MATERIALS AND METHODS: PubMed, Web of Science, Cochrane, and Embase databases were searched until May 7th, 2024. The Radiomics Quality Score tool assessed bias risk. Subgroup analyses based on radiomics and clinical characteristics were conducted.
RESULTS: Our systematic review included 19 studies, encompassing 5337 PTC cases. Among these, 12 articles focused on ETE and seven articles focused on BRAFV600E mutations. For the identification of ETE in the validation set, the summarized machine learning (ML) models demonstrated 0.80c-index (95%CI: 0.77-0.83), 0.77 sensitivity (95%CI: 0.72-0.81), and 0.78 specificity (95%CI: 0.73-0.82). Radiomics based on ultrasound demonstrated 0.82c-index (95%CI: 0.78-0.86), 0.77 sensitivity (95%CI: 0.68-0.84), and 0.84 specificity (95%CI: 0.75-0.91). For the identification of BRAFV600E mutations in the validation set, the summarized ML models showed 0.80c-index (95%CI: 0.72-0.87), 0.76 sensitivity (95%CI: 0.67-0.84), and 0.88 specificity (95%CI: 0.77-0.94). ML models based on ultrasound-guided radiomics had 0.81c-index (95%CI: 0.74-0.89), 0.79 sensitivity (95%CI: 0.71-0.86), and 0.87 specificity (95%CI: 0.74-0.94).
CONCLUSION: Radiomics in identifying ETE and BRAFV600E mutation have high c-index, sensitivity, and specificity, especially images from ultrasound, demonstrating the potential for diagnosing ETE and BRAFV600E mutations in PTC.