Study on Diagnosing Thyroid Nodules of ACR TI-RADS 4~5 with Multi-Modal Ultrasound Radiomics Technology

Abstract

Abstract Background Explore the feasibility of using multimodal ultrasound radiomics technology to diagnose ACR-TI-RADS 4 ~ 5 thyroid nodules. Method This study prospectively collected the clinical characteristics, conventional, and ultrasound elastography images of 100 patients diagnosed with ACR TI-RADS 4 ~ 5 nodules from May 2022 to May 2023. Independent risk factors for malignant thyroid nodules were extracted and screened using methods such as the least absolute shrinkage and selection operator (LASSO) logistic regression model, and a multimodal ultrasound radiomics combined diagnostic model was established. Using a multifactorial logistic regression analysis and a Rad-score rating, the predictive performance was validated and evaluated, and the final threshold range was determined to assess the clinical net benefit of the model. Results In the training set, the ultrasound radiomics combined predictive model (AUC = 0.928) had higher diagnostic performance compared to clinical characteristics (AUC = 0.779), conventional ultrasound (AUC = 0.794), and ultrasound elastography model (AUC = 0.852). In the validation set, the multimodal ultrasound radiomics combined diagnostic model (AUC = 0.829) also had higher diagnostic performance compared to clinical characteristics (AUC = 0.799), conventional ultrasound (AUC = 0.802), and ultrasound elastography model (AUC = 0.718). Conclusion Multi-modal ultrasound radiomics technology can effectively diagnose thyroid nodules of ACR TI-RADS 4 ~ 5, and the combination of radiomics signature and conventional ultrasound features can further improve the diagnostic performance.