Background: Thermal ablation (TA) has been applied in patients with low-risk papillary thyroid microcarcinoma (PTMC) who refuse surgery or active surveillance (AS). Recently, TA has been proposed as a potential therapeutic option for patients who are suitable for surgery or AS. However, the clinical outcomes of TA versus surgery remains controversial because of a lack of sufficient data. This study aimed to compare the clinical outcomes between radiofrequency ablation (RFA) versus thyroid lobectomy (TL) for low-risk PTMC in a large cohort. Methods: This retrospective study evaluated 884 patients with unifocal low-risk PTMC treated with TL or RFA from June 2014 to March 2018. Among them, 460 patients underwent TL (TL group) and 424 patients, who refused surgery or AS, underwent RFA (RFA group). Patients were regularly followed up after treatment. Local tumor progression, recurrence-free survival (RFS), complications, and treatment variables, including procedure time, estimated blood loss, hospitalization, and cost, were compared after propensity score matching (PSM). Results: After PSM, a total of 332 patients underwent TL (mean ages 43.8 ± 9.5 years) and 332 underwent RFA (mean ages 44.1 ± 9.5 years). During the follow-up (median [interquartile ranges], 48.3 [23.2] months), no significant differences were observed in local tumor progression (1.8% vs. 3.3%, p = 0.209), lymph node metastasis (0.6% vs. 0.6%, p = 1.000), recurrent PTMC (1.2% vs. 2.4%, p = 0.244), persistent lesion (0% vs. 0.3%, p = 0.317), and 4-year RFS rates (98.2% vs. 97.0%, p = 0.223) between the TL and RFA groups. Distant metastasis was not detected. None of the patients who were treated by RFA underwent delayed surgery. Patients undergoing RFA had shorter procedure time (3.4 [2.5] vs. 86.0 [37.0] minutes, p < 0.001), lower estimated blood loss (0 vs. 20 [10.0] mL, p < 0.001), shorter hospitalization (0 vs. 7.0 [3.0] days, p < 0.001), lower cost ($2035.7 [254.0] vs. $2269.1 [943.4], p < 0.001) and lower complication rate (0% vs. 4.5%, p < 0.001) than those treated by TL. The association between treatment modality and recurrence remained nonsignificant after Cox analysis ( p = 0.247). Conclusions: This large matched study revealed comparable four-year clinical outcomes between RFA and TL for low-risk PTMC. As a minimally invasive modality, RFA may be a promising alternative to the existing treatment options for low-risk PTMC.

Purpose: To evaluate the safety and efficacy of ultrasound-guided RFA for the treatment of papillary thyroid microcarcinoma (PTMC). Materials and methods: The data of 204 nodules from 198 PTMC patients who were treated using RFA were retrospectively reviewed in this study. Demographic variables, complication details and CEUS results in different time points were collected. The volumes and volume reduction rate (VRR) of the ablated area under CEUS at different follow-up time points were calculated and compared. Results: All the patients were successfully treated without major complication. Mild complications included cervical discomfort in three cases, postoperative cervical pain in one case, and transient hoarse voice in five cases. The volume of the ablated area in the 1st, 3rd, 6th, 12th, 18th and 24th month postoperatively were 241.7 ± 298.3mm³, 89.8 ± 147.2 mm³, 37.6 ± 87.2 mm³, 13.6 ± 59.8 mm³, 2.4 ± 14.4 mm³, and 0.2 ± 2.0 mm³ respectively, with a statistically significant decrease (F = 138.1, p = .000), and the VRR in those time points were 73.9 ± 13.7%, 90.5 ± 8.2%, 96.1 ± 5.9%, 98.8 ± 3.2%, 99.6 ± 1.9% and 99.8 ± 1.0% respectively, with a statistically significant decrease (F = 695.3, p = .000). Conclusions: US-guided RFA is safe and effective for PTMC, with a good oncological outcome and VRR. Further randomized controlled prospective trials are still needed to compare the value of RFA and surgery.

Background: Prediction of lymph node metastasis (LNM) is critical for individualized management of papillary thyroid carcinoma (PTC) patients to avoid unnecessary overtreatment as well as undesired under-treatment. Artificial intelligence (AI) trained by thyroid ultrasound (US) may improve prediction performance. Methods: From September 2017 to December 2018, patients with suspicious PTC from the first medical center of the Chinese PLA general hospital were retrospectively enrolled to pre-train the multi-scale, multi-frame, and dual-direction deep learning (MMD-DL) model. From January 2019 to July 2021, PTC patients from four different centers were prospectively enrolled to fine-tune and independently validate MMD-DL. Its diagnostic performance and auxiliary effect on radiologists were analyzed in terms of receiver operating characteristic (ROC) curves, areas under the ROC curve (AUC), accuracy, sensitivity, and specificity. Results: In total, 488 PTC patients were enrolled in the pre-training cohort, and 218 PTC patients were included for model fine-tuning (n = 109), internal test (n = 39), and external validation (n = 70). Diagnostic performances of MMD-DL achieved AUCs of 0.85 (95% CI: 0.73, 0.97) and 0.81 (95% CI: 0.73, 0.89) in the test and validation cohorts, respectively, and US radiologists significantly improved their average diagnostic accuracy (57% vs. 60%, P = 0.001) and sensitivity (62% vs. 65%, P < 0.001) by using the AI model for assistance. Conclusions: The AI model using US videos can provide accurate and reproducible prediction of cervical lymph node metastasis in papillary thyroid carcinoma patients preoperatively, and it can be used as an effective assisting tool to improve diagnostic performance of US radiologists. Trial registration: We registered on the Chinese Clinical Trial Registry website with the number ChiCTR1900025592.