Nuklearmedizin. Nuclear medicine最新文献

Purpose:  The aim of this study was to investigate the potential of multiparametric ¹⁸F-FDG PET/MR imaging as a platform for radiomics analysis and machine learning algorithms based on primary cervical cancers to predict N- and M-stage in patients.

Materials and methods:  A total of 30 patients with histopathological confirmation of primary and untreated cervical cancer were prospectively enrolled for a multiparametric ¹⁸F-FDG PET/MR examination, comprising a dedicated protocol for imaging of the female pelvis. The primary tumor in the uterine cervix was manually segmented on post-contrast T1-weighted images. Quantitative features were extracted from the segmented tumors using the Radiomic Image Processing Toolbox for the R software environment for statistical computing and graphics. 45 different image features were calculated from non-enhanced as well as post-contrast T1-weighted TSE images, T2-weighted TSE images, the ADC map, the parametric Ktrans, Kep, Ve and iAUC maps and PET images, respectively. Statistical analysis and modeling was performed using Python 3.5 and the scikit-learn software machine learning library for the Python programming language.

Results:  Prediction of M-stage was superior when compared to N-stage. Prediction of M-stage using SVM with SVM-RFE as feature selection obtained the highest performance providing sensitivity of 91 % and specificity of 92 %. Using receiver operating characteristic (ROC) analysis of the pooled predictions, the area under the curve (AUC) was 0.97. Prediction of N-stage using RBF-SVM with MIFS as feature selection reached sensitivity of 83 %, specificity of 67 % and an AUC of 0.82.

Conclusion:  M- and N-stage can be predicted based on isolated radiomics analyses of the primary tumor in cervical cancers, thus serving as a template for noninvasive tumor phenotyping and patient stratification using high-dimensional feature vectors extracted from multiparametric PET/MRI data.

Key points:   · Radiomics analysis based on multiparametric PET/MRI enables prediction of the metastatic status of cervical cancers. · Prediction of M-stage is superior to N-stage. · Multiparametric PET/MRI displays a valuable platform for radiomics analyses .

This version of the guideline for radioiodine therapy of benign thyroid disorders is an update of the version, which was published by the German Society of Nuclear Medicine (Deutsche Gesellschaft für Nuklearmedizin, DGN) in co-ordination with the German Society of Endocrinology (Deutsche Gesellschaft für Endokrinologie, DGE, Sektion Schilddrüse) and the German Society of General- and Visceral-Surgery (Deutsche Gesellschaft für Allgemein- und Viszeralchirurgie, DGAV) in 2015. This guideline was harmonized with the recommendations of the European Association of Nuclear Medicine (EANM). According to the German "Directive on Radiation Protection in Medicine" the physician specialised in nuclear medicine ("Fachkunde in der Therapie mit offenen radioaktiven Stoffen") is responsible for the justification to treat with radioiodine. Therefore, relevant medical indications for radioiodine therapy and alternative therapeutic options are discussed within the guideline. This procedure guideline is developed in the consensus of an expert group. This fulfils the level S1 (first step) within the German classification of Clinical Practice Guidelines.

Purpose:  To evaluate the recommendations for or against fine needle biopsy (FNB) of hypofunctioning thyroid nodules (TNs) using of five different Ultrasound (US) -based risk stratification systems (RSSs).

Methods:  German multicenter study with 563 TNs (≥ 10 mm) in 534 patients who underwent thyroid US and surgery. All TNs were evaluated with ACR TI-RADS, EU-TIRADS, ATA, K-TIRADS 2016 and modified K-TIRADS 2021. A correct recommendation was defined as: malignant TN with recommendation for FNB (appropriate) or benign TN without recommendation for FNB (avoided). An incorrect recommendation was defined as: malignant TN without recommendation for FNB (missed) or benign TN with recommendation for FNB (unnecessary).

Results:  ACR TI-RADS demonstrated the highest rate of correct (42.3 %) and lowest rate of incorrect recommendations (57.7 %). The other RRSs showed similar results for correct (26.5 %-35.7 %) and incorrect (64.3 %-73.5 %) recommendations. ACR TI-RADS demonstrated the lowest rate of unnecessary (73.4 %) and the highest rate of appropriate (26.6 %) FNB recommendation. For other RSSs, the rates of unnecessary and appropriate FNB were between 75.2 %-77.1 % and 22.9 %-24.8 %. The lowest rate of missed FNB (14.7 %) and the highest rate of avoided FNB (85.3 %) was found for ACR TI-RADS. For the other RSSs, the rates of missed and avoided FNB were between 17.8 %-26.9 % and 73.1 %-82.2 %. When the size cutoff was disregarded, an increase of correct recommendations and a decrease of incorrect recommendations was observed for all RSSs.

Conclusion:  The RSSs vary in their ability to correctly recommend for or against FNB. An understanding of the impact of nodule size cutoffs seems necessary for the future of TIRADS.

Purpose: The role of fibroblast activation protein inhibitor (FAPI) PET CT scan is not well documented in papillary thyroid cancer (PTC) patients. Patients with radioiodine refractory PTC and high thyroglobulin levels need PET/CT scan which is generally done by 18F FDG. In the current study, the diagnostic performance of 68Ga FAPI and FDG PET/CT scans were compared head to head in patients with radioiodine refractory PTC.

Method: Fourteen patients with negative whole body Iodine scans and high thyroglobulin levels underwent whole body PET scans with, respectively, 120-310 and 145-370 MBq 68Ga FAPI-46 and 18F FDG. SUVmax of the back ground in the blood pool and liver and the hottest, largest and average neck, mediastinum, lung and bone lesions were calculated and compared.

Result: Ten patients had at least one active (SUVmax>blood pool) lesion similarly in two scans. The liver and blood pool SUVmax values were 1.25(0.2) and 1.7(0.2) in FAPI and 2.65(0.2) and 2.0(0.2) in FDG PET images, respectively. The difference was significant (p=0.001). Standard SUV of the hottest lesion to liver was above 3 in all FAPI scans but in half of FDG scans. Target lesion number and intensity were similar between two PET studies but in a patient out of 5 pulmonary metastatic patients, pulmonary nodules were negative (SUVmax=0.9) in FDG while positive (SUVmax= 3.8) in FAPI images (i.e. 20% patient upstaged).

Conclusion: FAPI accumulates in the recurrent and metastatic lesions of patients with Iodine refractory PTC at least as well as FDG with particular privileges as lower injected activity and lower back ground.

Tracer kinetic modelling based on dynamic PET is an important field of Nuclear Medicine for quantitative functional imaging. Yet, its implementation in clinical routine has been constrained by its complexity and computational costs. Machine learning poses an opportunity to improve modelling processes in terms of arterial input function prediction, the prediction of kinetic modelling parameters and model selection in both clinical and preclinical studies while reducing processing time. Moreover, it can help improving kinetic modelling data used in downstream tasks such as tumor detection. In this review, we introduce the basics of tracer kinetic modelling and present a literature review of original works and conference papers using machine learning methods in this field.

Nuclear imaging techniques such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) in combination with computed tomography (CT) are established imaging modalities in clinical practice, particularly for oncological problems. Due to a multitude of manufacturers, different measurement protocols, local demographic or clinical workflow variations as well as various available reconstruction and analysis software, very heterogeneous datasets are generated. This review article examines the current state of interoperability and harmonisation of image data and related clinical data in the field of nuclear medicine. Various approaches and standards to improve data compatibility and integration are discussed. These include, for example, structured clinical history, standardisation of image acquisition and reconstruction as well as standardised preparation of image data for evaluation. Approaches to improve data acquisition, storage and analysis will be presented. Furthermore, approaches are presented to prepare the datasets in such a way that they become usable for projects applying artificial intelligence (AI) (machine learning, deep learning, etc.). This review article concludes with an outlook on future developments and trends related to AI in nuclear medicine, including a brief research of commercial solutions.

Aim: Despite a vast number of articles on radiomics and machine learning in positron emission tomography (PET) imaging, clinical applicability remains limited, partly owing to poor methodological quality. We therefore systematically investigated the methodology described in publications on radiomics and machine learning for PET-based outcome prediction.

Methods: A systematic search for original articles was run on PubMed. All articles were rated according to 17 criteria proposed by the authors. Criteria with >2 rating categories were binarized into "adequate" or "inadequate". The association between the number of "adequate" criteria per article and the date of publication was examined.

Results: One hundred articles were identified (published between 07/2017 and 09/2023). The median proportion of articles per criterion that were rated "adequate" was 65% (range: 23-98%). Nineteen articles (19%) mentioned neither a test cohort nor cross-validation to separate training from testing. The median number of criteria with an "adequate" rating per article was 12.5 out of 17 (range, 4-17), and this did not increase with later dates of publication (Spearman's rho, 0.094; p = 0.35). In 22 articles (22%), less than half of the items were rated "adequate". Only 8% of articles published the source code, and 10% made the dataset openly available.

Conclusion: Among the articles investigated, methodological weaknesses have been identified, and the degree of compliance with recommendations on methodological quality and reporting shows potential for improvement. Better adherence to established guidelines could increase the clinical significance of radiomics and machine learning for PET-based outcome prediction and finally lead to the widespread use in routine clinical practice.