Histopathological Characteristics of N1b Papillary Thyroid Carcinoma are Associated with Risk of Recurrence

Analysis of preoperative computed tomography radiomics and clinical factors for predicting postsurgical recurrence of papillary thyroid carcinoma

BACKGROUND

Postsurgical recurrence is of great concern for papillary thyroid carcinoma (PTC). We aim to investigate the value of computed tomography (CT)-based radiomics features and conventional clinical factors in predicting the recurrence of PTC.

METHODS

Two-hundred and eighty patients with PTC were retrospectively enrolled and divided into training and validation cohorts at a 6:4 ratio. Recurrence was defined as cytology/pathology-proven disease or morphological evidence of lesions on imaging examinations within 5 years after surgery. Radiomics features were extracted from manually segmented tumor on CT images and were then selected using four different feature selection methods sequentially. Multivariate logistic regression analysis was conducted to identify clinical features associated with recurrence. Radiomics, clinical, and combined models were constructed separately using logistic regression (LR), support vector machine (SVM), k-nearest neighbor (KNN), and neural network (NN), respectively. Receiver operating characteristic analysis was performed to evaluate the model performance in predicting recurrence. A nomogram was established based on all relevant features, with its reliability and reproducibility verified using calibration curves and decision curve analysis (DCA).

RESULTS

Eighty-nine patients with PTC experienced recurrence. A total of 1218 radiomics features were extracted from each segmentation. Five radiomics and six clinical features were related to recurrence. Among the 4 radiomics models, the LR-based and SVM-based radiomics models outperformed the NN-based radiomics model (P = 0.032 and 0.026, respectively). Among the 4 clinical models, only the difference between the area under the curve (AUC) of the LR-based and NN-based clinical model was statistically significant (P = 0.035). The combined models had higher AUCs than the corresponding radiomics and clinical models based on the same classifier, although most differences were not statistically significant. In the validation cohort, the combined models based on the LR, SVM, KNN, and NN classifiers had AUCs of 0.746, 0.754, 0.669, and 0.711, respectively. However, the AUCs of these combined models had no significant differences (all P > 0.05). Calibration curves and DCA indicated that the nomogram have potential clinical utility.

CONCLUSIONS

The combined model may have potential for better prediction of PTC recurrence than radiomics and clinical models alone. Further testing with larger cohort may help reach statistical significance.

The American Thyroid Association risk stratification and long-term outcomes of differentiated thyroid cancer: a 20-year follow-up of patients in Saudi Arabia

Background

Studies have reported differing factors associated with poor outcomes in patients with differentiated thyroid cancer (DTC). We aimed to describe our 20 years of experience in the management of thyroid cancer (TC) and identify predictors of treatment outcomes.

Methods

We conducted a retrospective review of medical records of patients with TC seen in the Thyroid Center at King Saud University Medical City (KSUMC) in Riyadh, Saudi Arabia, between the years 2000 and 2020. Demographic and clinical data including pathological characteristics were collected. The American Thyroid Association (ATA) risk stratification was determined for all patients at the postoperative period as well as the response to therapy at the final follow-up visit.

Results

A total of 674 patients (mean age: 47.21 years) with TC, 571 (84.7%) of which were women, were included. There were 404 (60.0%) patients with ATA low risk, 127 (18.8%) with intermediate risk, and 143 (21.2%) with high-risk histology. Overall, 461 patients (68.4%) had an excellent response to treatment, 65 (9.6%) had an indeterminate response, 83 (12.3%) had a biochemical incomplete response, and 65 (9.6%) had a structural incomplete response. Patients who had an excellent response were mostly ATA low risk (n = 318 of 431, 68.1%), whereas 40 of 65 patients (61.5%) of those with ATA high-risk histology had a structural incomplete response to treatment. There were significantly more women who had an excellent response compared with men. Obesity, lymphovascular invasion, and size of the tumor were significant predictors of worse outcomes to therapy.

Conclusion

Tumor size, lymphovascular invasion, and obesity are strong predictors of a worse response to therapy among patients with TC. Patients with obesity should be carefully followed up regardless of their risk stratification in light of the recent compelling evidence associating obesity with thyroid cancer and its higher risk of a worse disease outcome. ATA risk stratification is well correlated with patient long-term outcomes.