Efficacy and safety of single-session radiofrequency ablation for intrathoracic goiter: preliminary results and short-term evaluation.

BACKGROUND: An intrathoracic goiter (ITG) is defined as a thyroid extension below the sternal notch. Compared to cervical goiters, surgery for ITG is more challenging, with a higher risk of an extracervical approach. Ultrasound (US)-guided radiofrequency ablation (RFA) is a minimally invasive treatment modality. The purpose of this study was to prospectively evaluate the safety and efficacy of RFA in patients with ITG. METHODS: From a total of 324 patients who underwent thyroid RFA at a single medical center, 15 patients (mean age 52.2 years; 73.3% female) with 16 ITGs were included and classified into three grades and three types using the cross-section imaging CT system. Clinical features and demographics, degree of extension, RFA details, goiter volume, and complications were analyzed. RESULTS: Mean pre- and post-RFA goiter volumes as measured by US were 106.62 ± 61.82 and 25.09 ± 14.22 mL respectively, with a volume reduction rate (VRR) of 75.5% (p < 0.001) at 6 months. The VRR as measured by CT/MRI was 57.0 ± 10.0% (p < 0.001) at 6 months. The intrathoracic length reduction rate at 6 months was 44.9 ± 39.2% (p = 0.001). In addition, 4 (25%) ITGs had total regression of the intrathoracic extension, with a downgrade from grade 1 to cervical goiter. Mean pre- and post-RFA symptom and cosmetic scores were 1.53 and 0.15 (p = 0.001), and 2.67 and 2.00 (p = 0.001), respectively. One patient had transient vocal cord palsy and another had perithyroidal and mediastinal hemorrhage. CONCLUSION: US-guided RFA is an effective treatment for ITG in terms of both cervical and intrathoracic reductions with an acceptable complication rate.

Radiofrequency ablation for treatment of thyroid follicular neoplasm with low SUV in PET/CT study.

OBJECTIVES: To evaluate the feasibility of radiofrequency ablation (RFA) on follicular neoplasm with low standard uptake value (SUV) in a Positron emission tomography (PET/CT) study. METHODS: From January 2018 to July 2019, 86 consecutive patients were diagnosed with follicular neoplasm. Of the patients, 28 with PET/CT scans were enrolled in this study. All patients received ultrasound, fine/core needle aspiration, and PET/CT scan prior to treatment. In accordance with previous studies, we recommended 6 patients who had follicular neoplasm with SUVmax ≥5 undergo surgical resection due to an elevated suspicion of malignancy. For 22 patients SUVmax <5, RFA was performed using the moving shot technique. Ultrasound was performed 6 to 12 months after each procedure. RESULTS: Statistically significant volume reductions during follow-up between values prior to RFA and 12 months post RFA were demonstrated (12.6 ± 20.9 vs. 2.4 ± 3.0 cm3, p < 0.001). Volume reduction ratios at 6-12 months (mean: 10.1 months) after RFA were 73.3% ± 17.7%. One patient presented with vocal cord palsy and recovered within 3 months after RFA. No postprocedural hypothyroidism occurred in the RFA patients. CONCLUSIONS: By using PET/CT, we can select patients with low SUV follicular neoplasm. RFA offers a safe and feasible alternative treatment option for patients unsuitable or unwilling to undergo surgery.KEY POINTSBy using positron emission tomography-computed tomography, we can distinguish low SUV follicular neoplasm for radiofrequency ablation.For low SUV follicular neoplasm, RF ablation offers a safe and effective alternative treatment option for patients unsuitable or unwilling to undergo surgery.

Efficacy and safety of single-session radiofrequency ablation for benign thyroid nodules of different sizes: a retrospective study.

PURPOSE: To compare the effectiveness of radiofrequency ablation (RFA) for benign thyroid nodules (BTNs) among groups presenting with different nodule volumes. MATERIALS AND METHODS: This retrospective study evaluated 186 patients with BTNs who underwent ultrasound guided RFA treatment. The BTNs were categorized into small (≤10 ml); medium (10-30 ml); and large (>30 ml) according to the initial volume of BTNs before ablation. The RFA procedures were performed using the moving shot technique. The volume reduction ratio (VRR) of each nodule, cosmetic score, symptomatic score, and complications were analyzed at 1, 3, and 6 months after RFA treatment and the three groups compared. RESULTS: At 1-month follow-up, the large nodules group showed significantly greater VRR compared to the other two groups (small, 31.88% ± 37.91; medium, 38.9% ± 19.18; large, 48.7% ± 20.43, p = .03). At 6-month follow-up, there was no significant difference of VRR among the three groups (small, 74.6% ± 20.92; medium, 68.1% ± 17.07; large, 75.0% ± 11.88). The most common presented complication was temporary vocal palsy (6 patients; small, n = 1; medium, n = 1; large, n = 3). Additionally, one skin burn, one hematoma, and one nodular rupture of BTNs occurred after the procedures. The complication rate of the large nodules group was highest among the three groups and showed a considerable difference (8 patients; small, n = 1, 2.1%; medium, n = 2, 4.5%; large, n = 5, 11.4%, p = .061). CONCLUSIONS: RFA was confirmed as effective in patients with large thyroid nodule (>30ml), with therapeutic efficacy similar to patients with smaller thyroid nodules.

Evaluation of Outcomes following Radiofrequency Ablation for Treatment of Parotid Tail Warthin Tumors.

PURPOSE: To evaluate efficacy and safety of radiofrequency (RF) ablation for parotid Warthin tumor. MATERIALS AND METHODS: From September 2016 to August 2017, 7 consecutive patients with biopsy-proven parotid Warthin tumors who did not undergo surgery presented with symptoms or cosmetic concerns and underwent US-guided percutaneous RF ablation treatment. RF ablation procedures were performed using the moving shot technique. US, contrast-enhanced CT, or MR imaging was performed 6-12 months after each procedure. Complications and cosmetic scale improvement after RF ablation were also evaluated. RESULTS: There was a significant reduction in mean tumor volume from 14.6 cm3 ± 13.1 (range, 1.9-35.5 cm3) to 0.8 cm3 ± 0.5 (range, 0.2-1.54 cm3) and a mean cosmetic scale improvement (from 4 to 1) on imaging studies 6-12 months after RF ablation compared with before RF ablation (P < .05). Volume reduction ratios at 1-2 months, 5-6 months, and 10-12 months after RF ablation were 51.2% ± 18.1%, 87.8% ± 10.6%, and 94.3% ± 2.0%. There was no facial nerve injury. One patient with parotitis and hematoma recovered in 1 week. CONCLUSIONS: RF ablation using the moving shot technique could be an effective and safe alternative treatment for parotid tail Warthin tumors in patients unsuitable for or unwilling to undergo surgical resection.

Deep Learning-Based Surgical Treatment Recommendation and Nonsurgical Prognosis Status Classification for Scaphoid Fractures by Automated X-ray Image Recognition.

Biomedical information retrieval for diagnosis, treatment and prognosis has been studied for a long time. In particular, image recognition using deep learning has been shown to be very effective for cancers and diseases. In these fields, scaphoid fracture recognition is a hot topic because the appearance of scaphoid fractures is not easy to detect. Although there have been a number of recent studies on this topic, no studies focused their attention on surgical treatment recommendations and nonsurgical prognosis status classification. Indeed, a successful treatment recommendation will assist the doctor in selecting an effective treatment, and the prognosis status classification will help a radiologist recognize the image more efficiently. For these purposes, in this paper, we propose potential solutions through a comprehensive empirical study assessing the effectiveness of recent deep learning techniques on surgical treatment recommendation and nonsurgical prognosis status classification. In the proposed system, the scaphoid is firstly segmented from an unknown X-ray image. Next, for surgical treatment recommendation, the fractures are further filtered and recognized. According to the recognition result, the surgical treatment recommendation is generated. Finally, even without sufficient fracture information, the doctor can still make an effective decision to opt for surgery or not. Moreover, for nonsurgical patients, the current prognosis status of avascular necrosis, non-union and union can be classified. The related experimental results made using a real dataset reveal that the surgical treatment recommendation reached 80% and 86% in accuracy and AUC (Area Under the Curve), respectively, while the nonsurgical prognosis status classification reached 91% and 96%, respectively. Further, the methods using transfer learning and data augmentation can bring out obvious improvements, which, on average, reached 21.9%, 28.9% and 5.6%, 7.8% for surgical treatment recommendations and nonsurgical prognosis image classification, respectively. Based on the experimental results, the recommended methods in this paper are DenseNet169 and ResNet50 for surgical treatment recommendation and nonsurgical prognosis status classification, respectively. We believe that this paper can provide an important reference for future research on surgical treatment recommendation and nonsurgical prognosis classification for scaphoid fractures.

Effective Invasiveness Recognition of Imbalanced Data by Semi-Automated Segmentations of Lung Nodules.

Over the past few decades, recognition of early lung cancers was researched for effective treatments. In early lung cancers, the invasiveness is an important factor for expected survival rates. Hence, how to effectively identify the invasiveness by computed tomography (CT) images became a hot topic in the field of biomedical science. Although a number of previous works were shown to be effective on this topic, there remain some problems unsettled still. First, it needs a large amount of marked data for a better prediction, but the manual cost is high. Second, the accuracy is always limited in imbalance data. To alleviate these problems, in this paper, we propose an effective CT invasiveness recognizer by semi-automated segmentation. In terms of semi-automated segmentation, it is easy for doctors to mark the nodules. Just based on one clicked pixel, a nodule object in a CT image can be marked by fusing two proposed segmentation methods, including thresholding-based morphology and deep learning-based mask region-based convolutional neural network (Mask-RCNN). For thresholding-based morphology, an initial segmentation is derived by adaptive pixel connections. Then, a mathematical morphology is performed to achieve a better segmentation. For deep learning-based mask-RCNN, the anchor is fixed by the clicked pixel to reduce the computational complexity. To incorporate advantages of both, the segmentation is switched between these two sub-methods. After segmenting the nodules, a boosting ensemble classification model with feature selection is executed to identify the invasiveness by equalized down-sampling. The extensive experimental results on a real dataset reveal that the proposed segmentation method performs better than the traditional segmentation ones, which can reach an average dice improvement of 392.3%. Additionally, the proposed ensemble classification model infers better performances than the compared method, which can reach an area under curve (AUC) improvement of 5.3% and a specificity improvement of 14.3%. Moreover, in comparison with the models with imbalance data, the improvements of AUC and specificity can reach 10.4% and 33.3%, respectively.

Long-Term Outcomes of Radiofrequency Ablation for Treatment of Cystic Warthin Tumors versus Solid Warthin Tumors.

BACKGROUND: To describe the long-term outcomes of radiofrequency ablation (RFA) of parotid Warthin tumors that have different consistencies and locations. METHODS: We reviewed ten patients with Warthin tumors undergoing RFA treatment from 2016 to 2019. The mean follow-up was 24.3 ± 13.1 months (range 7-42 months). RESULTS: RFA was performed on 11 tumors in ten patients. Cystic tumors (n = 4) had better volume reduction ratios (VRR) than solid tumors (n = 7) at month one and month six, following RFA (77.9% vs. 47.3%, 95.1% vs. 80.6%, respectively, p = 0.003). Tumors in both superficial lobes and deep lobes (n = 7) were larger than tumors in superficial lobes alone (n = 4), though there was no difference in VRR after treatment. All residual tumors were found in superficial lobes. There was no increase in residual tumor size. Every patient showed marked cosmetic improvements, with visible tumors becoming non-palpable masses. CONCLUSIONS: RFA is a safe and effective treatment for Warthin tumors, with better volume reduction in cystic tumors. Results remained satisfying over the long-term for all residual tumors found in superficial lobes, making it easier for re-intervention if necessary.