CT-Free Attenuation Correction in Paediatric Long Axial Field-of-View Positron Emission Tomography Using Synthetic CT from Emission Data DOI Creative Commons

Maria Elkjær Montgomery,

Flemming Littrup Andersen, René Mathiasen

и другие.

Diagnostics, Год журнала: 2024, Номер 14(24), С. 2788 - 2788

Опубликована: Дек. 12, 2024

Background/Objectives: Paediatric PET/CT imaging is crucial in oncology but poses significant radiation risks due to children’s higher radiosensitivity and longer post-exposure life expectancy. This study aims minimize exposure by generating synthetic CT (sCT) images from emission PET data, eliminating the need for attenuation correction (AC) scans paediatric patients. Methods: We utilized a cohort of 128 patients, resulting 195 paired images. Data were acquired using Siemens Biograph Vision 600 Long Axial Field-of-View (LAFOV) Quadra scanners. A 3D parameter transferred conditional GAN (PT-cGAN) architecture, pre-trained on adult was adapted trained cohort. The model’s performance evaluated qualitatively nuclear medicine specialist quantitatively comparing sCT-derived (sPET) with standard Results: model demonstrated high qualitative quantitative performance. Visual inspection showed no (19/23) or minor clinically insignificant (4/23) differences image quality between sPET. Quantitative analysis revealed mean SUV relative difference −2.6 ± 5.8% across organs, agreement lesion overlap (Dice coefficient 0.92 0.08). also performed robustly low-count settings, maintaining reduced acquisition times. Conclusions: proposed method effectively reduces AC scans. It maintains diagnostic accuracy minimises motion-induced artifacts, making it valuable alternative clinical application. Further testing settings warranted confirm these findings enhance patient safety.

Язык: Английский

AI in Orthodontics: Revolutionizing Diagnostics and Treatment Planning—A Comprehensive Review DOI Open Access
Natalia Kazimierczak, Wojciech Kazimierczak, Zbigniew Serafin

и другие.

Journal of Clinical Medicine, Год журнала: 2024, Номер 13(2), С. 344 - 344

Опубликована: Янв. 7, 2024

The advent of artificial intelligence (AI) in medicine has transformed various medical specialties, including orthodontics. AI shown promising results enhancing the accuracy diagnoses, treatment planning, and predicting outcomes. Its usage orthodontic practices worldwide increased with availability applications tools. This review explores principles AI, its orthodontics, implementation clinical practice. A comprehensive literature was conducted, focusing on dental diagnostics, cephalometric evaluation, skeletal age determination, temporomandibular joint (TMJ) decision making, patient telemonitoring. Due to study heterogeneity, no meta-analysis possible. demonstrated high efficacy all these areas, but variations performance need for manual supervision suggest caution settings. complexity unpredictability algorithms call cautious regular validation. Continuous learning, proper governance, addressing privacy ethical concerns are crucial successful integration into

Язык: Английский

Процитировано

40
Deep learning-based PET image denoising and reconstruction: a review DOI Creative Commons
Fumio Hashimoto, Yuya Onishi,

Kibo Ote

и другие.

Radiological Physics and Technology, Год журнала: 2024, Номер 17(1), С. 24 - 46

Опубликована: Фев. 6, 2024

This review focuses on positron emission tomography (PET) imaging algorithms and traces the evolution of PET image reconstruction methods. First, we provide an overview conventional methods from filtered backprojection through to recent iterative algorithms, then deep learning for data up latest innovations within three main categories. The first category involves post-processing denoising. second comprises direct that learn mappings sinograms reconstructed images in end-to-end manner. third combine with neural-network enhancement. We discuss future perspectives technology.

Язык: Английский

Процитировано

29
Reducing pediatric total-body PET/CT imaging scan time with multimodal artificial intelligence technology DOI Creative Commons
Qiyang Zhang, Yingying Hu, Chao Zhou

и другие.

EJNMMI Physics, Год журнала: 2024, Номер 11(1)

Опубликована: Янв. 2, 2024

Abstract Objectives This study aims to decrease the scan time and enhance image quality in pediatric total-body PET imaging by utilizing multimodal artificial intelligence techniques. Methods A total of 270 patients who underwent PET/CT scans with a uEXPLORER at Sun Yat-sen University Cancer Center were retrospectively enrolled. 18 F-fluorodeoxyglucose ( F-FDG) was administered dose 3.7 MBq/kg an acquisition 600 s. Short-term images (acquired within 6, 15, 30, 60 150 s) obtained truncating list-mode data. three-dimensional (3D) neural network developed residual as basic structure, fusing low-dose CT prior information, which fed different scales. The short-term processed 3D generate full-length, high-dose images. nonlocal means method same without fused information used reference methods. performance model evaluated quantitative qualitative analyses. Results Multimodal techniques can significantly improve quality. When anatomical enhanced, s data produced comparable that full-time Conclusion effectively acquired using ultrashort times. has potential use sedation, guardian confidence, reduce probability motion artifacts.

Язык: Английский

Процитировано

11
Deep transformer-based personalized dosimetry from SPECT/CT images: a hybrid approach for [177Lu]Lu-DOTATATE radiopharmaceutical therapy DOI Creative Commons
Zahra Mansouri, Yazdan Salimi, Azadeh Akhavanallaf

и другие.

European Journal of Nuclear Medicine and Molecular Imaging, Год журнала: 2024, Номер 51(6), С. 1516 - 1529

Опубликована: Янв. 25, 2024

Abstract Purpose Accurate dosimetry is critical for ensuring the safety and efficacy of radiopharmaceutical therapies. In current clinical practice, MIRD formalisms are widely employed. However, with rapid advancement deep learning (DL) algorithms, there has been an increasing interest in leveraging calculation speed automation capabilities different tasks. We aimed to develop a hybrid transformer-based model that incorporates multiple voxel S -value (MSV) approach voxel-level [ 177 Lu]Lu-DOTATATE therapy. The goal was enhance performance achieve accuracy levels closely aligned Monte Carlo (MC) simulations, considered as standard reference. extended our analysis include (SSV MSV), thereby conducting comprehensive study. Methods used dataset consisting 22 patients undergoing up 4 cycles MC simulations were generate reference absorbed dose maps. addition, formalism approaches, namely, single (SSV) MSV techniques, performed. A UNEt TRansformer (UNETR) DL architecture trained using five-fold cross-validation MC-based Co-registered CT images fed into network input, whereas difference between (MC-MSV) set output. results then integrated revive Finally, maps generated by MSV, SSV, quantitatively compared at both level organ (organs risk lesions). Results showed slightly better (voxel relative absolute error (RAE) = 5.28 ± 1.32) RAE 5.54 1.4) outperformed SSV 7.8 3.02). Gamma pass rates 99.0 1.2%, 98.8 1.3%, 98.7 1.52% DL, respectively. computational time highest (~2 days single-bed SPECT study) DL-based other approaches terms efficiency (3 s SPECT). Organ-wise percent errors 1.44 3.05%, 1.18 2.65%, 1.15 2.5% respectively, lesion-absorbed doses. Conclusion developed fast accurate map generation, outperforming specifically heterogenous regions. achieved close gold potential implementation use on large-scale datasets.

Язык: Английский

Процитировано

11
Comparative Insight into Microglia/Macrophages-Associated Pathways in Glioblastoma and Alzheimer’s Disease DOI Open Access
Jian Shi, Shi‐Wei Huang

International Journal of Molecular Sciences, Год журнала: 2023, Номер 25(1), С. 16 - 16

Опубликована: Дек. 19, 2023

Microglia and macrophages are pivotal to the brain’s innate immune response have garnered considerable attention in context of glioblastoma (GBM) Alzheimer’s disease (AD) research. This review delineates complex roles these cells within neuropathological landscape, focusing on a range signaling pathways—namely, NF-κB, microRNAs (miRNAs), TREM2—that regulate behavior tumor-associated (TAMs) GBM disease-associated microglia (DAMs) AD. These pathways critical processes neuroinflammation, angiogenesis, apoptosis, which hallmarks We concentrate multifaceted regulation TAMs by NF-κB GBM, influence TREM2 DAMs’ responses amyloid-beta deposition, modulation both DAMs GBM- AD-related miRNAs. Incorporating recent advancements molecular biology, immunology, AI techniques, through detailed exploration mechanisms, we aim shed light their distinct overlapping regulatory functions The culminates with discussion how insights into miRNAs, may inform novel therapeutic approaches targeting neurodegenerative neoplastic conditions. comparative analysis underscores potential for new, targeted treatments, offering roadmap future research aimed at mitigating progression diseases.

Язык: Английский

Процитировано

20
AI-enhanced PET/CT image synthesis using CycleGAN for improved ovarian cancer imaging DOI Open Access

Amir Hossein Farshchitabrizi,

Mohammad Hossein Sadeghi,

Sedigheh Sina

и другие.

Polish Journal of Radiology, Год журнала: 2025, Номер 90, С. 26 - 35

Опубликована: Янв. 17, 2025

Purpose Ovarian cancer is the fifth fatal among women. Positron emission tomography (PET), which offers detailed metabolic data, can be effectively used for early screening. However, proper attenuation correction essential interpreting data obtained by this imaging modality. Computed (CT) commonly performed alongside PET correction. This approach may introduce some issues in spatial alignment and registration of images two modalities. study aims to perform image using generative adversarial networks (GANs), without additional CT imaging. Material methods The PET/CT from 55 ovarian patients were study. Three GAN architectures: Conditional GAN, Wasserstein CycleGAN, evaluated statistical performance each model was assessed calculating mean squared error (MSE) absolute (MAE). radiological assessments models comparing standardised uptake value Hounsfield unit values whole body selected organs, synthetic real images. Results Based on results, CycleGAN demonstrated effective pseudo-CT generation, with high accuracy. MAE MSE all 2.15 ± 0.34 3.14 0.56, respectively. For reconstruction, such found 4.17 0.96 5.66 1.01, Conclusions results showed potential deep learning reducing radiation exposure improving quality Further refinement clinical validation are needed full applicability.

Язык: Английский

Процитировано

1
Quantitation of dynamic total-body PET imaging: recent developments and future perspectives DOI Creative Commons
Fengyun Gu, Qi Wu

European Journal of Nuclear Medicine and Molecular Imaging, Год журнала: 2023, Номер 50(12), С. 3538 - 3557

Опубликована: Июль 18, 2023

Positron emission tomography (PET) scanning is an important diagnostic imaging technique used in disease diagnosis, therapy planning, treatment monitoring, and medical research. The standardized uptake value (SUV) obtained at a single time frame has been widely employed clinical practice. Well beyond this simple static measure, more detailed metabolic information can be recovered from dynamic PET scans, followed by the recovery of arterial input function application appropriate tracer kinetic models. Many efforts have devoted to development quantitative techniques over last couple decades.

Язык: Английский

Процитировано

17
SPECT/CT, PET/CT and PET/MRI: oncologic and infectious applications and protocol considerations DOI
Stephan D. Voss

Pediatric Radiology, Год журнала: 2023, Номер 53(7), С. 1443 - 1453

Опубликована: Март 11, 2023

Язык: Английский

Процитировано

14
From FDG and beyond: the evolving potential of nuclear medicine DOI
Kenji Hirata, Koji Kamagata, Daiju Ueda

и другие.

Annals of Nuclear Medicine, Год журнала: 2023, Номер 37(11), С. 583 - 595

Опубликована: Сен. 25, 2023

Язык: Английский

Процитировано

14
Artificial Intelligence’s Transformative Role in Illuminating Brain Function in Long COVID Patients Using PET/FDG DOI Creative Commons

Thorsten Rudroff

Brain Sciences, Год журнала: 2024, Номер 14(1), С. 73 - 73

Опубликована: Янв. 10, 2024

Cutting-edge brain imaging techniques, particularly positron emission tomography with Fluorodeoxyglucose (PET/FDG), are being used in conjunction Artificial Intelligence (AI) to shed light on the neurological symptoms associated Long COVID. AI, deep learning algorithms such as convolutional neural networks (CNN) and generative adversarial (GAN), plays a transformative role analyzing PET scans, identifying subtle metabolic changes, offering more comprehensive understanding of COVID's impact brain. It aids early detection abnormal metabolism patterns, enabling personalized treatment plans. Moreover, AI assists predicting progression symptoms, refining patient care, accelerating COVID research. can uncover new insights, identify biomarkers, streamline drug discovery. Additionally, application extends non-invasive stimulation transcranial direct current (tDCS), which have shown promise alleviating symptoms. optimize protocols by neuroimaging data, individual responses, automating adjustments real time. While potential benefits vast, ethical considerations data privacy must be rigorously addressed. The synergy scans research offers hope mitigating complexities this condition.

Язык: Английский

Процитировано

6