Non-invasive assessment of the risk of lymph node metastasis (LNM) in patients with papillary thyroid carcinoma (PTC) is of great value for the treatment option selection. The purpose of this paper is to develop a transfer learning radiomics (TLR) model for preoperative prediction of LNM in PTC patients in a multicenter, cross-machine, multi-operator scenario. Here we report the TLR model produces a stable LNM prediction. In the experiments of cross-validation and independent testing of the main cohort according to diagnostic time, machine, and operator, the TLR achieves an average area under the curve (AUC) of 0.90. In the other two independent cohorts, TLR also achieves 0.93 AUC, and this performance is statistically better than the other three methods according to Delong test. Decision curve analysis also proves that the TLR model brings more benefit to PTC patients than other methods.

Background: Papillary thyroid carcinoma is a type of indolent tumor with a dramatically increasing incidence rate and stably high survival rate. Reducing the overdiagnosis and overtreatment of papillary thyroid carcinoma is clinically emergent and important. A radiomics model is proposed in this article to predict lymph node metastasis, the most important risk factor of papillary thyroid carcinoma, based on noninvasive routine preoperative ultrasound images. Methods: Four hundred fifty ultrasound manually segmented images of patients with papillary thyroid carcinoma with lymph node status obtained from pathology report were enrolled in our retrospective study. A radiomics evaluation of 614 high-throughput features were calculated, including size, shape, margin, boundary, orientation, position, echo pattern, posterior acoustic pattern, and calcification features. Then, combined feature selection strategy was used to select features with the greatest ability to discriminate lymph node status. A support vector machine classifier was employed to build and validate the prediction model. Another independent testing cohort was used to further evaluate the performance of the radiomics model. Results: Among 614 radiomics features, 50 selected features most reflecting echo pattern, posterior acoustic pattern, and calcification showed the superior lymph node status distinguishable performance with area under the receiver operating characteristic curve of 0.753, 0.740, and 0.743 separately when using each type of features predicting the lymph node status. The results of model based on all 50 final features predicting the lymph node status shown an area under the receiver operating characteristic curve of 0.782, and accuracy of 0.712. In the independent testing cohort, the proposed approach showed similar results, with area under the receiver operating characteristic curve of 0.727 and accuracy of 0.710. Conclusion: Papillary thyroid carcinoma with lymph node metastasis usually shows a complex echo pattern, posterior region homogeneity, and macrocalcification or multiple calcification. The radiomics model proposed in this article is a promising method for assessing the risk of papillary thyroid carcinoma metastasis noninvasively.

Purpose: Due to the low contrast, blurry boundaries, and large amount of shadows in breast ultrasound (BUS) images, automatic tumor segmentation remains a challenging task. Deep learning provides a solution to this problem, since it can effectively extract representative features from lesions and the background in BUS images. Methods: A novel automatic tumor segmentation method is proposed by combining a dilated fully convolutional network (DFCN) with a phase-based active contour (PBAC) model. The DFCN is an improved fully convolutional neural network with dilated convolution in deeper layers, fewer parameters, and batch normalization techniques; and has a large receptive field that can separate tumors from background. The predictions made by the DFCN are relatively rough due to blurry boundaries and variations in tumor sizes; thus, the PBAC model, which adds both region-based and phase-based energy functions, is applied to further improve segmentation results. The DFCN model is trained and tested in dataset 1 which contains 570 BUS images from 89 patients. In dataset 2, a 10-fold support vector machine (SVM) classifier is employed to verify the diagnostic ability using 460 features extracted from the segmentation results of the proposed method. Results: Advantages of the present method were compared with three state-of-the-art networks; the FCN-8s, U-net, and dilated residual network (DRN). Experimental results from 170 BUS images show that the proposed method had a Dice Similarity coefficient of 88.97 AE 10.01%, a Hausdorff distance (HD) of 35.54 AE 29.70 pixels, and a mean absolute deviation (MAD) of 7.67 AE 6.67 pixels, which showed the best segmentation performance. In dataset 2, the area under curve (AUC) of the 10-fold SVM classifier was 0.795 which is similar to the classification using the manual segmentation results. Conclusions: The proposed automatic method may be sufficiently accurate, robust, and efficient for medical ultrasound applications.

This study aimed to establish and validate an ultrasound radiomics nomogram for the preoperative prediction of central lymph node (LN) metastasis in patients with papillary thyroid carcinoma (PTC). Patients and Methods: The prediction model was developed in 609 patients with clinicopathologically confirmed unifocal PTC who received ultrasonography between Jan 2018 and June 2018. Radiomic features were extracted after the ultrasonography of PTC. Lasso regression model was used for data dimensionality reduction, feature selection, and radiomics signature building. The predicting model was established based on the multivariable logistic regression analysis in which the radiomics signature, ultrasonography-reported LN status, and independent clinicopathologic risk factors were incorporated, and finally a radiomics nomogram was established. The performance of the nomogram was assessed with respect to the discrimination and consistence. An independent validation was performed in 326 consecutive patients from July 2018 to Sep 2018. Results: The radiomics signature consisted of 23 selected features and was significantly associated with LN status in both primary and validation cohorts. The independent predictors in the radiomics nomogram included the radiomics signature, age, TG level, TPOAB level, and ultrasonography-reported LN status. The model showed good discrimination and consistence in both cohorts: C-index of 0.816 (95% CI, 0.808-0.824) in the primary cohort and 0.858 (95% CI, 0.849-0.867) in the validation cohort. The area under receiver operating curve was 0.858. In the validation cohort, the accuracy, sensitivity, specificity and AUC of this model were 0.812, 0.816, 0.810, and 0.858 (95% CI, 0.785-0.930), respectively. Decision curve analysis indicated the radiomics nomogram was clinically useful. Conclusion: This study presents a convenient, clinically useful ultrasound radiomics nomogram that can be used for the pre-operative individualized prediction of central LN metastasis in patients with PTC.