9,736 research outputs found
Applications of machine learning and deep learning to thyroid imaging: Where do we stand?
No full textUltrasonography (US) is the primary diagnostic tool used to assess the risk of malignancy and to inform decision-making regarding the use of fine-needle aspiration (FNA) and post-FNA management in patients with thyroid nodules. However, since US image interpretation is operator-dependent and interobserver variability is moderate to substantial, unnecessary FNA and/or diagnostic surgery are common in practice. Artificial intelligence (AI)-based computer-aided diagnosis (CAD) systems have been introduced to help with the accurate and consistent interpretation of US features, ultimately leading to a decrease in unnecessary FNA. This review provides a developmental overview of the AI-based CAD systems currently used for thyroid nodules and describes the future developmental directions of these systems for the personalized and optimized management of thyroid nodules
The effect of fibrin glue on the quantity of drainage after thyroidectomy: a randomized controlled pilot trial
No full textPURPOSE: A seroma is a collection of exudates after surgical trauma in wound healing. Fibrin glue is used to prevent seroma by reducing the generation of exudate. However, the impact of fibrin glue on the prevention of seroma remains debatable. Therefore, we conducted a randomized controlled pilot trial to investigate the effect of the amount of fibrin glue used on the generation of exudate after thyroidectomy and the sample size of future definitive trials. METHODS: Between February and December 2020, 41 patients were enrolled; 21 patients in the low fibrin group and 20 in the high fibrin group. Stratified randomization was performed based on sex, body mass index, and thyroiditis. All patients underwent total thyroidectomy and bilateral central compartment dissection. In the low and high fibrin groups, 2 mL and 6 mL of fibrin glue were applied to patients, respectively. RESULTS: Both the total drain volume and flow rate during the first 12 hours were lower in the high fibrin group than in the low fibrin group (65.0 mL vs. 47.6 mL, P = 0.008 and 2.7 mL/hr vs. 1.8 mL/hr, P = 0.002, respectively). The calculated sample size for future randomized controlled trial was 32 patients (alpha = 0.05, power = 0.8), and the power of this trial was 0.91 with micro(1) = 2.7, micro(2) = 1.8, sigma = 0.9, and alpha = 0.05 (micro = mean, sigma = standard deviation). CONCLUSION: Six milliliters of fibrin glue could reduce total drain volume and flow rate of exudate after thyroidectomy. Therefore, applying an appropriate amount of fibrin glue after thyroidectomy may reduce postoperative seroma
Korean thyroid imaging reporting and data system: Current status, challenges, and future perspectives
No full textThe Korean Thyroid Imaging Reporting and Data System (K-TIRADS) is an ultrasound-based risk stratification system for thyroid nodules that has been widely applied for the diagnosis and management of thyroid nodules since 2016. This review article provides an overview of the use of the K-TIRADS compared with other risk stratification systems. Moreover, this review describes the challenges in the clinical application of the K-TIRADS, as well as future development directions toward the personalized management of patients with thyroid nodules
Minimally Invasive Treatment for Benign Parathyroid Lesions: Treatment Efficacy and Safety Based on Nodule Characteristics
No full textOBJECTIVE: This study aimed to evaluate the efficacy and safety of ultrasound (US)-guided minimally invasive treatment in patients with parathyroid lesions. MATERIALS AND METHODS: This study included 27 patients who had undergone US-guided radiofrequency ablation (RFA) or ethanol ablation (EA) for parathyroid lesions between January 2010 and 2018. RFA was performed in 19 patients with primary hyperparathyroidism (PHPT, n = 11) or secondary hyperparathyroidism (SHPT, n = 8), and EA was performed in eight patients with symptomatic nonfunctioning parathyroid cysts (SNPCs). Nodule size, volume, serum parathyroid hormone (PTH) and calcium levels were recorded before and after treatment. Complications were evaluated during and after treatment. RESULTS: In patients with PHPT, significant reductions in size and volume were noted after RFA at 6- and 12-month follow-up (all, p < 0.05). Seven nodules nearly completely disappeared (residual volume < 0.1 mL); serum PTH and calcium levels were reduced to normal ranges (7/11, 63.6%). Four patients experienced partial reductions of serum PTH and calcium levels (4/11, 36.4%). In patients with SHPT, three experienced therapeutic response of serum PTH (3/8, 37.5%), while five showed persistent hyperparathyroidism (5/8, 62.5%) within 6 months after RFA. In patients with SNPCs, EA resulted in significant reductions in cyst size and volume (all, p < 0.05) at the last follow-up. A total of four complications (two transient hypocalcemia [RFA], one permanent [RFA], and one transient [EA] hoarseness) were observed. CONCLUSION: Minimally invasive treatments, such as RFA and EA, may serve as therapeutic alternatives for patients with PHPT or SNPCs; they may have limited usefulness in patients with SHPT
Real-World Performance of Computer-Aided Diagnosis System for Thyroid Nodules Using Ultrasonography
No full textThis study evaluated the diagnostic performance of a commercially available computer-aided diagnosis (CAD) system (S-Detect 1 and S-Detect 2 for thyroid) for detecting thyroid cancers. Among 218 thyroid nodules in 106 patients, the sensitivity, specificity, positive predictive value, negative predictive value and accuracy of the CAD systems were 80.2%, 82.6%, 75.0%, 86.3% and 81.7%, respectively, for the S-Detect 1 and 81.4%, 68.2%, 62.5%, 84.9% and 73.4%, respectively, for the S-Detect 2. The inter-observer agreement between the CAD system and radiologist for the description of calcifications was fair (kappa=0.336), while the final diagnosis and each ultrasonographic descriptor showed moderate to substantial agreement for the S-Detect 2. To conclude, the current CAD systems had limited specificity in the diagnosis of thyroid cancer. One of the main limitations of the S-Detect 2 was its inaccuracy in recognizing calcifications, which meant that differentiation had to be undertaken by the radiologist
Development of a machine learning-based fine-grained risk stratification system for thyroid nodules using predefined clinicoradiological features
No full textObjective: We constructed and validated a machine learning-based malignancy risk estimation model using predefined clinicoradiological features, and evaluated its clinical utility for the management of thyroid nodules. Methods: In total, 5708 benign (n = 4597) and malignant (n = 1111) thyroid nodules were collected from 5081 consecutive patients treated in 26 institutions. Seventeen experienced radiologists evaluated nodule characteristics on ultrasonographic images. Eight predictive models were used to stratify the thyroid nodules according to malignancy risk; model performance was assessed via nested 10-fold cross-validation. The best-performing algorithm was externally validated using data for 454 thyroid nodules from a tertiary hospital, then compared to the Thyroid Imaging Reporting and Data System (TIRADS)–based interpretations of radiologists (American College of Radiology, European and Korean TIRADS, and AACE/ACE/AME guidelines). Results: The area under the receiver operating characteristic (AUROC) curves of the algorithms ranged from 0.773 to 0.862. The sensitivities, specificities, positive predictive values, and negative predictive values of the best-performing models were 74.1–76.6%, 80.9–83.4%, 49.2–51.9%, and 93.0–93.5%, respectively. For the external validation set, the ElasticNet values were 83.2%, 89.2%, 81.8%, and 90.1%, respectively. The corresponding TIRADS values were 66.5–85.0%, 61.3–80.8%, 45.9–72.1%, and 81.5–90.3%, respectively. The new model exhibited a significantly higher AUROC and specificity than did the TIRADS risk stratification, although its sensitivity was similar. Conclusion: We developed a reliable machine learning–based predictive model that demonstrated enhanced specificity when stratifying thyroid nodules according to malignancy risk. This system will contribute to improved personalized management of thyroid nodules.
Key Points: • The area under the receiver operating characteristic (AUROC) curve, sensitivity, and specificity of our model were 0.914, 83.2%, and 89.2%, respectively (derived using the validation dataset). • Compared to the TIRADS values, the AUROC and specificity are significantly higher, while the sensitivity is similar. • An interactive version of our AI algorithm is athttp://tirads.cdss.co.kr
Clinical practice guidelines for radiofrequency ablation of benign thyroid nodules: A systematic review
No full textPurpose: Thermal ablation is a novel treatment alternative for benign thyroid nodules, and one of the most promising thermal ablation techniques is radiofrequency ablation (RFA). Considering the increasing use of thyroid RFA, some scientific societies have proposed clinical practice guidelines. We systemically reviewed and compared these guidelines for thyroid RFA to identify a standard treatment strategy that represents the positions of most societies. Methods: We searched the MEDLINE and EMBASE databases for studies with human participants that were published in English between January 1, 2000 and August 2, 2019. Studies containing clinical practice guidelines for the RFA of benign thyroid nodules were included. We extracted data regarding indications, pre-and post-procedural evaluations, treatment techniques, and the need to obtain informed consent. Results: Of the 83 studies found, four studies were included, and one study was added after searching the bibliographies of those articles. The five included studies were guidelines developed by the Korean Society of Thyroid Radiology, a group of experts from Italian scientific societies, the Italian Working Group on Minimally Invasive Treatments of the Thyroid, the United Kingdom’s National Institute for Health and Clinical Excellence, and a group of four professional Austrian thyroid associations. Indications, pre-and post-procedural evaluations, and techniques were similar across studies; however, differences in each of these categories were found. Conclusion: While the reviewed guidelines are similar with regard to major categories, international guidelines for the RFA of benign thyroid nodules should be established in the future
Standardized Imaging and Reporting for Thyroid Ultrasound: Korean Society of Thyroid Radiology Consensus Statement and Recommendation
No full textUltrasonography (US) is a primary imaging modality for diagnosing nodular thyroid disease and has an essential role in identifying the most appropriate management strategy for patients with nodular thyroid disease. Standardized imaging techniques and reporting formats for thyroid US are necessary. For this purpose, the Korean Society of Thyroid Radiology (KSThR) organized a task force in June 2021 and developed recommendations for standardized imaging technique and reporting format, based on the 2021 KSThR consensus statement and recommendations for US-based diagnosis and management of thyroid nodules. The goal was to achieve an expert consensus applicable to clinical practice
Development of an evidence-based clinical imaging diagnostic guideline for implant planning: Joint recommendations of the Korean Academy of Oral and Maxillofacial Radiology and National Evidence-based Healthcare Collaborating Agency
No full textPURPOSE: This study was conducted to develop an evidence-based clinical imaging diagnostic guideline for implant planning, taking into account efficacy, benefits, and risks. MATERIALS AND METHODS: The guideline development process employed the adaptation methodology used for Korean clinical imaging guidelines(K-CIG). Core databases(Ovid-Medline, Ovid-Embase, National Guideline Clearinghouse, Guideline International Network) and domestic databases (KoreaMed, KMbase, and KoMGI) were searched for guidelines. The retrieved articles were analyzed by 2 reviewers, and articles were selected using well-established inclusion criteria. RESULTS: The search identified 294 articles, of which 3 were selected as relevant guidelines. Based on those 3 guidelines, 3 recommendations for implant planning were derived. CONCLUSION: We recommend radiography or cone-beam computed tomography (CBCT) scanning for individual patients judged to require a cross-sectional image after reading of a panoramic X-ray image and a conventional intraoral radiological image. Various steps should be taken to raise awareness of these recommendations among clinicians and the public, and K-CIG should be regularly reviewed and revised
- …
