Rewolucja w Medycynie Nuklearnej: Jak Sztuczna Inteligencja Przekształca Diagnostykę i Leczenie Nowotworów - przegląd najnowszej literatury
Keywords:
sztuczna inteligencja, medycyna nuklearna, uczenie maszynowe, głębokie uczenie, rak prostaty, rak płucSynopsis
Wstęp: Sztuczna inteligencja (AI) odgrywa kluczową rolę w medycynie nuklearnej, przyczyniając się do rewolucji w diagnostyce i leczeniu. Algorytmy uczenia maszynowego (ML) i głębokiego uczenia (DL) pozwalają na analizę danych obrazowych, takich jak PET i SPECT, z precyzją przewyższającą możliwości ludzkie. Celem pracy było przeglądowe omówienie potencjału AI w medycynie nuklearnej, w tym jej wpływu na diagnostykę, personalizację terapii i efektywność opieki zdrowotnej. Materiały i metody: Dokonano analizy 34 publikacji naukowych z ostatniego roku, wyselekcjonowanych za pomocą słów kluczowych, takich jak „AI”, „PET”, „SPECT”, „machine learning” i „deep learning”, w bazie PubMed. Ocenę przeprowadzono według schematu PICO, skupiając się na parametrach, takich jak czułość, swoistość i AUC. Zastosowano retrospektywne podejście, uwzględniając wyniki badań nad AI w różnych obszarach medycyny nuklearnej. Wyniki: AI znacząco poprawia precyzję diagnostyczną, czułość (do 97%) i swoistość (do 92%) w zastosowaniach takich jak diagnostyka raka prostaty i płuc. W obrazowaniu PET/CT modele AI osiągnęły AUC na poziomie 0,98 w przewidywaniu progresji raka prostaty oraz 0,93 w różnicowaniu zmian nowotworowych. Automatyzacja segmentacji obrazów skróciła czas analizy z godzin do minut, redukując zmienność międzyobserwacyjną. Wyniki te potwierdzają potencjał AI w personalizacji terapii oraz prognozowaniu wyników leczenia. Wnioski: AI w medycynie nuklearnej oferuje przełomowe możliwości diagnostyczne i terapeutyczne, zwiększając precyzję oraz efektywność opieki zdrowotnej. Kluczowe pozostają jednak dalsze badania nad walidacją modeli, ich interpretowalnością oraz integracją w praktyce klinicznej. Pełne wykorzystanie potencjału AI wymaga harmonizacji danych i wieloośrodkowej walidacji. AI stanowi narzędzie przyszłości, które może znacząco poprawić jakość opieki medycznej.
References
Mintz Y, Brodie R. Introduction to artificial intelligence in medicine. Minimally Invasive Therapy & Allied Technologies. 2019;28(2):73-81. doi:https://doi.org/10.1080/13645706.2019.1575882
Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017;69(69):S36-S40. doi:https://doi.org/10.1016/j.metabol.2017.01.011
Nensa F, Demircioglu A, Rischpler C. Artificial Intelligence in Nuclear Medicine. Journal of Nuclear Medicine. 2019;60(Supplement 2):29S-37S. doi:https://doi.org/10.2967/jnumed.118.220590
Balyen L, Peto T. Promising Artificial Intelligence-Machine Learning-Deep Learning Algorithms in Ophthalmology. Asia-Pacific Journal of Ophthalmology. 2019;8(3). doi:https://doi.org/10.22608/apo.2018479
Tafti D, Banks KP. Nuclear Medicine Physics. StatPearls. Published online Spring 2023. https://pubmed.ncbi.nlm.nih.gov/33760490/
Najam H, Dearborn MC, Tafti D. Nuclear Medicine Instrumentation. StatPearls. Published online Summer 2023. https://pubmed.ncbi.nlm.nih.gov/37983326/
Heston TF, Tafti D. Nuclear Medicine Safety. StatPearls. Published online Summer 2024. https://pubmed.ncbi.nlm.nih.gov/38753905/
Eli A, Oladele S, Ping X, Shai L. Detecting Fraudulent Claims in Nuclear Medicine Using Machine Learning Algorithms. ResearchGate. Published November 19, 2024. https://www.researchgate.net/publication/385943265
Xu K, Kang H. A Review of Machine Learning Approaches for Brain Positron Emission Tomography Data Analysis. Nuclear Medicine and Molecular Imaging. 2024;58(4):203-212. doi:https://doi.org/10.1007/s13139-024-00845-6
Robert JH, Slomka PJ. Artificial Intelligence in Nuclear Cardiology: An Update and Future Trends. Seminars in Nuclear Medicine. 2024;54(5). doi:https://doi.org/10.1053/j.semnuclmed.2024.02.005
Glemser PA, Freitag M, Kovacs B, et al. Enhancing the diagnostic capacity of [18F]PSMA-1007 PET/MRI in primary prostate cancer staging with artificial intelligence and semi-quantitative DCE: an exploratory study. Deleted Journal. 2024;8(1). doi:https://doi.org/10.1186/s41824-024-00225-5
Liu J, Cundy TP, Dixon, Desai N, Marimuthu Palaniswami, Lawrentschuk N. A systematic review on artificial intelligence evaluating PSMA PET scan for intraprostatic cancer. BJU International. 2024;134(5). doi:https://doi.org/10.1111/bju.16412
Tapper W, Carneiro G, Christos Mikropoulos, Thomas SA, Evans PM, Stergios Boussios. The Application of Radiomics and AI to Molecular Imaging for Prostate Cancer. Journal of Personalized Medicine. 2024;14(3):287. doi:https://doi.org/10.3390/jpm14030287
Sarah Lindgren Belal, Frantz S, Minarik D, et al. Applications of Artificial Intelligence in PSMA PET/CT for Prostate Cancer Imaging. Seminars in Nuclear Medicine. 2023;54(1). doi:https://doi.org/10.1053/j.semnuclmed.2023.06.001
Huang B, Yang Q, Li X, et al. Deep learning–based whole-body characterization of prostate cancer lesions on [68Ga]Ga-PSMA-11 PET/CT in patients with post-prostatectomy recurrence. European Journal of Nuclear Medicine and Molecular Imaging. 2023;51(4):1173-1184. doi:https://doi.org/10.1007/s00259-023-06551-3
Zang S, Jiang C, Zhang L, et al. Deep learning based on 68Ga-PSMA-11 PET/CT for predicting pathological upgrading in patients with prostate cancer. Frontiers in Oncology. 2024;13. doi:https://doi.org/10.3389/fonc.2023.1273414
Janbain A, Farolfi A, Armelle Guenegou-Arnoux, et al. A Machine Learning Approach for Predicting Biochemical Outcome After PSMA-PET–Guided Salvage Radiotherapy in Recurrent Prostate Cancer After Radical Prostatectomy: Retrospective Study. JMIR Cancer. 2024;10:e60323. doi:https://doi.org/10.2196/60323
Cao Y, Sutera P, Silva Mendes W, et al. Machine learning predicts conventional imaging metastasis-free survival (MFS) for oligometastatic castration-sensitive prostate cancer (omCSPC) using prostate-specific membrane antigen (PSMA) PET radiomics. Radiotherapy and Oncology. 2024;199:110443. doi:https://doi.org/10.1016/j.radonc.2024.110443
Wang Y, Dong L, Zhao H, et al. The superior detection rate of total-body [68Ga]Ga-PSMA-11 PET/CT compared to short axial field-of-view [68Ga]Ga-PSMA-11 PET/CT for early recurrent prostate cancer patients with PSA < 0.2 ng/mL after radical prostatectomy. European Journal of Nuclear Medicine and Molecular Imaging. 2024;51(8):2484-2494. doi:https://doi.org/10.1007/s00259-024-06674-1
Li Y, Imami MR, Zhao L, et al. An Automated Deep Learning-Based Framework for Uptake Segmentation and Classification on PSMA PET/CT Imaging of Patients with Prostate Cancer. Deleted Journal. 2024;37(5):2206-2215. doi:https://doi.org/10.1007/s10278-024-01104-y
Liu J, Cundy TP, Dixon, Lawrentschuk N. A Systematic Review on Artificial Intelligence Evaluating Metastatic Prostatic Cancer and Lymph Nodes on PSMA PET Scans. Cancers. 2024;16(3):486. doi:https://doi.org/10.3390/cancers16030486
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. Radiation Oncology. 2024;19(1). doi:https://doi.org/10.1186/s13014-024-02491-w
Urso L, Corrado Cittanti, Manco L, et al. ML Models Built Using Clinical Parameters and Radiomic Features Extracted from 18F-Choline PET/CT for the Prediction of Biochemical Recurrence after Metastasis-Directed Therapy in Patients with Oligometastatic Prostate Cancer. Diagnostics. 2024;14(12):1264. doi:https://doi.org/10.3390/diagnostics14121264
Guzmán Ortiz S, Hurtado Ortiz R, Jara Gavilanes A, Ávila Faican R, Parra Zambrano B. A serial image analysis architecture with positron emission tomography using machine learning combined for the detection of lung cancer. Revista Española de Medicina Nuclear e Imagen Molecular (English Edition). 2024;43(3):500003. doi:https://doi.org/10.1016/j.remnie.2024.500003
Zhao H, Su Y, Lyu Z, et al. Non-invasively Discriminating the Pathological Subtypes of Non-small Cell Lung Cancer with Pretreatment 18 F-FDG PET/CT Using Deep Learning. Academic Radiology. 2024;31(1):35-45. doi:https://doi.org/10.1016/j.acra.2023.03.032
Liang C, Zheng M, Zou H, et al. Deep learning-based image analysis predicts PD-L1 status from 18F-FDG PET/CT images in non-small-cell lung cancer. Frontiers in Oncology. 2024;14. doi:https://doi.org/10.3389/fonc.2024.1402994
Sung C, Oh JS, Park BS, Kim SS, Song SY, Lee JJ. Diagnostic performance of a deep-learning model using 18F-FDG PET/CT for evaluating recurrence after radiation therapy in patients with lung cancer. Annals of Nuclear Medicine. 2024;38(7):516-524. doi:https://doi.org/10.1007/s12149-024-01925-5
Yuan L, An L, Zhu Y, et al. Machine Learning in Diagnosis and Prognosis of Lung Cancer by PET-CT. Cancer Management and Research. 2024;Volume 16:361-375. doi:https://doi.org/10.2147/cmar.s451871
Li B, Su J, Liu K, Hu C. Deep learning radiomics model based on PET/CT predicts PD-L1 expression in non-small cell lung cancer. European Journal of Radiology Open. 2024;12:100549. doi:https://doi.org/10.1016/j.ejro.2024.100549
Zhang Y, Liu H, Chang C, Yin Y, Wang R. Machine learning for differentiating lung squamous cell cancer from adenocarcinoma using Clinical-Metabolic characteristics and 18F-FDG PET/CT radiomics. PloS One. 2024;19(4):e0300170. doi:https://doi.org/10.1371/journal.pone.0300170
Ju L, Li W, Zuo R, et al. Deep Learning Features and Metabolic Tumor Volume Based on PET/CT to Construct Risk Stratification in Non-small Cell Lung Cancer. Academic Radiology. 2024;31(11):4661-4675. doi:https://doi.org/10.1016/j.acra.2024.04.036
Hakkak Moghadam Torbati A, Pellegrino S, Fonti R, Morra R, Placido SD, Vecchio SD. Machine Learning and Texture Analysis of [18F]FDG PET/CT Images for the Prediction of Distant Metastases in Non-Small-Cell Lung Cancer Patients. Biomedicines. 2024;12(3):472. doi:https://doi.org/10.3390/biomedicines12030472
Hosseini SA, Ghasem Hajianfar, Pardis Ghaffarian, et al. PET radiomics-based lymphovascular invasion prediction in lung cancer using multiple segmentation and multi-machine learning algorithms. Physical and Engineering Sciences in Medicine. 2024;47:1613-1625. doi:https://doi.org/10.1007/s13246-024-01475-0
Zhu Y, Cong S, Zhang Q, et al. Multimodal radiomics-based methods using deep learning for prediction of brain metastasis in non-small cell lung cancer with 18F-FDG PET/CT images. Biomedical Physics & Engineering Express. 2024;10(6):065011. doi:https://doi.org/10.1088/2057-1976/ad7595
Meng N, Feng P, Yu X, et al. An [18F]FDG PET/3D-ultrashort echo time MRI-based radiomics model established by machine learning facilitates preoperative assessment of lymph node status in non-small cell lung cancer. European Radiology. 2023;34(1):318-329. doi:https://doi.org/10.1007/s00330-023-09978-2
Toosi A, Shiri I, Zaidi H, Rahmim A. 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. 2024;16(14):2538. doi:https://doi.org/10.3390/cancers16142538
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. Journal of Nuclear Medicine. 2024;65(4):623-629. doi:https://doi.org/10.2967/jnumed.123.266574
Wang Z, Zheng C, Han X, Chen W, Lu L. An Innovative and Efficient Diagnostic Prediction Flow for Head and Neck Cancer: A Deep Learning Approach for Multi-Modal Survival Analysis Prediction Based on Text and Multi-Center PET/CT Images. Diagnostics. 2024;14(4):448. doi:https://doi.org/10.3390/diagnostics14040448
Zhi H, Xiang Y, Chen C, et al. Development and validation of a machine learning-based 18F-fluorodeoxyglucose PET/CT radiomics signature for predicting gastric cancer survival. Cancer Imaging. 2024;24(1). doi:https://doi.org/10.1186/s40644-024-00741-4
Jannusch K, Dietzel F, Bruckmann NM, et al. Prediction of therapy response of breast cancer patients with machine learning based on clinical data and imaging data derived from breast [18F]FDG-PET/MRI. European Journal of Nuclear Medicine and Molecular Imaging. 2023;51(5):1451-1461. doi:https://doi.org/10.1007/s00259-023-06513-9
Wu KC, Chen SW, Chang RF, et al. Early prediction of radiotherapy outcomes in pharyngeal cancer using deep learning on baseline [18F]Fluorodeoxyglucose positron emission Tomography/Computed tomography. European Journal of Radiology. 2024;181:111811. doi:https://doi.org/10.1016/j.ejrad.2024.111811
Duan C, Liu Q, Wang J, et al. GWO+RuleFit: rule-based explainable machine-learning combined with heuristics to predict mid-treatment FDG PET response to chemoradiation for locally advanced non-small cell lung cancer. Physics in Medicine & Biology. 2024;69(15):155018. doi:https://doi.org/10.1088/1361-6560/ad6118
De Biase A, Ma B, Guo J, et al. Deep learning-based outcome prediction using PET/CT and automatically predicted probability maps of primary tumor in patients with oropharyngeal cancer. Computer Methods and Programs in Biomedicine. 2023;244:107939. doi:https://doi.org/10.1016/j.cmpb.2023.107939
Wang H, Zhang J, Li Y, et al. Deep-learning features based on F18 fluorodeoxyglucose positron emission tomography/computed tomography (18F-FDG PET/CT) to predict preoperative colorectal cancer lymph node metastasis. Clinical Radiology. 2024;79(9):e1152-e1158. doi:https://doi.org/10.1016/j.crad.2024.05.017
Published
June 19, 2025
Copyright (c) 2025 Krzysztof Żerdziński
License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
