The progress of artificial intelligence (AI), particularly its core algorithms—machine learning (ML) and deep learning (DL)—has been significant in the medical field, impacting both scientific research and clinical practice. These algorithms are now capable of analyzing ultrasound images, processing them, and providing outcomes, such as determining the benignity or malignancy of thyroid nodules. This integration into ultrasound machines is referred to as computer-aided diagnosis (CAD). The use of such software extends beyond ultrasound to include cytopathological and molecular assessments, enhancing the estimation of malignancy risk. AI’s considerable potential in cancer diagnosis and prevention is evident. This article provides an overview of AI models based on ML and DL algorithms used in thyroid diagnostics. Recent studies demonstrate their effectiveness and diagnostic role in ultrasound, pathology, and molecular fields. Notable advancements include content-based image retrieval (CBIR), enhanced saliency CBIR (SE-CBIR), Restore-Generative Adversarial Networks (GANs), and Vision Transformers (ViTs). These new algorithms show remarkable results, indicating their potential as diagnostic and prognostic tools for thyroid pathology. The future trend points to these AI systems becoming the preferred choice for thyroid diagnostics.

While the frequency of papillary thyroid carcinoma (PTC) has increased in recent decades, both due to improvements in diagnostic procedures and a real, effective percentage increase in cases, the frequency of medullary thyroid carcinoma (MTC), however, has remained almost unchanged, representing 3–5% of thyroid cancer cases. Our experience relates to the observation of cases with the synchronous presence of PTC and MTC, also in chronic autoimmune thyroiditis, and this led us to carry out a brief review of the literature on the subject, with the aim above all of identifying the most correct postoperative therapeutic process.

Thyroid nodule evaluation relies heavily on ultrasound imaging, yet it suffers from significant inter-operator variability. To address this, we present a preliminary validation of the Synergy-Net platform, an AI-driven Computer-Aided Diagnosis (CAD) system designed to standardize acquisition and improve diagnostic accuracy. The system integrates a U-Net architecture for anatomical segmentation and a ResNet-50 classifier for lesion characterization within a Human-in-the-Loop (HITL) workflow. The study enrolled 110 patients (71 benign, 39 malignant) undergoing surgery. Performance was evaluated against histopathological ground truth. The system achieved an Accuracy of 90.35% (95% CI: 88.2–92.5%), Sensitivity of 90.64% (95% CI: 87.9–93.4%), and an AUC of 0.90. Furthermore, the framework introduces a multimodal approach, performing late fusion of imaging features with genomic profiles (TruSight One panel). While current results validate the 2D diagnostic pipeline, the discussion outlines the transition to the ANTHEM framework, incorporating future 3D volumetric analysis and digital pathology integration. These findings suggest that AI-assisted standardization can significantly enhance diagnostic precision, though multi-center validation remains necessary.

Background: Ultrasound-guided radiofrequency ablation (RFA) has become an established minimally invasive treatment for selected benign and autonomously functioning thyroid nodules. Although clinical outcomes are well documented, the biological mechanisms underlying tissue remodeling after ablation remain incompletely characterized. The integration of imaging, molecular, and histopathological data may provide a more comprehensive understanding of treatment response. Methods: We conducted a prospective monocentric observational translational cohort study including 60 patients undergoing ultrasound-guided RFA for benign or autonomously functioning thyroid nodules between November 2024 and December 2025. Patients underwent standardized pre-procedural assessment including high-resolution ultrasound with volumetric evaluation, three-dimensional reconstruction, and collection of peripheral blood samples for exploratory extracellular vesicle (EV)-derived microRNA (miRNA) profiling. Clinical outcomes, volumetric changes, vascular remodeling, and procedural complications were assessed during scheduled follow-up visits (mean follow-up duration: 11 months; range: 5–17 months). A subgroup of patients who subsequently required surgery because of insufficient volumetric response underwent thyroidectomy, allowing histopathological evaluation of post-ablation tissue changes. Clinical, imaging, molecular, and pathological data were integrated within a multimodal translational framework. Results: RFA resulted in a mean nodule volume reduction of 56% at early follow-up, with progressive volumetric reduction observed during longitudinal ultrasound evaluation. A clinically relevant improvement in compressive symptoms was observed, with a 44% reduction in symptom burden. Doppler ultrasound demonstrated progressive changes in vascular patterns consistent with post-ablation devascularization and tissue remodeling. Ten patients underwent thyroidectomy after RFA because of insufficient volumetric response, providing histological validation of treatment-induced tissue alterations, including coagulative necrosis, fibrosis, inflammatory changes, and architectural remodeling. Exploratory EV-derived miRNA profiling was incorporated into the translational workflow to investigate potential molecular correlates of treatment response; however, molecular findings require further validation in larger cohorts. Conclusions: This study provides a multimodal translational characterization of tissue response after thyroid RFA by integrating clinical outcomes, ultrasound imaging, histopathology, and exploratory EV-derived miRNA analysis. The proposed framework may contribute to a deeper understanding of biological changes following thermal ablation and support future investigations aimed at identifying reliable biomarkers of treatment response.