I. Gomez, Ł. Kaiser, and I. Polosukhin,“Attention is all you need,” in Advances in Neural Information Processing Systems, 2017, pp. 5998–6008.
6. Gong K, Guan J, Liu CC, Qi J. PET image denoising using a deep neural network through fine tuning. IEEE Transactions on Radiation and Plasma Medical Sciences. 2018 Oct 23;3(2):153-61.
7. Adler J, Öktem O. Learned primal-dual reconstruction. IEEE transactions on medical imaging. 2018 Jan 29;37(6):1322-32.
8. Chen KT, Gong E, de Carvalho Macruz FB, Xu J, Boumis A, Khalighi M, Poston KL, Sha SJ, Greicius MD, Mormino E, Pauly JM. Ultra–low-dose 18F-florbetaben amyloid PET imaging using deep learning with multi-contrast MRI inputs. Radiology. 2019 Mar;290(3):649-56.
9. Hatamizadeh A, Tang Y, Nath V, Yang D, Myronenko A, Landman B, Roth HR, Xu D. Unetr: Transformers for 3d medical image segmentation. InProceedings of the IEEE/CVF winter conference on applications of computer vision 2022 (pp. 574-584).
10. Oreiller V, Andrearczyk V, Jreige M, Boughdad S, Elhalawani H, Castelli J, Vallieres M, Zhu S, Xie J, Peng Y, Iantsen A. Head and neck tumor segmentation in PET/CT: the HECKTOR challenge. Medical image analysis. 2022 Apr 1;77:102336.
Journal of Nuclear Engineering & Technology
| Volume | 16 |
| 01 | |
| Received | 29/04/2026 |
| Accepted | 30/04/2026 |
| Published | 11/05/2026 |
| Publication Time | 12 Days |
Login
PlumX Metrics