Applying machine-learning models to differentiate benign and malignant thyroid nodules classified as C-TIRADS 4 based on 2D-ultrasound combined with five contrast-enhanced ultrasound key frames.

Objectives: To apply machine learning to extract radiomics features from thyroid two-dimensional ultrasound (2D-US) combined with contrast-enhanced ultrasound (CEUS) images to classify and predict benign and malignant thyroid nodules, classified according to the Chinese version of the thyroid imaging reporting and data system (C-TIRADS) as category 4. Materials and methods: This retrospective study included 313 pathologically diagnosed thyroid nodules (203 malignant and 110 benign). Two 2D-US images and five CEUS key frames ("2nd second after the arrival time" frame, "time to peak" frame, "2nd second after peak" frame, "first-flash" frame, and "second-flash" frame) were selected to manually label the region of interest using the "Labelme" tool. A total of 7 images of each nodule and their annotates were imported into the Darwin Research Platform for radiomics analysis. The datasets were randomly split into training and test cohorts in a 9:1 ratio. Six classifiers, namely, support vector machine, logistic regression, decision tree, random forest (RF), gradient boosting decision tree and extreme gradient boosting, were used to construct and test the models. Performance was evaluated using a receiver operating characteristic curve analysis. The area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), and F1-score were calculated. One junior radiologist and one senior radiologist reviewed the 2D-US image and CEUS videos of each nodule and made a diagnosis. We then compared their AUC and ACC with those of our best model. Results: The AUC of the diagnosis of US, CEUS and US combined CEUS by junior radiologist and senior radiologist were 0.755, 0.750, 0.784, 0.800, 0.873, 0.890, respectively. The RF classifier performed better than the other five, with an AUC of 1 for the training cohort and 0.94 (95% confidence interval 0.88-1) for the test cohort. The sensitivity, specificity, accuracy, PPV, NPV, and F1-score of the RF model in the test cohort were 0.82, 0.93, 0.90, 0.85, 0.92, and 0.84, respectively. The RF model with 2D-US combined with CEUS key frames achieved equivalent performance as the senior radiologist (AUC: 0.94 vs. 0.92, P = 0.798; ACC: 0.90 vs. 0.92) and outperformed the junior radiologist (AUC: 0.94 vs. 0.80, P = 0.039, ACC: 0.90 vs. 0.81) in the test cohort. Conclusions: Our model, based on 2D-US and CEUS key frames radiomics features, had good diagnostic efficacy for thyroid nodules, which are classified as C-TIRADS 4. It shows promising potential in assisting less experienced junior radiologists.

Applying contrast-enhanced ultrasound model to distinguish atypical focal adenomyosis from uterine leiomyomas.

Background: Different from conventional ultrasound, contrast-enhanced ultrasound (CEUS) is better in observing microperfusion. For atypical focal adenomyosis and uterine leiomyomas that are difficult to be distinguished by conventional ultrasound, this study aims to further improve the differential diagnosis performance by using CEUS model. Methods: After screening the cases with difficulties in identifying focal myometrium lesions through conventional ultrasound, the number of cases covered in the focal adenomyosis group and leiomyomas group were 60 and 30 in derivation cohort, 14 and 7 in validation cohort. The qualitative and quantitative characteristics of CEUS were analyzed according to the surgical pathology. The qualitative characteristics include: the enhancement level based on the myometrium, the contrast enhancement pattern, the enhanced time of the lesion based on the myometrium, post-contrast lesion border, the distribution of the contrast agent, and the wash-out time based on the myometrium. The quantitative characteristics include: arrive time (AT), time to peak (TTP), peak intensity (PI), ΔAT, ΔTTP, ΔPI, |ΔAT|, |ΔTTP|, |ΔPI| and lesion temporal variability. Multiple logistic regression analysis was used to screen the independent risk factors, and a risk prediction model for the differential diagnosis of the two diseases was established. The area under the receiver operating characteristic (ROC) curve (AUC) was used to assess the diagnostic performance of the model. The validation cohort was used to further evaluate the diagnostic performance of the model. Results: Through the multivariate analysis, it concluded that short-term vessels first enhanced enhancement mode, unclear boundary, lesion temporal variability under CEUS >9.5 s, uneven contrast agent distribution could be independent risk factors for the diagnosis of adenomyosis [AUC =0.908, 95% confidence interval (CI): 0.833-0.982]. We also determined the sensitivity (98.33%), specificity (70.00%), positive predictive value (PPV) (86.76%), negative predictive value (NPV) (95.45%), and accuracy (87.78%) of this model. Based on pathological diagnosis, the sensitivity and specificity of the model in the validation cohort were both 85.71%, with NPV of 75% and PPV of 92.3%. The area under the ROC curve was 0.898 (95% CI: 0.742-1.000). Conclusions: The establishment of CEUS model has certain clinical application value in differentiating atypical focal adenomyosis from leiomyomas.