PET und KI: Ein narrativer Überblick

Julian Manuel Michael Rogasch; Jakub Mikolajczak; Dirk Hellwig; Jens Maus; Frank Hofheinz; Anja Braune; Pavel Nikulin

doi:10.1055/a-2385-3773

Angewandte Nuklearmedizin, Table of Contents

Angewandte Nuklearmedizin 2025; 48(03): 204-212
DOI: 10.1055/a-2385-3773

PET/CT

Übersicht

PET und KI: Ein narrativer Überblick

PET and AI: A narrative review

Authors

Julian Manuel Michael Rogasch

¹Department of Nuclear Medicine, Charité - Universitätsmedizin Berlin, Berlin, Germany
Jakub Mikolajczak

²Abteilung für Nuklearmedizin, Universitätsklinikum Regensburg, Regensburg, Germany (Ringgold ID: RIN39070)

³Medizinisches Datenintegrationszentrum, Universitätsklinikum Regensburg, Regensburg

⁴Bayerisches Zentrum für Krebsforschung (BZKF), Regensburg, Germany
Dirk Hellwig

²Abteilung für Nuklearmedizin, Universitätsklinikum Regensburg, Regensburg, Germany (Ringgold ID: RIN39070)

³Medizinisches Datenintegrationszentrum, Universitätsklinikum Regensburg, Regensburg

⁴Bayerisches Zentrum für Krebsforschung (BZKF), Regensburg, Germany
Jens Maus

⁵Inst. für Radiopharm. Krebsforschung, Helmholtz-Zentrum Dresden-Rossendorf, Dresden
Frank Hofheinz

⁵Inst. für Radiopharm. Krebsforschung, Helmholtz-Zentrum Dresden-Rossendorf, Dresden
Anja Braune

⁵Inst. für Radiopharm. Krebsforschung, Helmholtz-Zentrum Dresden-Rossendorf, Dresden
Pavel Nikulin

⁵Inst. für Radiopharm. Krebsforschung, Helmholtz-Zentrum Dresden-Rossendorf, Dresden

Abstract

Zusammenfassung

Dieser Artikel bietet einen aktuellen Überblick über Entwicklungen zu Künstlicher Intelligenz (KI) in der PET-Bildgebung. Neben einer Einführung in Deep Learning-Methoden werden Anwendungen wie Bildrekonstruktion und Bildsegmentierung beleuchtet. Zudem wird die aktuelle Literatur zu KI-gestützten diagnostischen, prognostischen und prädiktiven Modelle in Onkologie und Neurologie dargestellt. Fortschritte in Vision-Language Models (VLMs) und Large-Language Models (LLMs) zeigen Potenzial für eine strukturierte Befundung und Workflow-Optimierung. Trotz vielversprechender Entwicklungen bleibt eine sorgfältige Validierung der KI-Modelle essenziell, um Generalisierbarkeit und klinische Anwendbarkeit sicherzustellen.

Abstract

This article provides a current overview of developments in artificial intelligence (AI) for PET imaging. In addition to an introduction to deep learning methods, it discusses applications such as image reconstruction and image segmentation. Furthermore, it reviews the latest literature on AI-assisted diagnostic, prognostic, and predictive models in oncology and neurology. Advances in vision-language models (VLMs) and large language models (LLMs) demonstrate potential for structured reporting and workflow optimization. Despite these promising developments, rigorous validation of AI models remains essential to ensure their generalizability and clinical applicability.

Schlüsselwörter

Positronen-Emissions-Tomographie - künstliche Intelligenz - Deep Learning - Large Language Models - Radiomics

Keywords

Positron emission tomography - artificial intelligence - deep learning - large language models - radiomics

Full Text

References

Referenzen
1 Zhang H, Qie Y. Applying Deep Learning to Medical Imaging: A Review. Applied Sciences 2023; 13: 10521
2 Huang S-C, Pareek A, Jensen M. et al. Self-supervised learning for medical image classification: a systematic review and implementation guidelines. NPJ Digit Med 2023; 6: 74
3 Raza K, Singh NK. A Tour of Unsupervised Deep Learning for Medical Image Analysis. Curr Med Imaging 2021; 17: 1059-1077
4 Bluemke DA, Moy L, Bredella MA. et al. Assessing Radiology Research on Artificial Intelligence: A Brief Guide for Authors, Reviewers, and Readers-From the Radiology Editorial Board. Radiology 2020; 294: 487-489
5 Islam J, Zhang Y. GAN-based synthetic brain PET image generation. Brain Inform 2020; 7: 3
6 Reddy S. Generative AI in healthcare: an implementation science informed translational path on application, integration and governance. Implement Sci 2024; 19: 27
7 Tie X, Shin M, Pirasteh A. et al. Personalized Impression Generation for PET Reports Using Large Language Models. J Imaging Inform Med 2024; 37: 471-488
8 Reader AJ, Pan B. AI for PET image reconstruction. Br J Radiol 2023; 96: 20230292
9 Häggström I, Schmidtlein CR, Campanella G. et al. DeepPET: A deep encoder-decoder network for directly solving the PET image reconstruction inverse problem. Med Image Anal 2019; 54: 253-262
10 Liu Z, Chen H, Liu H. Deep Learning Based Framework for Direct Reconstruction of PET Images. In: Shen D, Liu T, Peters TM. et al. , Hrsg. Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. Cham: Springer International Publishing; 2019: 48-56
11 Whiteley W, Luk WK, Gregor J. DirectPET: full-size neural network PET reconstruction from sinogram data. J Med Imaging (Bellingham) 2020; 7: 032503
12 Shiri I, Arabi H, Geramifar P. et al. Deep-JASC: joint attenuation and scatter correction in whole-body 18F-FDG PET using a deep residual network. Eur J Nucl Med Mol Imaging 2020; 47: 2533-2548
13 Li T, Zhang M, Qi W. et al. Motion correction of respiratory-gated PET images using deep learning based image registration framework. Phys Med Biol 2020; 65: 155003
14 Ledig C, Theis L, Huszar F. et al. Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network. arXiv 2017;
15 Hellwig D, Hellwig NC, Boehner S. et al. Artificial Intelligence and Deep Learning for Advancing PET Image Reconstruction: State-of-the-Art and Future Directions. Nuklearmedizin 2023; 62: 334-342
16 Hofheinz F, Pötzsch C, Oehme L. et al. Automatic volume delineation in oncological PET. Evaluation of a dedicated software tool and comparison with manual delineation in clinical data sets. Nuklearmedizin 2012; 51: 9-16
17 Trimpl MJ, Campbell S, Panakis N. et al. Deep learning-assisted interactive contouring of lung cancer: Impact on contouring time and consistency. Radiotherapy and Oncology 2024; 200: 110500
18 Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Navab N, Hornegger J, Wells WM. et al. , Hrsg. Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Cham: Springer International Publishing; 2015: 234-241
19 Shamshad F, Khan S, Zamir SW. et al. Transformers in medical imaging: A survey. Medical Image Analysis 2023; 88: 102802
20 Raghu M, Unterthiner T, Kornblith S. et al. Do Vision Transformers See Like Convolutional Neural Networks?. arXiv 2021;
21 Isensee F, Jaeger PF, Kohl SAA. et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 2021; 18: 203-211
22 Han K, Sheng VS, Song Y. et al. Deep semi-supervised learning for medical image segmentation: A review. Expert Systems with Applications 2024; 245: 123052
23 Bowles C, Chen L, Guerrero R. et al. GAN Augmentation: Augmenting Training Data using Generative Adversarial Networks. arXiv 2018;
24 Bergen RV, Rajotte J-F, Yousefirizi F. et al. 3-D PET Image Generation with tumour masks using TGAN. arXiv 2021;
25 Cao K, Bi L, Feng D. et al. Improving PET-CT Image Segmentation via Deep Multi-modality Data Augmentation. In: Deeba F, Johnson P, Würfl T. , Hrsg. Machine Learning for Medical Image Reconstruction. Cham: Springer International Publishing; 2020: 145-152
26 Shiri I, Razeghi B, Vafaei Sadr A. et al. Multi-institutional PET/CT image segmentation using federated deep transformer learning. Computer Methods and Programs in Biomedicine 2023; 240: 107706
27 Andrearczyk V, Oreiller V, Abobakr M. et al. Overview of the HECKTOR Challenge at MICCAI 2022: Automatic Head and Neck Tumor Segmentation and Outcome Prediction in PET/CT. In: Andrearczyk V, Oreiller V, Hatt M. , Hrsg. Head and Neck Tumor Segmentation and Outcome Prediction. Cham: Springer Nature Switzerland; 2023: 1-30
28 Jiang C, Chen K, Teng Y. et al. Deep learning–based tumour segmentation and total metabolic tumour volume prediction in the prognosis of diffuse large B-cell lymphoma patients in 3D FDG-PET images. Eur Radiol 2022; 32: 4801-4812
29 Nikulin P, Zschaeck S, Maus J. et al. A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in $$[^{18}$$F]FDG PET/CT. Eur J Nucl Med Mol Imaging 2023; 50: 2751-2766
30 Kovacs DG, Ladefoged CN, Andersen KF. et al. Clinical Evaluation of Deep Learning for Tumor Delineation on 18F-FDG PET/CT of Head and Neck Cancer. J Nucl Med 2024; 65: 623-629
31 Liu Z, Mhlanga JC, Siegel BA. et al. Need for objective task-based evaluation of AI-based segmentation methods for quantitative PET. In: Chen Y, Mello-Thoms CR. , Hrsg. Medical Imaging 2023: Image Perception, Observer Performance, and Technology Assessment. San Diego, United States: SPIE; 2023.
32 Wang Y, Lombardo E, Huang L. et al. Comparison of deep learning networks for fully automated head and neck tumor delineation on multi-centric PET/CT images. Radiat Oncol 2024; 19: 3
33 Isensee F, Wald T, Ulrich C. et al. nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation. arXiv 2024;
34 AlBadawy EA, Saha A, Mazurowski MA. Deep learning for segmentation of brain tumors: Impact of cross-institutional training and testing. Medical Physics 2018; 45: 1150-1158
35 Holzschuh JC, Mix M, Freitag MT. et al. The impact of multicentric datasets for the automated tumor delineation in primary prostate cancer using convolutional neural networks on 18F-PSMA-1007 PET. Radiat Oncol 2024; 19: 106
36 Cacciamani GE, Sanford DI, Chu TN. et al. Is Artificial Intelligence Replacing Our Radiology Stars? Not Yet!. Eur Urol Open Sci 2023; 48: 14-16
37 Frood R, Willaime JMY, Miles B. et al. Comparative effectiveness of standard vs. AI-assisted PET/CT reading workflow for pre-treatment lymphoma staging: a multi-institutional reader study evaluation. Front Nucl Med 2024; 3: 1327186
38 Niehoff JH, Kalaitzidis J, Kroeger JR. et al. Evaluation of the clinical performance of an AI-based application for the automated analysis of chest X-rays. Sci Rep 2023; 13: 3680
39 Häggström I, Leithner D, Alvén J. et al. Deep learning for [18F]fluorodeoxyglucose-PET-CT classification in patients with lymphoma: a dual-centre retrospective analysis. Lancet Digit Health 2024; 6: e114-e125
40 Borrelli P, Ly J, Kaboteh R. et al. AI-based detection of lung lesions in [18F]FDG PET-CT from lung cancer patients. EJNMMI Phys 2021; 8: 32
41 Nakao T, Hanaoka S, Nomura Y. et al. Anomaly detection in chest 18F-FDG PET/CT by Bayesian deep learning. Jpn J Radiol 2022; 40: 730-739
42 Wallis D, Soussan M, Lacroix M. et al. An [18F]FDG-PET/CT deep learning method for fully automated detection of pathological mediastinal lymph nodes in lung cancer patients. Eur J Nucl Med Mol Imaging 2022; 49: 881-888
43 Weisman AJ, Kieler MW, Perlman SB. et al. Convolutional Neural Networks for Automated PET/CT Detection of Diseased Lymph Node Burden in Patients with Lymphoma. Radiol Artif Intell 2020; 2: e200016
44 Solal M, Hassanaly R, Burgos N. Leveraging healthy population variability in deep learning unsupervised anomaly detection in brain FDG PET. In: Colliot O, Mitra J. , Hrsg. Medical Imaging 2024: Image Processing. San Diego, United States: SPIE; 2024.
45 Etminani K, Soliman A, Davidsson A. et al. A 3D deep learning model to predict the diagnosis of dementia with Lewy bodies, Alzheimer’s disease, and mild cognitive impairment using brain 18F-FDG PET. Eur J Nucl Med Mol Imaging 2022; 49: 563-584
46 Wu P, Zhao Y, Wu J. et al. Differential Diagnosis of Parkinsonism Based on Deep Metabolic Imaging Indices. J Nucl Med 2022; 63: 1741-1747
47 Zhao Y, Wu P, Wu J. et al. Decoding the dopamine transporter imaging for the differential diagnosis of parkinsonism using deep learning. Eur J Nucl Med Mol Imaging 2022; 49: 2798-2811
48 Borys K, Schmitt YA, Nauta M. et al. Explainable AI in medical imaging: An overview for clinical practitioners - Beyond saliency-based XAI approaches. Eur J Radiol 2023; 162: 110786
49 Lambin P, Rios-Velazquez E, Leijenaar R. et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 2012; 48: 441-446
50 Hatt M, Krizsan AK, Rahmim A. et al. Joint EANM/SNMMI guideline on radiomics in nuclear medicine: Jointly supported by the EANM Physics Committee and the SNMMI Physics, Instrumentation and Data Sciences Council. Eur J Nucl Med Mol Imaging 2023; 50: 352-375
51 Toosi A, Shiri I, Zaidi H. et al. Segmentation-Free Outcome Prediction from Head and Neck Cancer PET/CT Images: Deep Learning-Based Feature Extraction from Multi-Angle Maximum Intensity Projections (MA-MIPs). Cancers (Basel) 2024; 16: 2538
52 Rogasch JMM, Shi K, Kersting D. et al. Methodological evaluation of original articles on radiomics and machine learning for outcome prediction based on positron emission tomography (PET). Nuklearmedizin 2023; 62: 361-369
53 Huang B, Sollee J, Luo Y-H. et al. Prediction of lung malignancy progression and survival with machine learning based on pre-treatment FDG-PET/CT. EBioMedicine 2022; 82: 104127
54 Oh S, Kang S-R, Oh I. et al. Deep learning model integrating positron emission tomography and clinical data for prognosis prediction in non-small cell lung cancer patients. BMC Bioinformatics 2023; 24: 39
55 Ferrández MC, Golla SSV, Eertink JJ. et al. An artificial intelligence method using FDG PET to predict treatment outcome in diffuse large B cell lymphoma patients. Sci Rep 2023; 13: 13111
56 Jiang C, Qian C, Jiang Z. et al. Robust deep learning-based PET prognostic imaging biomarker for DLBCL patients: a multicenter study. Eur J Nucl Med Mol Imaging 2023; 50: 3949-3960
57 Wang Y, Lombardo E, Avanzo M. et al. Deep learning based time-to-event analysis with PET, CT and joint PET/CT for head and neck cancer prognosis. Comput Methods Programs Biomed 2022; 222: 106948
58 Cheng N-M, Yao J, Cai J. et al. Deep Learning for Fully Automated Prediction of Overall Survival in Patients with Oropharyngeal Cancer Using FDG-PET Imaging. Clin Cancer Res 2021; 27: 3948-3959
59 Hu D, Li X, Lin C. et al. Deep Learning to Predict the Cell Proliferation and Prognosis of Non-Small Cell Lung Cancer Based on FDG-PET/CT Images. Diagnostics (Basel) 2023; 13: 3107
60 Juarez-Orozco LE, Martinez-Manzanera O, van der Zant FM. et al. Deep Learning in Quantitative PET Myocardial Perfusion Imaging: A Study on Cardiovascular Event Prediction. JACC Cardiovasc Imaging 2020; 13: 180-182
61 Ballman KV. Biomarker: Predictive or Prognostic?. J Clin Oncol 2015; 33: 3968-3971
62 Zhong Y, Cai C, Chen T. et al. PET/CT based cross-modal deep learning signature to predict occult nodal metastasis in lung cancer. Nat Commun 2023; 14: 7513
63 Song J, Zhang J, Liu G. et al. PET/CT deep learning prognosis for treatment decision support in esophageal squamous cell carcinoma. Insights Imaging 2024; 15: 161
64 Gertz RJ, Bunck AC, Lennartz S. et al. GPT-4 for Automated Determination of Radiological Study and Protocol based on Radiology Request Forms: A Feasibility Study. Radiology 2023; 307: e230877
65 Rogasch JMM, Metzger G, Preisler M. et al. ChatGPT: Can You Prepare My Patients for [18F]FDG PET/CT and Explain My Reports?. J Nucl Med 2023;
66 Oura T, Tatekawa H, Horiuchi D. et al. Diagnostic accuracy of vision-language models on Japanese diagnostic radiology, nuclear medicine, and interventional radiology specialty board examinations. Jpn J Radiol 2024; 42: 1392-1398
67 Currie GM. GPT-4 in Nuclear Medicine Education: Does It Outperform GPT-3.5?. J Nucl Med Technol 2023; 51: 314-317
68 Rogasch JMM, Jochens HV, Metzger G. et al. Keeping Up With ChatGPT: Evaluating Its Recognition and Interpretation of Nuclear Medicine Images. Clin Nucl Med 2024; 49: 500-504
69 Chen K, Xu W, Li X. The Potential of Gemini and GPTs for Structured Report Generation based on Free-Text 18F-FDG PET/CT Breast Cancer Reports. Acad Radiol 2025; 32: 624-633
70 Xue S, Guo R, Bohn KP. et al. A cross-scanner and cross-tracer deep learning method for the recovery of standard-dose imaging quality from low-dose PET. Eur J Nucl Med Mol Imaging 2022; 49: 1843-1856
71 Seyyedi N, Ghafari A, Seyyedi N. et al. Deep learning-based techniques for estimating high-quality full-dose positron emission tomography images from low-dose scans: a systematic review. BMC Med Imaging 2024; 24: 238
72 Leung KH, Rowe SP, Sadaghiani MS. et al. Deep Semisupervised Transfer Learning for Fully Automated Whole-Body Tumor Quantification and Prognosis of Cancer on PET/CT. J Nucl Med 2024; 65: 643-650
73 Moor M, Banerjee O, Abad ZSH. et al. Foundation models for generalist medical artificial intelligence. Nature 2023; 616: 259-265
74 Lopes L, Lopez-Montes A, Chen Y. et al. The Evolution of Artificial Intelligence in Nuclear Medicine. Semin Nucl Med 2025;
75 Wornow M, Xu Y, Thapa R. et al. The shaky foundations of large language models and foundation models for electronic health records. NPJ Digit Med 2023; 6: 135
76 Yang Y, Liu Y, Liu X. et al. Demographic bias of expert-level vision-language foundation models in medical imaging. Sci Adv 2025; 11: eadq0305
77 Khan W, Leem S, See KB. et al. A Comprehensive Survey of Foundation Models in Medicine. IEEE Rev Biomed Eng 2025; 1-20
78 Geis JR, Brady AP, Wu CC. et al. Ethics of Artificial Intelligence in Radiology: Summary of the Joint European and North American Multisociety Statement. Radiology 2019; 293: 436-440