Radiomics Analysis of [18F]FDG PET/CT Thyroid Incidentalomas: How Can It Improve Patients’ Clinical Management? A Systematic Review from the Literature

Deciding on Fine Needle Aspiration Biopsy in Thyroid Incidentalomas in FDG-PET/CT: Should Ultrasonographic Evaluation or FDG Uptake Be in the Foreground?

Objectives

18-Fluorodeoxyglucose Positron Emission Tomography/Computed Tomography (FDG-PET/CT) is a widespread imaging technique for whole-body scanning. Incidental lesions may be detected in thyroid gland and the importance and management of these lesions are still a matter of debate. The aims of this study were the evaluation of the diagnostic success of ultrasonography and FDG-PET/CT for predicting malignancy and contribution of these techniques for the decision of Fine Needle Aspiration Biopsy (FNAB) in incidental thyroid lesions detected in FDG-PET/CT.

Methods

Patients who underwent FDG-PET/CT in Nuclear Medicine Unit in a single institution between January 2018 and December 2022 were screened for thyroid incidentaloma with increased focal FDG uptake. Imaging studies and pathology results of the patients with Focal Thyroid Incidentalomas (FTI) were reviewed retrospectively.

Results

A total of 14.003 FDG-PET/CT reports of 8.259 patients were evaluated. In FDG-PET/CT imaging, 495 (6.0%) patients had increased uptake in thyroid gland, 383 (4.6%) patients had focal and 112 (1.4%) patients had diffuse FDG uptake. The rate of malignancy in FTIs was 19.2%. In the ROC curve analysis, regarding the prediction of malignancy in FTIs with FDG uptake, a SUVmax value of 5.5 and above predicts malignancy with a sensitivity of 71.4% and a specificity of 68.6% (AUC:0.718, p=0.018, 95%CI:0.564-0.872). The sensitivity of ACR-TIRADS-5 was 35.7% (95%CI:14.6-61.7) and sensitivity of the combination of SUVmax>5.5 and ACR-TIRADS-5 was 30.0% (95%CI:8.5-60.7).

Conclusion

FDG-PET/CT findings can be used for determining malignancy risk and cutoff values such as 5.5 can be threshold for ordering FNAB. In patients with SUVmax less than 5.5, ultrasonographic risk classification criteria should be used for decision-making.

A Machine Learning-Based Radiomics Model for the Differential Diagnosis of Benign and Malignant Thyroid Nodules in F-18 FDG PET/CT: External Validation in the Different Scanner

BACKGROUND/OBJECTIVES

Accurate diagnosis is essential to avoid unnecessary procedures for thyroid incidentalomas (TIs). Advances in radiomics and machine learning applied to medical imaging offer promise for assessing thyroid nodules. This study utilized radiomics analysis on F-18 FDG PET/CT to improve preoperative differential diagnosis of TIs.

METHODS

A total of 152 patient cases were retrospectively analyzed and split into training and validation sets (7:3) using stratification and randomization.

RESULTS

The least absolute shrinkage and selection operator (LASSO) algorithm identified nine radiomics features from 960 candidates to construct a radiomics signature predictive of malignancy. Performance of the radiomics score was evaluated using receiver operating characteristic (ROC) analysis and area under the curve (AUC). In the training set, the radiomics score achieved an AUC of 0.794 (95% CI: 0.703-0.885, p < 0.001). Validation was performed on internal and external datasets, yielding AUCs of 0.702 (95% CI: 0.547-0.858, p = 0.011) and 0.668 (95% CI: 0.500-0.838, p = 0.043), respectively.

CONCLUSIONS

These results demonstrate that the selected nine radiomics features effectively differentiate malignant thyroid nodules. Overall, the radiomics model shows potential as a valuable predictive tool for thyroid cancer in patients with TIs, supporting improved preoperative decision-making.

The Interplay Between High Cumulative Doses of Radioactive Iodine and Type 2 Diabetes Mellitus: A Complex Cardiovascular Challenge

Starting from the metabolic profile of type 2 diabetes mellitus (T2DM), we hypothesized that the mechanisms of ¹³¹I-induced cardiotoxicity differ between patients diagnosed with differentiated thyroid cancer (DTC) with/without T2DM, with metformin potentially acting as a cardioprotective agent by mitigating inflammation in patients with T2DM. To address this hypothesis, we quantified, using ELISA, the serum concentration of several key biomarkers that reflect cardiac injury (NT-proBNP, NT-proANP, ST2/IL-33R, and cTn I) in 74 female patients with DTC/-T2DM and 25 with DTC/+T2DM treated with metformin. All patients received a cumulative oral dose of 131I exceeding 150 mCi (5.55 GBq) over approximately 53 months. Our results showed the following: (i) In DTC/-T2DM patients, high-cumulative 131I doses promote a pro-inflammatory state that accelerates the development of cardiotoxicity. Monitoring NT-proBNP, ST2/IL-33R, and cTn I in these patients may help identify those at risk of developing cardiac complications. (ii) In patients with DTC/+T2DM, high-cumulative 131I doses lead to the release of NT-proANP (r = 0.63), which signals that the atria are under significant stress. (iii) In patients with DTC/+T2DM, metformin suppresses inflammation, leading to a dose-dependent reduction in cTn I (r = -0.59). Monitoring cTn I and NT-proANP, and considering the use of metformin as part of the therapeutic strategy, could help manage cardiotoxicity in T2DM patients undergoing 131I therapy.

Positron Emission Tomography/Computed Tomography in Thyroid Cancer: An Updated Review

PET/computed tomography (CT) is a valuable hybrid imaging modality for the evaluation of thyroid cancer, potentially impacting management decisions. 18F-fluorodeoxyglucose (FDG) PET/CT has proven utility for recurrence evaluation in differentiated thyroid cancer (DTC) patients having thyroglobulin elevation with negative iodine scintigraphy. Aggressive histologic subtypes such as anaplastic thyroid cancer shower higher FDG uptake. 18F-FDOPA is the preferred PET tracer for medullary thyroid cancer. Fibroblast activation protein inhibitor and arginylglycylaspartic acid -based radiotracers have emerged as promising PET agents for radioiodine refractory DTC patients with the potential for theranostic application.

Application of radiomics and machine learning to thyroid diseases in nuclear medicine: a systematic review

BACKGROUND

In the last years growing evidences on the role of radiomics and machine learning (ML) applied to different nuclear medicine imaging modalities for the assessment of thyroid diseases are starting to emerge. The aim of this systematic review was therefore to analyze the diagnostic performances of these technologies in this setting.

METHODS

A wide literature search of the PubMed/MEDLINE, Scopus and Web of Science databases was made in order to find relevant published articles about the role of radiomics or ML on nuclear medicine imaging for the evaluation of different thyroid diseases.

RESULTS

Seventeen studies were included in the systematic review. Radiomics and ML were applied for assessment of thyroid incidentalomas at 18 F-FDG PET, evaluation of cytologically indeterminate thyroid nodules, assessment of thyroid cancer and classification of thyroid diseases using nuclear medicine techniques.

CONCLUSION

Despite some intrinsic limitations of radiomics and ML may have affect the results of this review, these technologies seem to have a promising role in the assessment of thyroid diseases. Validation of preliminary findings in multicentric studies is needed to translate radiomics and ML approaches in the clinical setting.

Portrait of the Inflammatory Response to Radioiodine Therapy in Female Patients with Differentiated Thyroid Cancer with/without Type 2 Diabetes Mellitus

No clinical studies have investigated the effect of radioiodine (131I)-targeted therapy on the neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) as inflammatory response markers in patients with differentiated thyroid cancer (DTC) associated with type 2 diabetes mellitus (T2DM) and obesity. This study aimed to assess the relationship between blood radioactivity, body mass index (BMI), and peripheral blood cells three days after 131I intake in 56 female patients without T2DM (DTC/-T2DM) vs. 24 female patients with T2DM (DTC/+T2DM). Blood radioactivity, measured three days after 131I intake, was significantly lower in the DTC/+T2DM than in the DTC/-T2DM patients (0.7 mCi vs. 1.5 mCi, p < 0.001). The relationship between blood radioactivity and BMI (r = 0.83, p < 0.001), blood radioactivity and NLR (r = 0.53, p = 0.008), and BMI and NLR (r = 0.58, p = 0.003) indicates a possible connection between the bloodstream 131I uptake and T2DM-specific chronic inflammation. In patients without T2DM, 131I therapy has immunosuppressive effects, leading to increased NLR (19.6%, p = 0.009) and PLR (39.1%, p = 0.002). On the contrary, in the chronic inflammation context of T2DM, 131I therapy amplifies immune metabolism, leading to a drop in NLR (10%, p = 0.032) and PLR (13.4%, p = 0.021). Our results show that, in DTC/+T2DM, the bidirectional crosstalk between neutrophils and obesity may limit 131I uptake in the bloodstream. Considering the immune response to 131I therapy, the two groups of patients can be seen as a synchronous portrait of two sides. The explanation could lie in the different radiosensitivity of T and B lymphocytes, with T lymphocytes being predominant in patients with DTC/-T2DM and, most likely, B lymphocytes being predominant in T2DM.

Prediction of Malignant Thyroid Nodules Using 18 F-FDG PET/CT-Based Radiomics Features in Thyroid Incidentalomas

OBJECTIVE

The purpose of the current study was to evaluate the diagnostic performances of 18 F-FDG PET/CT-based radiomics features for prediction of malignant thyroid nodules (TNs) in thyroid incidentaloma (TI).

METHODS

PubMed, Cochrane database, and EMBASE database, from the earliest available date of indexing through December 31, 2022, were searched for studies evaluating diagnostic performance of 18 F-FDG PET/CT-based radiomics features for prediction of malignant TNs in TI. We determined the sensitivities and specificities across studies, calculated positive and negative likelihood ratios (LRs; positive and negative LRs), and estimated pooled area under the curve.

RESULTS

Across 5 studies (518 patients), the pooled sensitivity of 18 F-FDG PET/CT was 0.77 (95% confidence interval [CI], 0.67-0.84), and a pooled specificity was 0.67. Likelihood ratio syntheses gave an overall positive LR of 2.3 (95% CI, 1.5-3.6) and negative LR of 0.35 (95% CI, 0.26-0.47). The pooled diagnostic odds ratio was 7 (95% CI, 4-12). The pooled area under the curve of fixed effects was 0.763 (95% CI, 0.736-0.791), and that of random effects was 0.763 (95% CI, 0.721-0.805).

CONCLUSION

18 F-FDG PET/CT-based radiomics features showed a good diagnostic performance for prediction of malignant TNs in TI.

Positron Emission Tomography Radiopharmaceuticals in Differentiated Thyroid Cancer

Differentiated thyroid cancer (DTC), arising from thyroid follicular epithelial cells, is the most common type of thyroid cancer. Despite the well-known utilization of radioiodine treatment in DTC, i.e., iodine-131, radioiodine imaging in DTC is typically performed with iodine-123 and iodine-131, with the current hybrid scanner performing single photon emission tomography/computed tomography (SPECT/CT). Positron emission tomography/computed tomography (PET/CT) provides superior visualization and quantification of functions at the molecular level; thus, lesion assessment can be improved compared to that of SPECT/CT. Various types of cancer, including radioiodine-refractory DTC, can be detected by 2-[¹⁸F]fluoro-2-deoxy-D-glucose ([¹⁸F]FDG), the most well-known and widely used PET radiopharmaceutical. Several other PET radiopharmaceuticals have been developed, although some are limited in availability despite their potential clinical utilizations. This article aims to summarize PET radiopharmaceuticals in DTC, focusing on molecular pathways and applications.