CD200+ fibroblasts form a pro-resolving mesenchymal network in arthritis.

Fibroblasts are important regulators of inflammation, but whether fibroblasts change phenotype during resolution of inflammation is not clear. Here we use positron emission tomography to detect fibroblast activation protein (FAP) as a means to visualize fibroblast activation in vivo during inflammation in humans. While tracer accumulation is high in active arthritis, it decreases after tumor necrosis factor and interleukin-17A inhibition. Biopsy-based single-cell RNA-sequencing analyses in experimental arthritis show that FAP signal reduction reflects a phenotypic switch from pro-inflammatory MMP3+/IL6+ fibroblasts (high FAP internalization) to pro-resolving CD200+DKK3+ fibroblasts (low FAP internalization). Spatial transcriptomics of human joints indicates that pro-resolving niches of CD200+DKK3+ fibroblasts cluster with type 2 innate lymphoid cells, whereas MMP3+/IL6+ fibroblasts colocalize with inflammatory immune cells. CD200+DKK3+ fibroblasts stabilized the type 2 innate lymphoid cell phenotype and induced resolution of arthritis via CD200-CD200R1 signaling. Taken together, these data suggest a dynamic molecular regulation of the mesenchymal compartment during resolution of inflammation.

Metabolic and molecular imaging in inflammatory arthritis.

It is known that metabolic shifts and tissue remodelling precede the development of visible inflammation and structural organ damage in inflammatory rheumatic diseases such as the inflammatory arthritides. As such, visualising and measuring metabolic tissue activity could be useful to identify biomarkers of disease activity already in a very early phase. Recent advances in imaging have led to the development of so-called 'metabolic imaging' tools that can detect these changes in metabolism in an increasingly accurate manner and non-invasively.Nuclear imaging techniques such as 18F-D-glucose and fibroblast activation protein inhibitor-labelled positron emission tomography are increasingly used and have yielded impressing results in the visualisation (including whole-body staging) of inflammatory changes in both early and established arthritis. Furthermore, optical imaging-based bedside techniques such as multispectral optoacoustic tomography and fluorescence optical imaging are advancing our understanding of arthritis by identifying intra-articular metabolic changes that correlate with the onset of inflammation with high precision and without the need of ionising radiation.Metabolic imaging holds great potential for improving the management of patients with inflammatory arthritis by contributing to early disease interception and improving diagnostic accuracy, thereby paving the way for a more personalised approach to therapy strategies including preventive strategies. In this narrative review, we discuss state-of-the-art metabolic imaging methods used in the assessment of arthritis and inflammation, and we advocate for more extensive research endeavours to elucidate their full field of application in rheumatology.

Imaging in inflammatory arthritis: progress towards precision medicine.

Imaging techniques such as ultrasonography and MRI have gained ground in the diagnosis and management of inflammatory arthritis, as these imaging modalities allow a sensitive assessment of musculoskeletal inflammation and damage. However, these techniques cannot discriminate between disease subsets and are currently unable to deliver an accurate prediction of disease progression and therapeutic response in individual patients. This major shortcoming of today's technology hinders a targeted and personalized patient management approach. Technological advances in the areas of high-resolution imaging (for example, high-resolution peripheral quantitative computed tomography and ultra-high field MRI), functional and molecular-based imaging (such as chemical exchange saturation transfer MRI, positron emission tomography, fluorescence optical imaging, optoacoustic imaging and contrast-enhanced ultrasonography) and artificial intelligence-based data analysis could help to tackle these challenges. These new imaging approaches offer detailed anatomical delineation and an in vivo and non-invasive evaluation of the immunometabolic status of inflammatory reactions, thereby facilitating an in-depth characterization of inflammation. By means of these developments, the aim of earlier diagnosis, enhanced monitoring and, ultimately, a personalized treatment strategy looms closer.

Ultrasound characteristics of follicular and parafollicular thyroid neoplasms: diagnostic performance of artificial neural network.

BACKGROUND: Ultrasound is the first-line imaging modality for detection and classification of thyroid nodules. Certain features observable by ultrasound have recently been equated with potential malignancy. This retrospective cohort study was conducted to test the hypothesis that radiomics of the four categorical divisions (medullary [MTC], papillary [PTC], or follicular [FTC] carcinoma and follicular thyroid adenoma [FTA]) demonstrate distinctive sonographic characteristics. Using an artificial neural network model for proof of concept, these sonographic features served as input. METHODS: A total of 148 patients were enrolled for study, all with confirmed thyroid pathology in one of the four named categories. Preoperative ultrasound profiles were obtained via standardized protocols. The neural network consisted of seven input neurons; three hidden layers with 50, 250, and 100 neurons, respectively; and one output layer. RESULTS: Radiomics of contour, structure, and calcifications differed significantly according to nodule type (p = 0.025, p = 0.032, and p = 0.0002, respectively). Levels of accuracy shown by artificial neural network analysis in discriminating among categories ranged from 0.59 to 0.98 (95% confidence interval [CI]: 0.57-0.99), with positive and negative predictive ranges of 0.41-0.99 and 0.78-0.97, respectively. CONCLUSIONS: Our data indicate that some MTCs, PTCs, FTCs, and FTAs have distinctive sonographic characteristics. However, a significant overlap of these characteristics may impede an explicit classification. Further prospective investigations involving larger patient and nodule numbers and multicenter access should be pursued to determine if neural networks of this sort are beneficial, helping to classify neoplasms of the thyroid gland.

Ability of 18F-FDG Positron Emission Tomography Radiomics and Machine Learning in Predicting KRAS Mutation Status in Therapy-Naive Lung Adenocarcinoma.

OBJECTIVE: Considering the essential role of KRAS mutation in NSCLC and the limited experience of PET radiomic features in KRAS mutation, a prediction model was built in our current analysis. Our model aims to evaluate the status of KRAS mutants in lung adenocarcinoma by combining PET radiomics and machine learning. METHOD: Patients were retrospectively selected from our database and screened from the NSCLC radiogenomic dataset from TCIA. The dataset was randomly divided into three subgroups. Two open-source software programs, 3D Slicer and Python, were used to segment lung tumours and extract radiomic features from 18F-FDG-PET images. Feature selection was performed by the Mann-Whitney U test, Spearman's rank correlation coefficient, and RFE. Logistic regression was used to build the prediction models. AUCs from ROCs were used to compare the predictive abilities of the models. Calibration plots were obtained to examine the agreements of observed and predictive values in the validation and testing groups. DCA curves were performed to check the clinical impact of the best model. Finally, a nomogram was obtained to present the selected model. RESULTS: One hundred and nineteen patients with lung adenocarcinoma were included in our study. The whole group was divided into three datasets: a training set (n = 96), a validation set (n = 11), and a testing set (n = 12). In total, 1781 radiomic features were extracted from PET images. One hundred sixty-three predictive models were established according to each original feature group and their combinations. After model comparison and selection, one model, including wHLH_fo_IR, wHLH_glrlm_SRHGLE, wHLH_glszm_SAHGLE, and smoking habits, was validated with the highest predictive value. The model obtained AUCs of 0.731 (95% CI: 0.619~0.843), 0.750 (95% CI: 0.248~1.000), and 0.750 (95% CI: 0.448~1.000) in the training set, the validation set and the testing set, respectively. Results from calibration plots in validation and testing groups indicated that there was no departure between observed and predictive values in the two datasets (p = 0.377 and 0.861, respectively). CONCLUSIONS: Our model combining 18F-FDG-PET radiomics and machine learning indicated a good predictive ability of KRAS status in lung adenocarcinoma. It may be a helpful non-invasive method to screen the KRAS mutation status of heterogenous lung adenocarcinoma before selected biopsy sampling.

68Ga-FAPI PET/CT Interobserver Agreement on Tumor Assessment: An International Multicenter Prospective Study.

68Ga-fibroblast activation protein inhibitors (FAPIs) are promising radiotracers for cancer imaging, with emerging data in the recent years. Nonetheless, the interobserver agreement on 68Ga-FAPI PET/CT study interpretations in cancer patients remains poorly understood. Methods: 68Ga-FAPI PET/CT was performed on 50 patients with various tumor entities (sarcoma [n = 10], colorectal cancer [n = 10], pancreatic adenocarcinoma [n = 10], genitourinary cancer [n = 10], and other types of cancer [n = 10]). Fifteen masked observers reviewed and interpreted the images using a standardized approach for local, local nodal, and metastatic involvement. Observers were grouped by experience as having a low (<30 prior 68Ga-FAPI PET/CT studies; n = 5), intermediate (30-300 studies; n = 5), or high level of experience (>300 studies; n = 5). Two independent readers with a high level of experience and unmasked to clinical information, histopathology, tumor markers, and follow-up imaging (CT/MRI or PET/CT) served as the standard of reference (SOR). Observer groups were compared by overall agreement (percentage of patients matching SOR) and Fleiss κ with mean and corresponding 95% CI. We defined acceptable agreement as a κ value of at least 0.6 (substantial or higher) and acceptable accuracy as at least 80%. Results: Highly experienced observers agreed substantially on all categories (primary tumor: κ = 0.71; 95% CI, 0.71-0.71; local nodal involvement: κ = 0.62; 95% CI, 0.61-0.62; distant metastasis: κ = 0.75; 95% CI, 0.75-0.75), whereas observers with intermediate experience showed substantial agreement on primary tumor (κ = 0.73; 95% CI, 0.73-0.73) and distant metastasis (κ = 0.65; 95% CI, 0.65-0.65) but moderate agreement on local nodal stages (κ = 0.55; 95% CI, 0.55-0.55). Observers with low experience had moderate agreement on all categories (primary tumor: κ = 0.57; 95% CI, 0.57-0.58; local nodal involvement: κ = 0.51; 95% CI, 0.51-0.52; distant metastasis: κ = 0.54; 95% CI, 0.53-0.54). Compared with SOR, the accuracy for readers with high, intermediate, and low experience was 85%, 83%, and 78%, respectively. In summary, only highly experienced readers showed substantial agreement and a diagnostic accuracy of at least 80% in all categories. Conclusion: The interpretation of 68Ga-FAPI PET/CT for cancer imaging had substantial reproducibility and accuracy among highly experienced observers only, especially for local nodal and metastatic assessments. Therefore, for accurate interpretation of different tumor entities and pitfalls, we recommend training or experience with at least 300 representative scans for future clinical readers.

Adverse events unlikely after fine-needle aspiration biopsies of thyroid nodules in patients on low-dose aspirin: a prospective controlled systematic single center analysis.

AIM: Our aim was to test the assertion that in terms of rate or severity level, adverse events (AEs) after fine-needle aspiration biopsies (FNABs) of thyroid nodules are unfazed by daily low-dose (100 mg) aspirin (acetylsalicylic acid, ASA) intake. METHODS: We selected 268 patients for study, grouped as ASA-treated (PASA, n=78) or control (PCtrl, n=190) subjects. Controls received no antithrombotic medication. AE rates and severities were then analyzed based on patient- and nodule-related factors. We also compared group rates of non-diagnostic cytology results. RESULTS: AEs arising after FNABs (PASA, 5%; PCtrl, 8%) did not differ significantly by group in rate (p=0.4873) or severity level (p=0.3399). All were classifiable as minor incidents, none warranting any intervention. CONCLUSIONS: The data from the present study suggest, AEs after FNABs of thyroid nodules seldom occur and qualify as minor incidents. Such procedures may be safely conducted in patients taking daily low-dose ASA. There is no evidence to support preemptive therapeutic withdrawal.

Assessment of myocardial fibrosis in patients with systemic sclerosis using [68Ga]Ga-FAPI-04-PET-CT.

PURPOSE: Myocardial fibrosis (MF) is a factor of poor prognosis in systemic sclerosis (SSc). Direct in-vivo visualization of fibroblast activation as early readout of MF has not been feasible to date. Here, we characterize 68Gallium-labeled-Fibroblast-Activation-Inhibitor-04 ([68Ga]Ga-FAPI-04)-PET-CT as a diagnostic tool in SSc-related MF. METHODS: In this proof-of-concept trial, six SSc patients with and eight without MF of the EUSTAR cohort Erlangen underwent [68Ga]Ga-FAPI-04-PET-CT and cardiac MRI (cMRI) and clinical and serologic investigations just before baseline and during follow-up between January 2020 and December 2020. Myocardial biopsy was performed as clinically indicated. RESULTS: [68Ga]Ga-FAPI-04 tracer uptake was increased in SSc-related MF with higher uptake in SSc patients with arrhythmias, elevated serum-NT-pro-BNP, and increased late gadolinium enhancement (LGE) in cMRI. Histologically, myocardial biopsies from cMRI- and [68Ga]Ga-FAPI-04-positive regions confirmed the accumulation of FAP+ fibroblasts surrounded by collagen deposits. We observed similar but not equal spatial distributions of [68Ga]Ga-FAPI-04 uptake and quantitative cMRI-based techniques. Using sequential [68Ga]Ga-FAPI-04-PET-CTs, we observed dynamic changes of [68Ga]Ga-FAPI-04 uptake associated with changes in the activity of SSc-related MF, while cMRI parameters remained stable after regression of molecular activity and rather indicated tissue damage. CONCLUSIONS: We present first in-human evidence that [68Ga]Ga-FAPI-04 uptake visualizes fibroblast activation in SSc-related MF and may be a diagnostic option to monitor cardiac fibroblast activity in situ.

Eligibility for 177Lu-PSMA Therapy Depends on the Choice of Companion Diagnostic Tracer: A Comparison of 68Ga-PSMA-11 and 99mTc-MIP-1404 in Metastatic Castration-Resistant Prostate Cancer.

177Lu-prostate-specific membrane antigen-617 (177Lu-PSMA-617) is an effective therapy for metastatic castration-resistant prostate cancer (mCRPC), with evidence of improved survival over standard care. The VISION trial inclusion criteria required a metastatic lesion-to-liver ratio of greater than 1 on 68Ga-PSMA-11 PET scans. We aimed to determine whether an equivalent ratio is suitable for a SPECT tracer, 99mTc-MIP-1404, and to compare lesion and lesion-to-normal-organ ratios between the 2 radiotracers. Methods: Two cohorts of patients with mCRPC matched for age, prostate-specific antigen level, and total Gleason score, with either 99mTc-MIP-1404 SPECT/CT (n = 25) or 68Ga-PSMA-11 PET/CT (n = 25) scans, were included for analysis. Up to 3 lesions in each site (prostate/prostate bed, lymph nodes, bone and soft-tissue metastases) as well as normal liver, parotid gland, spleen, and mediastinal blood-pool SUVmax were measured. Results: 99mTc-MIP-1404 SPECT lesion SUVmax was not significantly different from 68Ga-PSMA-11 PET (median, 18.2 vs. 17.3; P = 0.93). However, 99mTc-MIP-1404 liver SUVmax was higher (median, 8.5 vs. 5.8; P = 0.002) and lesion-to-liver ratios were lower (median, 2.7 vs. 3.5; P = 0.009). There was no significant difference in parotid gland or splenic SUVmax or lesion-to-parotid gland ratios between the 2 tracers although there was a small difference in lesion-to-spleen ratios (P = 0.034). Conclusion: There are differences in biodistribution and, in particular, liver activity, between 68Ga-PSMA-11 and 99mTc-MIP-1404. Therefore, if 99mTc-MIP-1404 is used to assess eligibility for 177Lu-PSMA-617 therapy, a lower adjusted lesion-to-liver ratio should be used.

Fibroblast Activation Protein Inhibitor Imaging in Nonmalignant Diseases: A New Perspective for Molecular Imaging.

Fibroblast activation protein-α (FAP-α) is a type II transmembrane glycoprotein that is overexpressed in activated fibroblasts such as those in the stroma of tumors or in the fibrotic processes accompanying various benign diseases. The recent development and clinical implementation of radiolabeled quinolone-based tracers suitable for PET that act as FAP inhibitors (FAPIs) have opened a new perspective in molecular imaging. Although multiple studies have investigated the use of FAPI imaging in cancer, evidence concerning its use in nonmalignant diseases is still scarce. Herein, we provide a comprehensive review of FAPI imaging in nonmalignant diseases to clarify the current and potential role of this class of molecules in nuclear medicine.

Cinematic rendering in rheumatic diseases-Photorealistic depiction of pathologies improves disease understanding for patients.

Background: Patient education is crucial for successful chronic disease management. Current education material for rheumatic patients however rarely includes images of disease pathologies, limiting patients' disease understanding. Cinematic rendering (CR) is a new tool that allows segmentation of standard medical images (DICOMs) into pictures that illustrate disease pathologies in a photorealistic way. Thus CR has the potential to simplify and improve the explanation of disease pathologies, disease activity and disease consequences and could therefore be a valuable tool to effectively educate and inform patients about their rheumatic and musculoskeletal disease (RMD). Objectives: To examine the feasibility of creating photorealistic images using CR from RMD patients depicting typical rheumatic disease pathologies and, in a second step to investigate the patient-perceived educational potential of these photorealistic images in clinical routine. Methods: We selected conventional, high-resolution (HR) and positron emission tomography (PET) computed tomography (CT) images of patients with rheumatoid arthritis (RA), psoriatic arthritis (PsA), axial spondyloarthritis (axSpA), and giant cell arteritis (GCA) that showed typical respective disease pathologies. These images were segmented using CR technique. In a prospective study, physicians used CR-enhanced and conventional original images to explain the depicted pathognomonic pathologies to patients with the respective rheumatic disease. Patients were then asked to complete a questionnaire evaluating the perceived usefulness of being presented with CR-enhanced images to better understand their underlying disease. Results: CR images were successfully generated from above mentioned CT methods. Pathologies such as bone erosions, bony spurs, bone loss, ankylosis, and PET-based inflammation could be visualized in photorealistic detail. A total of 79 patients (61% females) with rheumatic diseases (RA 29%, PsA 29%, axSpA 24%, GCA 18%) were interviewed and answered the quantitative questionnaire. Mean age was 55.4 ± 12.6 years. Irrespective of disease, all patients agreed or highly agreed that CR-based images help to improve disease understanding, should be shown at disease onset, provide a rationale to regularly take medication and would like to have access to their own CR-enhanced images. Conclusion: Conventional disease images can successfully be turned into photorealistic disease depictions using CR. Patients perceived CR images as a valuable addition to current patient education, enabling personalized disease education and potentially increased medication adherence.

Standardized 18F-FDG PET/CT radiomic features provide information on PD-L1 expression status in treatment-naïve patients with non-small cell lung cancer.

PURPOSE: To study the relationship between standardized 18F-FDG PET/CT radiomic features and clinicopathological variables and programmed death ligand-1 (PD-L1) expression status in non-small cell lung cancer (NSCLC) patients. METHODS: 58 NSCLC patients with preoperative 18F-FDG PET/CT scans and postoperative results of PD-L1 expression were retrospectively analysed. A standardized, open-source software was used to extract 86 radiomic features from PET and low-dose CT images. Univariate analysis and multivariate logistic regression were used to find independent predictors of PD-L1 expression. The Area Under the Curve (AUC) of receiver operating characteristic (ROC) curve was used to compare the ability of variables and their combination in predicting PD-L1 expression. RESULTS: Multivariate logistic regression resulted in the PET radiomic feature GLRLM_LGRE (Odds Rate (OR): 0.300 vs 0.114, 95% confidence interval (CI): 0.096-0.931 vs 0.021-0.616, in NSCLC and adenocarcinoma respectively) and the CT radiomic feature GLZLM_SZE (OR: 3.338 vs 7.504, 95%CI: 1.074-10.375 vs 1.382-40.755, in NSCLC and adenocarcinoma respectively), being independent predictors of PD-L1 status. In NSCLC group, after adjusting for gender and histology, the PET radiomic feature GLRLM_LGRE (OR: 0.282, 95%CI: 0.085-0.936) remained an independent predictor for PD-L1 status. In the adenocarcinoma group, when adjusting for gender the PET radiomic feature GLRLM_LGRE (OR: 0.115, 95%CI: 0.021-0.631) and the CT radiomic feature GLZLM_SZE (OR: 7.343, 95%CI: 1.285-41.965) remained associated with PD-L1 expression. CONCLUSION: NSCLC and adenocarcinoma with PD-L1 expression show higher tumour heterogeneity. Heterogeneity-related 18F-FDG PET and CT radiomic features showed good ability to non-invasively predict PD-L1 expression.

Targeting of fibroblast activation protein in rheumatoid arthritis patients: imaging and ex vivo photodynamic therapy.

OBJECTIVE: Activated synovial fibroblasts are key effector cells in RA. Selectively depleting these based upon their expression of fibroblast activation protein (FAP) is an attractive therapeutic approach. Here we introduce FAP imaging of inflamed joints using 68Ga-FAPI-04 in a RA patient, and aim to assess feasibility of anti-FAP targeted photodynamic therapy (FAP-tPDT) ex vivo using 28H1-IRDye700DX on RA synovial explants. METHODS: Remnant synovial tissue from RA patients was processed into 6 mm biopsies and, from several patients, into primary fibroblast cell cultures. Both were treated using FAP-tPDT. Cell viability was measured in fibroblast cultures and biopsies were evaluated for histological markers of cell damage. Selectivity of the effect of FAP-tPDT was assessed using flow cytometry on primary fibroblasts and co-cultured macrophages. Additionally, one RA patient intravenously received 68Ga-FAPI-04 and was scanned using PET/CT imaging. RESULTS: In the RA patient, FAPI-04 PET imaging showed high accumulation of the tracer in arthritic joints with very low background signal. In vitro, FAP-tPDT induced cell death in primary RA synovial fibroblasts in a light dose-dependent manner. An upregulation of cell damage markers was observed in the synovial biopsies after FAP-tPDT. No significant effects of FAP-tPDT were noted on macrophages after FAP-tPDT of neighbouring fibroblasts. CONCLUSION: In this study the feasibility of selective FAP-tPDT in synovium of rheumatoid arthritis patients ex vivo is demonstrated. Furthermore, this study provides the first indication that FAP-targeted PET/CT can be used to image arthritic joints, an important step towards application of FAP-tPDT as a targeted locoregional therapy for RA.

Quantification of Translocation-Specific ctDNA Provides an Integrating Parameter for Early Assessment of Treatment Response and Risk Stratification in Ewing Sarcoma.

PURPOSE: We evaluated the predictive and prognostic value of circulating tumor DNA (ctDNA) in patients with Ewing sarcoma (EWS) treated in the EWING2008 trial. EXPERIMENTAL DESIGN: Plasma samples from 102 patients with EWS enrolled in the EWING2008 trial were obtained before and during induction chemotherapy. Genomic EWSR1 fusion sequence spanning primers and probes were used for highly specific and sensitive quantification of the levels of ctDNA by digital droplet PCR. ctDNA levels were correlated to established clinical risk factors and outcome parameters. RESULTS: Pretreatment ctDNA copy numbers were correlated with event-free and overall survival. The reduction in ctDNA levels below the detection limit was observed in most cases after only two blocks of vincristine, ifosfamide, doxorubicin, and etoposide (VIDE) induction chemotherapy. The persistence of ctDNA after two VIDE blocks was a strong predictor of poor outcomes. ctDNA levels correlated well with most established clinical risk factors; an inverse correlation was found only for the histologic response to induction therapy. ctDNA levels did not provide simple representations of tumor volume, but integrated information from various tumor characteristics represented an independent EWS tumor marker with predictive and prognostic value. CONCLUSIONS: ctDNA copy number in the plasma of patients with EWS is a quantifiable parameter for early risk stratification and can be used as a dynamic noninvasive biomarker for early prediction of treatment response and outcome of patients.

Advanced thyroid carcinomas: neural network analysis of ultrasonographic characteristics.

BACKGROUND: Ultrasound is the first-line imaging modality for detection and classification of thyroid nodules. Certain characteristics observable by ultrasound have recently been identified that may indicate malignancy. This retrospective cohort study was conducted to test the hypothesis that advanced thyroid carcinomas show distinctive clinical and sonographic characteristics. Using a neural network model as proof of concept, nine clinical/sonographic features served as input. METHODS: All 96 study enrollees had histologically confirmed thyroid carcinomas, categorized (n = 32, each) as follows: group 1, advanced carcinoma (ADV) marked by local invasion or distant metastasis; group 2, non-advanced papillary carcinoma (PTC); or group 3, non-advanced follicular carcinoma (FTC). Preoperative ultrasound profiles were obtained via standardized protocols. The neural network had nine input neurons and one hidden layer. RESULTS: Mean age and the number of male patients in group 1 were significantly higher compared with groups 2 (p = 0.005) or 3 (p <  0.001). On ultrasound, tumors of larger volume and irregular shape were observed significantly more often in group 1 compared with groups 2 (p <  0.001) or 3 (p ≤ 0.01). Network accuracy in discriminating advanced vs. non-advanced tumors was 84.4% (95% confidence interval [CI]: 75.5-91), with positive and negative predictive values of 87.1% (95% CI: 70.2-96.4) and 92.3% (95% CI: 83.0-97.5), respectively. CONCLUSIONS: Our study has shown some evidence that advanced thyroid tumors demonstrate distinctive clinical and sonographic characteristics. Further prospective investigations with larger numbers of patients and multicenter design should be carried out to show whether a neural network incorporating these features may be an asset, helping to classify malignancies of the thyroid gland.