Evaluation of the Perinodular Stiffness Potentially Predicts the Malignancy of Thyroid Nodules

Convolutional neural network based on automatic segmentation of peritumoral shear-wave elastography images for predicting breast cancer

Objective

Our aim was to develop dual-modal CNN models based on combining conventional ultrasound (US) images and shear-wave elastography (SWE) of peritumoral region to improve prediction of breast cancer.

Method

We retrospectively collected US images and SWE data of 1271 ACR- BIRADS 4 breast lesions from 1116 female patients (mean age ± standard deviation, 45.40 ± 9.65 years). The lesions were divided into three subgroups based on the maximum diameter (MD): ≤15 mm; >15 mm and ≤25 mm; >25 mm. We recorded lesion stiffness (SWV1) and 5-point average stiffness of the peritumoral tissue (SWV5). The CNN models were built based on the segmentation of different widths of peritumoral tissue (0.5 mm, 1.0 mm, 1.5 mm, 2.0 mm) and internal SWE image of the lesions. All single-parameter CNN models, dual-modal CNN models, and quantitative SWE parameters in the training cohort (971 lesions) and the validation cohort (300 lesions) were assessed by receiver operating characteristic (ROC) curve.

Results

The US + 1.0 mm SWE model achieved the highest area under the ROC curve (AUC) in the subgroup of lesions with MD ≤15 mm in both the training (0.94) and the validation cohorts (0.91). In the subgroups with MD between15 and 25 mm and above 25 mm, the US + 2.0 mm SWE model achieved the highest AUCs in both the training cohort (0.96 and 0.95, respectively) and the validation cohort (0.93 and 0.91, respectively).

Conclusion

The dual-modal CNN models based on the combination of US and peritumoral region SWE images allow accurate prediction of breast cancer.

Convolutional Neural Network for Predicting Thyroid Cancer Based on Ultrasound Elastography Image of Perinodular Region

We aimed to develop deep learning models based on perinodular regions' shear-wave elastography (SWE) images and ultrasound (US) images of thyroid nodules (TNs) and determine their performances in predicting thyroid cancer. A total of 1747 American College of Radiology Thyroid Imaging Reporting & Data System 4 (TR4) thyroid nodules (TNs) in 1582 patients were included in this retrospective study. US images, SWE images, and 2 quantitative SWE parameters (maximum elasticity of TNs; 5-point average maximum elasticity of TNs) were obtained. Based on US and SWE images of TNs and perinodular tissue, respectively, 7 single-image convolutional neural networks (CNN) models [US, internal SWE, 0.5 mm SWE, 1.0 mm SWE, 1.5 mm SWE, 2.0 mm SWE of perinodular tissue, and whole SWE region of interest (ROI) image] and another 6 fusional-image CNN models (US + internal SWE, US + 0.5 mm SWE, US + 1.0 mm SWE, US + 1.5 mm SWE, US + 2.0 mm SWE, US + ROI SWE) were established using RestNet18. All of the CNN models and quantitative SWE parameters were built on a training cohort (1247 TNs) and evaluated on a validation cohort (500 TNs). In predicting thyroid cancer, US + 2.0 mm SWE image CNN model obtained the highest area under the curve in 10 mm < TNs ≤ 20 mm (0.95 for training; 0.92 for validation) and TNs > 20 mm (0.95 for training; 0.92 for validation), while US + 1.0 mm SWE image CNN model obtained the highest area under the curve in TNs ≤ 10 mm (0.95 for training; 0.92 for validation). The CNN models based on the fusion of SWE segmentation images and US images improve the radiological diagnostic accuracy of thyroid cancer.

Evaluation of Ultrasound Elastography Combined With Chi-Square Automatic Interactive Detector in Reducing Unnecessary Fine-Needle Aspiration on TIRADS 4 Thyroid Nodules

Background

Conventional ultrasound diagnosis of thyroid nodules (TNs) had a high false-positive rate, resulting in many unnecessary fine-needle aspirations (FNAs).

Objective

This study aimed to establish a simple algorithm to reduce unnecessary FNA on TIRADS 4 TNs using different quantitative parameters of ultrasonic elasticity and chi-square automatic interactive detector (CHAID) method.

Methods

From January 2020 to May 2021, 432 TNs were included in the study, which were confirmed by FNA or surgical pathology. Each TN was examined using conventional ultrasound, sound touch elastography, and Shell measurement function. The quantitative parameters E and E_shell were recorded, and the E_shell/E values were calculated for each TN. The diagnostic performance of the quantitative parameters was evaluated using the receiver operating characteristic curves. The CHAID was used to classify and analyze the quantitative parameters, and the prediction model was established.

Results

A total of 226 TNs were malignant and 206 were benign. E_shell and E_shell/E ratio were included in the classification algorithm, which showed a depth of two ramifications (E_shell/E ≤ 0.988 or 0.988–1.043 or >1.043; if E_shell/E ≤ 0.988, then E_shell ≤ 64.0 or 64.0–74.0 or >74.0; if E_shell/E = 0.988–1.043, then E_shell ≤ 66.0 or > 66.0; if E_shell/E >1.043, then E_shell ≤ 69.0 or >69.0). The unnecessary FNAs could have been avoided in 57.3% of the cases using this algorithm.

Conclusion

The prediction model using quantitative parameters had high diagnostic performance; it could quickly distinguish benign lesions and avoid subjective influence to some extent.

Assessment of perinodular stiffness in differentiating malignant from benign thyroid nodules

OBJECTIVE

We evaluated the diagnostic accuracy of perinodular stiffness, four risk stratification systems (RSSs) (KWAK-TIRADS, ACR-TIRADS, EU-TIRADS, and C-TIRADS), and the combination of perinodular stiffness and the four RSSs in differentiating malignant from benign thyroid nodules (TNs).

METHODS

A total of 788 TNs in 726 patients were examined with conventional ultrasound (US) examination and sound touch elastography (STE). All TNs were classified by each of the four RSSs. The stiffness inside (E) the TNs was measured by STE. The stiffness of the 2.0-mm perinodular region (Eshell) was measured with the Shell measurement function of STE. The diagnostic performances of four RSSs, the E values, and the Eshell values were evaluated. All TNs were further divided into subgroups based on size (≤ 10 mm group and > 10 mm group).

RESULTS

Ninety-six TNs were classified as benign and 692 as malignant. Among the single-method approaches, ACR-TIRADS showed the highest AUC (0.77) for differentiating malignant from benign TNs for all TNs included. Eshell showed the highest AUC (0.75) in differentiating malignant from benign TNs for TNs with sizes ≤ 10 mm, and there were no significant differences in AUC among all single methods for diagnosis of TNs with sizes > 10 mm (P > 0.05). The combination of C-TIRADS and Eshell/E yielded the highest AUC for all TNs (0.83) and for TNs with size ≤ 10 mm (0.85) compared with other combinations.

CONCLUSIONS

Eshell/E combined with conventional US improves the diagnostic accuracy in TNs and may reduce unnecessary fine-needle aspiration.