Background: The risk stratification system of the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) for thyroid nodules is affected by low diagnostic specificity. Machine learning (ML) methods can optimize the diagnostic performance in medical image analysis. However, it is unknown which ML-based diagnostic pattern is more effective in improving diagnostic performance for thyroid nodules and reducing nodule biopsies. Therefore, we compared ML-assisted visual approaches and radiomics approaches with ACR TI-RADS in diagnostic performance and unnecessary fine-needle aspiration biopsy (FNAB) rate for thyroid nodules. Methods: This retrospective study evaluated a data set of ultrasound (US) and shear wave elastography (SWE) images in patients with biopsy-proven thyroid nodules (‡1 cm) from the Shanghai Tenth People's Hospital (743 nodules in 720 patients from September 2017 to January 2019) and an independent test data set from the Ma'anshan People's Hospital (106 nodules in 102 patients from February 2019 to April 2019). Six US features and five SWE parameters from the radiologists' interpretation were used for building the ML-assisted visual approaches. The radiomics features extracted from the US and SWE images were used with ML methods for developing the radiomics approaches. The diagnostic performance for differentiating thyroid nodules and the unnecessary FNAB rate of the ML-assisted visual approaches and the radiomics approaches were compared with ACR TI-RADS. Results: The ML-assisted US visual approach had the best diagnostic performance than the US radiomics approach and ACR TI-RADS (area under the curve [AUC]: 0.900 vs. 0.789 vs. 0.689 for the validation data set, 0.917 vs. 0.770 vs. 0.681 for the test data set). After adding SWE, the ML-assisted visual approach had a better diagnostic performance than US alone (AUC: 0.951 vs. 0.900 for the validation data set, 0.953 vs. 0.917 for the test data set). When applying the ML-assisted US+SWE visual approach, the unnecessary FNAB rate decreased from 30.0% to 4.5% in the validation data set and from 37.7% to 4.7% in the test data set in comparison to ACR TI-RADS. Conclusions: The ML-assisted dual modalities visual approach can assist radiologists to diagnose thyroid nodules more effectively and considerably reduce the unnecessary FNAB rate in the clinical management of thyroid nodules.
Background: The carotid artery plaque score (PS) is an independent predictor of Coronary Heart Disease (CHD). This study aims to evaluate the combination of PS and carotid hemodynamics to predict CHD. Methods: A total of 476 patients who underwent carotid ultrasonography and coronary angiography were divided into two groups depending on the presence of CHD. PS, carotid intima-media thickness, and carotid blood flow were measured. Receiver operating characteristic curve analysis was performed to establish the best prediction model for CHD presence. Results: Age, sex, carotid intima-media thickness of internal carotid artery and carotid bifurcation, PS, peak systolic velocity (PSA) of right internal carotid artery (RICA), and most resistance index data were significantly related with the presence of CHD. The area under the curve for a collective model, which included factors of the PS, carotid hemodynamics and age, was significantly higher than the other model. Age, PS, and PSA of RICA were significant contributors for predicting CHD presence. Conclusions: The model of PS and PSA of RICA has greater predictive value for CHD than PS alone. Adding age to PS and PSA of RICA further improves predictive value over PS alone.
Objective
We herein compared the diagnostic accuracy of the BI‐RADS, ABVS, SWE, and combined techniques for the classification of breast lesions.
Methods
Breast lesions were appraised using the BI‐RADS classification system as well as the combinations of BI‐RADS plus ABVS (BI‐RADS + ABVS) and BI‐RADS plus SWE (BI‐RADS + SWE), and both methods (BI‐RADS + ABVS + SWE) by two specialties Medical Ultrasound physician. The Fisher's exact and χ2 tests were performed to compare the degree of malignancy for the various methods with a pathology ground truth. Receiver operating characteristic curves (ROC) were generated and the corresponding area under the curve (AUC) values were determined to test the diagnostic efficacy of the various methods and identify the optimal SWE cut‐off indicative of malignancy.
Results
The incidence of the retraction phenomenon on ABVS images of the malignant group was significantly higher (P < .001) than that of the benign group. The specificity, sensitivity, and positive and negative predictive values of the BI‐RADS classification were 88.72, 79.38, 83.70, and 85.50%, respectively. BI‐RADS plus SWE‐Max exhibited enhanced specificity, sensitivity, and positive and negative predictive values of 88.72, 92.78, 85.70, and 94.40%, respectively. Similarly, when BI‐RADS + ABVS was utilized, the sensitivity and negative predictive value increased to 95.88 and 96.40%, respectively. BI‐RADS + ABVS + SWE possessed the highest overall sensitivity (96.91%), specificity (94.74%), and positive (93.10%) and negative (97.70%) predictive values from all four indices.
Conclusion
ABVS and SWE can reduce the subjectivity of BI‐RADS. As a result, BI‐RADS + ABVS + SWE resulted in the best diagnostic accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.