No abstract

No abstract

IMPORTANCE Thyroid nodules are common incidental findings. Ultrasonography and molecular testing can be used to assess risk of malignant neoplasm.OBJECTIVE To examine whether a model developed through automated machine learning can stratify thyroid nodules as high or low genetic risk by ultrasonography imaging alone compared with stratification by molecular testing for high-and low-risk mutations.DESIGN, SETTING, AND PARTICIPANTS This diagnostic study was conducted at a single tertiary care urban academic institution and included patients (n = 121) who underwent ultrasonography and molecular testing for thyroid nodules from January 1, 2017, through August 1, 2018. Nodules were classified as high risk or low risk on the basis of results of an institutional molecular testing panel for thyroid risk genes. All thyroid nodules that underwent genetic sequencing for cytological results with Bethesda System categories III and IV were reviewed. Patients without diagnostic ultrasonographic images within 6 months of fine-needle aspiration or who received definitive treatment at an outside medical center were excluded.MAIN OUTCOMES AND MEASURES Thyroid nodules were categorized by the model as high risk or low risk using ultrasonographic images. Results were compared using genetic testing. RESULTS Among the 134 lesions identified in 121 patients (mean [SD] age, 55.7 [14.2] years; 102 women [84.3%]), 683 diagnostic ultrasonographic images were selected. Of the 683 images, 556 (81.4%) were used for training the model, 74 (10.8%) for validation, and 53 (7.8%) for testing. Most nodules had no mutation (75 [56.0%]), whereas 43 nodules (32.1%) had a high-risk mutation and 16 (11.9%) had an unknown or a low-risk mutation (χ 2 = 39.060; P < .001). In total, 228 images (33.4%) were of nodules classified as genetically high risk (n = 43), and 455 (66.6%) were of low-risk nodules (n = 91). The model performed with a sensitivity of 45% (95% CI, 23.1%-68.5%), a specificity of 97% (95% CI, 84.2%-99.9%), a positive predictive value of 90% (95% CI, 55.2%-98.5%), a negative predictive value of 74.4% (95% CI, 66.1%-81.3%), and an overall accuracy of 77.4% (95% CI, 63.8%-97.7%). CONCLUSIONS AND RELEVANCEThe study found that the model developed through automated machine learning could produce high specificity for identifying nodules with high-risk mutations on molecular testing. This finding shows promise for the diagnostic applications of machine learning interpretation of sonographic imaging of indeterminate thyroid nodules.

Contrast-enhanced ultrasound (CEUS) has evolved from the use of agitated saline to second generation bioengineered microbubbles designed to withstand insonation with limited destruction. While only one of these newer agents is approved by the Food and Drug Administration for use outside echocardiography, interventional radiologists are increasingly finding off-label uses for ultrasound contrast agents. Notably, these agents have an extremely benign safety profile with no hepatic or renal toxicities and no radiation exposure. Alongside diagnostic applications, CEUS has begun to develop its own niche within the realm of interventional oncology. Certainly, the characterization of focal solid organ lesions (such as hepatic and renal lesions) by CEUS has been an important development. However, interventional oncologists are finding that the dynamic and real-time information afforded by CEUS can improve biopsy guidance, ablation therapy, and provide early evidence of tumor viability after locoregional therapy. Even more novel uses of CEUS include lymph node mapping and sentinel lymph node localization. Critical areas of research still exist. The purpose of this article is to provide a narrative review of the emerging roles of CEUS in interventional oncology.