Background: The diagnosis of thyroid cancer and distinguishing benign from malignant thyroid nodules by junior radiologists can be challenging. This study aimed to develop a computer-aided diagnosis (CAD) system based on the Thyroid Imaging Reporting and Data System (TI-RADS) to distinguish benign from malignant thyroid nodules by analyzing ultrasound images to improve the diagnostic performance of junior radiologists. Material/Methods: A modified TI-RADS based on a convolutional neural network (CNN) was used to develop the CAD system. This retrospective study reviewed 789 thyroid nodules from 695 patients and included radiologists with different diagnostic experience. Five study groups included the CAD group, the junior radiologist group, the intermediate-level radiologist group, the senior radiologist group, and the group in which the junior radiologist used the CAD system. The ultrasound findings were reviewed and compared with the histopathology diagnosis. Results: The CAD system for the diagnosis of thyroid cancer showed an accuracy of 80.35%, a sensitivity of 80.64%, a specificity of 80.13%, a positive predictive value (PPV) of 76.02%, a negative predictive value (NPV) of 84.12%, and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.87. The accuracy of the junior radiologists in diagnosing thyroid cancer using CAD was similar to that of intermediate-level radiologists (79.21% vs. 77.57%; P=0.427). Conclusions: The use of ultrasound CAD based on the TI-RADS showed potential for distinguishing between benign and malignant thyroid nodules and improved the diagnostic performance of junior radiologists.
Patients with microinvasive carcinoma often have favorable prognosis, but it remains unclear whether this special type of breast cancer represents a distinct morphological entity with its own biological features and clinical behavior distinct from those of ductal carcinoma in situ (DCIS). The study is a retrospective analysis of a large patient cohort from a single institution. One hundred and thirty one microinvasive carcinoma and 451 DCIS cases were collected. ER, PR, HER2, and Ki67 were examined by immunohistochemistry in pathological sections. We assessed the clinicopathologic characteristics, molecular features, and survival status of microinvasive carcinoma and compared to those of DCIS. Microinvasive carcinoma differed from DCIS with respect to tumor size, lymph node status, and initial presentation (P < 0.05). There was a significant difference in nuclear grade among microinvasive carcinoma of different molecular subtype (P < 0.05). The clinicalpathologic features and outcomes of patients with microinvasive carcinoma were similar to those with DCIS. The 5-year OS rate for microinvasive carcinoma and DCIS patients was 99.0 and 99.2%, respectively. A combination of pathologic, clinical, and molecular factors may ultimately reveal more powerful and robust measures for disease classification than any one modality alone. Microinvasive carcinoma does not significantly predict for worse DFS or OS in comparison with patients with DCIS.
Purpose: To evaluate the clinical application of core-needle biopsy (CNB) for low-risk papillary thyroid microcarcinoma (PTMC) after radiofrequency ablation (RFA) Methods: A total of 202 patients with 211 low-risk PTMCs were included in this study. RFA procedure was used the hydrodissection technique and moving-shot technique. Patients were followed at 1, 3, 6, 12 months and every 6 months thereafter. The volume of ablation area and the volume reduction ratio (VRR) were calculated. At 3 or 6 months after RFA, CNB was performed to the central zone, the peripheral zone and surrounding thyroid parenchyma for post-ablation evaluation. Results: The mean volume of tumors was 102.34±93.84 mm 3 (range 4.19-424.10 mm 3), which decreased significantly to 1.37±7.74 mm 3 (range 0-73.30 mm 3) at a mean follow-up time of 24.42±9.15 months (range 3-42 months) with a mean VRR of 99.14±4.18% (range 71.88-100%). A total of 3 ablation areas had positive CNB in the peripheral zone and underwent additional RFA. No recurrent or suspicious metastatic lymph nodes were detected Conclusion: CNB is a feasible and effective evaluation for low-risk PTMC after RFA, which can detect residual cancer cells early.
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.