Classifier Model Based on Machine Learning Algorithms: Application to Differential Diagnosis of Suspicious Thyroid Nodules via Sonography
|
|
- Colin Reeves
- 5 years ago
- Views:
Transcription
1 Neuroradiology/Head and Neck Imaging Original Research Wu et al. Use of Machine Learning Algorithms to Evaluate Thyroid Nodules Neuroradiology/Head and Neck Imaging Original Research Hongxun Wu 1 Zhaohong Deng 2 Bingjie Zhang 1 Qianyun Liu 1 Junyong Chen 2 Wu H, Deng Z, Zhang B, Liu Q, Chen J Keywords: classifier, nodule, thyroid, ultrasound DOI: /AJR Received November 9, 2015; accepted after revision April 1, Supported by grant H from Planned Project of Health Department of Jiangsu Province. 1 Department of Ultrasound, Jiangyuan Hospital Affiliated to Jiangsu Institute of Nuclear Medicine (Key Laboratory of Nuclear Medicine, Ministry of Health/ Jiangsu Key Laboratory of Molecular Nuclear Medicine), 20 Qianrong Rd, Wuxi, Jiangsu , China. Address correspondence to H. Wu (whxmd@outlook.com). 2 School of Digital Media, Jiangnan University, Wuxi, Jiangsu, China. AJR 2016; 207: X/16/ American Roentgen Ray Society Classifier Model Based on Machine Learning Algorithms: Application to Differential Diagnosis of Suspicious Thyroid Nodules via Sonography OBJECTIVE. The purpose of this article is to construct classifier models using machine learning algorithms and to evaluate their diagnostic performances for differentiating malignant from benign thyroid nodules. MATERIALS AND METHODS. This study included 970 histopathologically proven thyroid nodules in 970 patients. Two radiologists retrospectively reviewed ultrasound images, and nodules were graded according to a five-tier sonographic scoring system. Statistically significant variables based on an experienced radiologist s observations were obtained with attribute optimization using fivefold cross-validation and applied as the input nodes to build models for predicting malignancy of nodules. The performances of the machine learning algorithms and radiologists were compared using ROC curve analysis. RESULTS. Diagnosis by the experienced radiologist achieved the highest predictive accuracy of 88.66% with a specificity of 85.33%, whereas the radial basis function (RBF) neural network (NN) achieved the highest sensitivity of 92.31%. The AUC value for diagnosis by the experienced radiologist (AUC = ) was greater than those for diagnosis by the less experienced radiologist, the naïve Bayes classifier, the support vector machine, and the RBF-NN (AUC = , , , and , respectively; p < 0.05). CONCLUSION. The machine learning algorithms underperformed with respect to the experienced radiologist s readings used to construct them, and the RBF-NN outperformed the other machine learning algorithm models. T hyroid nodules are very common, with an incidence of 10 67% among the general population as identified by high-resolution ultrasound [1, 2]. Although most thyroid nodules are benign, according to the results of ultrasound-guided fine-needle aspiration, 9 15% of nodules are malignant [2 4]. After evaluation of a thyroid nodule, it is important to determine the most appropriate strategies to properly manage malignant nodules while avoiding unnecessary procedures and surgery in patients with benign nodules. Ultrasound is an ideal imaging modality for examining thyroid nodules because it is noninvasive and cost-effective. Many studies have investigated the use of ultrasound features for predicting the risk of nodule malignancy [2, 3, 5], and several ultrasound features have been proposed as possible markers of malignancy, including the presence of hypoechogenicity, microcalcifications, a tallerthan-wide shape, ill-defined margins, internal vascularity, extracapsular invasion, and a suspicious lymph node [6]. However, no single ultrasound feature is adequately sensitive or specific to identify all malignant nodules. Meanwhile, ultrasound is a rather subjective and operator-dependent diagnostic tool. High inter- and intraobserver agreement is achieved only among experienced radiologists for interpretation of ultrasound findings related to thyroid nodules [7]. In the past few decades, a number of machine learning algorithms have been developed to create classifier models for preoperation diagnosis, including binary logistic regression, the naïve Bayes classifier, the support vector machine (SVM), and the radial basis function (RBF) neural network (NN) [8 11], and these differ in terms of their corresponding characteristics. For instance, SVMs are basically widely accepted linear classifiers and are considered very effective for pattern recognition and machine learning. The key feature of the SVM is the maximization of the functional gap between two classes so as to minimize the general- AJR:207, October
2 Wu et al. ization error. The naïve Bayes classifier also has been widely used in disease diagnosis. An advantage of the naïve Bayes classifier is that it requires only a small amount of training data to estimate the parameters necessary for classification. In the current study, we designed classifier models using different machine learning algorithms to differentiate malignant from benign thyroid nodules on ultrasound and compared the diagnostic performances of the machine learning algorithms to that of two radiologists using ROC curve analysis. Materials and Methods Study Population The study cohort included 1073 patients who underwent partial or total thyroidectomy between January 2012 and June 2014 at Jiangsu Institute of Nuclear Medicine. The decision to undergo surgery was based on any one of the following criteria: first, abnormal results of ultrasound-guided fine-needle aspiration, including malignancy, suspicion of malignancy, and follicular lesion of undetermined significance; second, suspicious malignant ultrasound findings, including hypoechogenicity, microcalcifications, a taller-than-wide shape and associated cervical lymphadenopathy with round shape, intranodal cystic components, or microcalcifications; and third, pressure symptoms [12]. Patients medical records, including age, sex, ultrasound features of the dominant nodule, and histopathologic results, were collected retrospectively. The dominant nodule was defined as the nodule most likely to be malignant among all the nodules observed on ultrasound. The largest nodule was designated as the dominant nodule when none of the nodules showed suspicious ultrasound features. Nodule identification was achieved via ultrasound imaging and gross pathologic examination records. We excluded 103 nodules in 103 patients because the ultrasound data or images for these nodules were incomplete, or there were coalescent thyroid lesions not clearly distinguishable and matched with the histopathologic results. This retrospective study was approved by the institutional review board of Jiangsu Institute of Nuclear Medicine, and the need for informed patient consent for inclusion in this study was waived. Ultrasound and Image Interpretation Thyroid ultrasound examination was performed by a radiologist using an ultrasound system (iu22, Philips Healthcare) with a 5-12 MHz transducer. Static images were archived as jpeg image files for subsequent evaluation. The ultrasound images of the dominant nodule were presented in a random fashion by the study coordinator (an author with 6 years of ultrasound experience). During interpretation, two radiologists with differing experience in ultrasound examination of thyroid nodules (17 and 3 years, respectively) were blinded to any subsequent cytologic or histologic diagnosis as well as the assessments of the other radiologist. In the measurement of nodules, lengths corresponded to the long-axis measurements on the longitudinal scan, and widths and thicknesses corresponded to the short-axis measurements on the transverse scan. The following ultrasound features were documented for each nodule: location (left, right, or isthmus), position (upper pole, medium, or lower pole), shape (ovoid-to-round, taller-than-wide, or irregular), margin (ill-defined or well-defined), internal contents (solid, mixture, or cystic), echogenicity (hyperechoic, isoechoic, hypoechoic, or marked hypoechoic), calcification (microcalcification, macrocalcification, or rim calcification), echogenic foci in solid portion (absent or present), halo sign (usual or unusual), infiltration and extracapsular invasion (absent or present), multifocal (absent or present), increased intranodular vascularity (absent or present), and abnormal lymphadenopathy (absent or present). The definitions and categorizations of shape, echogenicity, and calcification were consistent with those used in the literature [6]. Partly interrupted rim calcification corresponded to incomplete peripheral calcification surrounding the lesion. Ill-defined margin included spiculated and microlobulated margin. The internal content was categorized in terms of the ratio of the cystic portion to the solid portion as solid ( 10% of the cystic portion), mixture (> 10% of the cystic portion and 90% of the cystic portion), and cystic (> 90% of the cystic portion) [6]. Echogenic foci were bright spots with comet tails caused by reverberation artifacts. When a lesion was surrounded by an irregular or thick anechoic halo, it was considered an unusual halo. Infiltration was defined as an interruption of the hyperechogenicity of the thyroid capsule. Extracapsular invasion was considered if the tumoral tissue extended beyond the contours of the thyroid gland and invaded into adjacent structures [13]. A multifocal lesion was defined by the presence of two or more isolated or noncontiguous lesions with similar suspicious malignant ultrasound features in one or both thyroid lobes [14]. Increased intranodular vascularity was defined by an increased predominance within the nodule in comparison with the surrounding parenchyma. Lymph nodes were considered abnormal when a suspicious sonographic finding (calcifications and cystic change) was present, whereas round shape, hyperechogenicity, and abnormal vascularity of lymph nodes were excluded for low specificity or positive predictive value [15, 16]. Sonographic Scoring System In accordance with our experiences, combined with the data available in the literature [16 18], we adopted a five-tier sonographic scoring system for stratifying the risk of nodule malignancy in routine clinical practice. Ultrasound features, including marked hypoechogenicity, taller-than-wide shape, microcalcifications, multifocal, infiltration or extracapsular invasion, and abnormal lymphadenopathy, were regarded as indications for malignancy. Borderline ultrasound features included hypoechogenicity, an irregular shape, an ill-defined margin, an unusual halo, increased intranodular vascularity, macrocalcifications, and partly interrupted rim calcifications. The ultrasound features of a benign nodule included isoechogenicity, hyperechogenicity, an ovoid-to-round shape, a well-defined margin, echogenic foci in the cystic portion, a usual halo (regular and thin), and a spongiform and pure cystic nodule. The criteria for ultrasound-based diagnosis of a thyroid nodule were as follows: If a nodule had three or more ultrasound features of malignancy, regardless of borderline or benign ultrasound features, the nodule was considered malignant. If a thyroid nodule had at least one ultrasound feature of malignancy, regardless of borderline or benign ultrasound features, it was considered as being suspicious for malignancy. If a thyroid nodule had one or more borderline ultrasound features without malignant features, regardless of benign ultrasound features, it was considered borderline. If a thyroid nodule had two or more benign ultrasound features suggesting no malignancy or borderline ultrasound features, it was considered as likely benign. Finally, if a thyroid nodule was a spongiform or pure cystic nodule with no features of malignancy or borderline ultrasound features, it was considered benign [18]. Classifier Model Construction We built the models using Matlab (version 8.1, MathWorks). The observations of radiologist 1 (i.e., the experienced radiologist) were evaluated using the machine learning algorithms to obtain the model diagnoses for the same case. The standard datamining process was adopted in the classifier development and consisted of the following steps: data cleaning and integration, data selection and transformation, and data mining and pattern evaluation. All variables describing clinical information and ultrasound features were selected as input variables for the classifier models. Subsequent attribute optimization was used to optimize variable selection and input node confirmation. A fivefold cross-validation using a train-and-test method was performed to guarantee the validity of the results. Unrelated and confounding variables were then pruned from the final models. A random number was assigned to 860 AJR:207, October 2016
3 Use of Machine Learning Algorithms to Evaluate Thyroid Nodules A B Fig. 1 Two patients with papillary thyroid carcinoma. In both cases, classic comet tail artifact that inverted echogenic triangle was clearly documented posterior to focus in solid portion. A, 51-year-old woman with papillary thyroid carcinoma. Longitudinal ultrasound image shows 4.6-mm hypoechogenic solid nodule (area within arrows) with internal echogenic foci in lower pole of right lobe of thyroid gland. Both radiologists classified nodule as borderline. Nodule had probability of malignancy of 58.4% for naïve Bayes classifier, 68.9% for support vector machine (SVM), and 67.1% for radial basis function (RBF) neural network (NN). B, 44-year-old man with papillary thyroid carcinoma. Ultrasound image shows 13.5-mm mixture nodule containing multiple punctate echogenic foci in both cystic and solid portions. Radiologist 1 classified nodule as borderline, and radiologist 2 classified it as likely benign. Nodule had probability of malignancy of 55.2% for naïve Bayes classifier, 61.0% for SVM, and 63.6% for RBF-NN. each nodule. Nodules with an odd number (n = 485, 50%) were assigned to a training cohort, and those with an even number were assigned to a validation cohort (n = 485, 50%). In the first training phase, we had applied three classification algorithms on the obtained significant attributes. For naïve Bayes classifier, we set the first evidence on the input nodes, and then the output nodes could be queried using Bayesian network inference. The links in the naïve Bayes classifier were directed from output to input, which made the classifier simplified, because there were no interactions between the inputs. The SVM classifier was trained with a learning algorithm from optimization theory. The training instances closest to the maximum margin hyperplane were called support vectors, which were then used to build an optimal linear separating hyperplane. The RBF-NN contained three layers of nodes but with only a single hidden layer. The classifier-adopted RBF-NN used a clustering method to determine the center of the RBF, and the least-mean square method was used to determine the connection weights between the hidden layer and output layer. Training was terminated when the error between the actual output and the desired output was minimized or the given maximum number of epochs to train was obtained. Cross-validation was used to reduce the risk of overtraining, which will lead to good performance in a training cohort but poor performance in a validation cohort. The data were split via stratified sampling to ensure the same class distribution in the subset to generate comparison results with lower bias. Subsequently, the classifiers were used for classification in the second validation phase. The performance was analyzed with ROC curves. Ultimately, once we add evidence to a trained and cross-validated classifier given prior knowledge, it will generate case-specific malignant prediction through predicting the probability of classification. Statistical Analysis Continuous variables are presented as mean ± SD and were compared with the two-sample t test. Categoric variables are presented as percentages, and chi-square or Fisher exact tests were used to determine the statistical significance of the differences between the two groups. For evaluation of the performance of machine learning algorithms and the two radiologists in the task of predicting the probability of malignancy, the AUC values were calculated and compared. Results Clinical Characteristics The mean age of the 970 patients was ± (SD) years (range, years); 756 (77.94%) were female and 214 (22.06%) were male. There were 507 cases of malignant nodules (52.27%) and 463 cases of benign nodules (47.73%). Diagnoses of malignancy included papillary thyroid carcinoma (n = 487), follicular thyroid carcinoma (n = 12), medullary thyroid carcinoma (n = 4), well-differentiated carcinoma (n = 3), and clear cell carcinoma (n = 1). The sex distribution was not statistically significantly different between the patients with malignant and benign nodules (maleto-female ratio, 103:404 vs 111:352; p = ), but a statistically significant difference in age was observed between the patients with malignant and benign nodules (44.76 ± years vs ± 12.14; p < 0.01). Benign nodules were statistically significantly larger than the malignant nodules (p < 0.01), and a taller-than-wide shape was found more frequently in malignant nodules (39.05%) than in benign nodules (10.37%). More malignant nodules had an ill-defined margin compared with the benign nodules (91.72% vs 57.24%). Solid nodules were more frequently detected among the malignant nodules (96.45% vs 67.82%). Hypoechogenicity was an ultrasound feature found in most malignant nodules (94.87%), and the frequency of microcalcifications in malignant nodules was statistically significantly higher than that in benign nodules (44.38% vs 8.64%). When echogenic foci presented in the solid portion, the prevalence of malignancy was 24.4% (10/41) (Fig. 1). The presence of unusual halo sign, infiltration and extracapsular invasion, and multifocal and abnormal lymphadenopathy were statistically significantly different between malignant and benign groups (p < 0.01). No statistically significant differences were found with respect to patient sex, left and right lobe location, cystic contents, hyperechogenicity and marked hypoechogenicity, macrocalcification, partly interrupted rim calcification, and increased intranodular vascularity between benign and malignant nodules (p > 0.05). Thus, these features were regarded as suspicious invalid redundant features for malignancy. AJR:207, October
4 Wu et al. TABLE 1: The Performance of Proposed Predictive Model With Suspicious Invalid Redundant Features Predictive Model Sensitivity (%) Specificity (%) Accuracy (%) AUC Naïve Bayes classifier (2.82) (6.13) (3.94) (0.0239) Support vector machine (3.46) (6.63) (3.97) (0.0247) Radial basis function neural network (2.61) (6.29) (3.54) (0.0232) Note Data are mean (SD). TABLE 2: The Performance of Proposed Predictive Model Without Suspicious Invalid Redundant Features Predictive Model Sensitivity (%) Specificity (%) Accuracy (%) AUC Naïve Bayes classifier (3.33) (6.38) (4.46) (0.0254) Support vector machine (3.46) (5.99) (3.29) (0.0284) Radial basis function neural network (2.67) (6.27) (3.56) (0.0210) Note Data are mean (SD). We assessed the predictive accuracy of machine learning algorithms, both including (Table 1) and excluding (Table 2) the suspicious invalid redundant features. After excluding the suspicious invalid redundant features, the accuracies of the naïve Bayes classifier and SVM for predicting malignancy of thyroid nodules (83.30% and 83.89%, respectively) were better than those achieved with inclusion of the suspicious invalid redundant features (82.99% and 83.71%, respectively; p < 0.05). After excluding the suspicious invalid redundant features, the accuracy of the RBF-NN was slightly less than that with inclusion of the suspicious invalid redundant features (83.61% vs 83.92%; p = ), whereas the AUC was higher with suspicious invalid redundant features excluded versus included ( vs ; p < 0.05). Therefore, we considered that the suspicious invalid redundant features were unrelated to the construction of the classifier and pruned them from the final models. Comparison of Models The performances of the proposed models were evaluated using the validation cohort (Table 3). The most favorable sensitivity, specificity, positive predictive, negative predictive, and accuracy values were achieved when we defined the indeterminate as benign. In the final evaluation of the validation cohort, radiologist 1 (the experienced radiologist) achieved the highest prediction accuracy of 88.66% with a sensitivity of 91.54% and a specificity of 85.33%. Radiologist 2 (the less experienced radiologist) achieved a prediction accuracy of 81.03% with a sensitivity of 85.38% and a specificity of 76.00%. For comparison, the respective corresponding values were 83.30%, 89.62%, and 76.00% for the naïve Bayes classifier; 83.09%, 89.23%, and 75.11% for the SVM; and 84.74%, 92.31%, and 76.00% for the RBF-NN. The AUC value for radiologist 1 was higher (AUC = ) than those for radiologist 2, naïve Bayes classifier, SVM, and RBF-NN (AUC = , , , and , respectively; p < 0.05). In addition, the AUC for the RBF-NN was statistically significantly higher than those for the other machine learning algorithms and radiologist 2 (all p < 0.05). Discussion The primary aim of this study was to design classifier models using different machine learning algorithms for the differential diagnosis of suspicious thyroid nodules on ultrasound. The use of more highly discriminatory attributes as inputs into the machine learning algorithms enhanced the accuracy of the evaluations. There was no interobserver bias for ultrasound procedures, which were performed by a single experienced radiologist. The bias in model construction was acceptable, because less misperception of the observations was achieved by using a single radiologist. The optimum classifier model with the RBF-NN could effectively predict malignancy (AUC = ) in thyroid nodules but underperformed compared with the experienced radiologist (AUC = ). The goal of thyroid nodule evaluation is to determine whether a nodule is benign or malignant to choose the most appropriate management. As a cost-effective tool, ultrasound has a high sensitivity for detecting thyroid nodules. Several published studies have proven that some ultrasound features are associated with malignancy, including hypoechogenicity, microcalcifications, a taller-than-wide shape, spiculated margins, and intranodular vascularity [2, 3, 5, 19 21]. Unfortunately, thyroid carcinoma can have different presentations depending on the histopathologic subtype. Therefore, the predictive values of these features are extremely variable between studies. In addition, variations in radiologists perceptions and the lack of standard definitions of the features observed TABLE 3: The Performance of Proposed Predictive Models and Two Radiologists in Validation Cohort Predictive Model Sensitivity (%) Specificity (%) Accuracy (%) AUC Radiologist (4.26) (5.04) (3.40) (0.0190) Radiologist (4.46) (6.13) (3.55) (0.0234) Naïve Bayes classifier (2.75) (5.59) (4.01) (0.0231) Support vector machine (3.55) (6.64) (4.48) (0.0280) Radial basis function neural network (4.33) (5.38) (4.10) (0.0231) Note Data are mean (SD). 862 AJR:207, October 2016
5 Use of Machine Learning Algorithms to Evaluate Thyroid Nodules in the images also contribute to variability in thyroid nodule diagnosis. In recent decades, a few clinical research groups have used data mining to develop quantitative and reproducible decision models for determining the diagnosis or treatment strategies in thyroid diseases [22 24]. Their results showed that machine learning algorithms could be helpful for improving the accuracy of diagnoses by reducing the diagnostic error rate. One key contributing factor to the efficiency of machine learning algorithms is the capability of incremental learning from qualitative data. Using a training dataset, the machine learning algorithms are capable of determining the probability of certain classes of thyroid disease in some cases, given the values of the predictor variables. Different machine learning algorithms were used in the current study in an attempt to select the best one that yields satisfactory results. Within a discriminative model, the SVM tends to find the optimal hyperplane between different categories, reflecting the differences between heterogeneous data. The SVM is widely used for classification because of its simplicity and robustness. However, the discriminative model is inherently supervised and, thus, cannot easily be extended to unsupervised learning [23, 25]. The naïve Bayes classifier, a generative model, analyzes the distribution of the data from the statistics and thereby reflects the similarity of homogeneous data. The naïve Bayes classifier is highly scalable and requires only a small amount of training data to estimate the parameters necessary for classification [26]. Both discriminative models and generative models have limitations, and neither model type provides a perfect solution for practical application. The RBF-NN, a hybrid classifier model merging the discriminative model (multilayer perceptron) with the generative model (gaussian mixture model), is able to approximate any arbitrary nonlinear function in a complex multidimensional space with computing complexity reduction [27]. Hence, with the properties of experiencebased learning and ability for generalization, the RBF-NN is regarded as an ideal solution for solving complex problems [28, 29]. On the basis of the results of the current study, compared with the other machine learning algorithms, the RBF-NN showed excellent performance in all aspects, and even though the accuracy of the RBF-NN was slightly reduced after exclusion of the suspicious invalid redundant features, the RBF-NN achieved the highest AUC value of These results also suggest that the RBF-NN had good performance with respect to noise data disposal. Overall, the proper selection of a classifier on the basis of the inherent properties was the key point for model construction. Accurate observation and interpretation of thyroid features is important for model construction; therefore, in the current study, we applied only the observations provided by the most experienced radiologist in developing the models. When we compared the diagnostic performances between the machine learning algorithms and radiologists, the RBF-NN significantly outperformed even the experienced radiologist in terms of sensitivity. This finding indicates that the RBF-NN has a better chance of correctly identifying positive cases (i.e., malignant thyroid nodules). However, none of the machine learning algorithms achieved the diagnostic performance in terms of accuracy, specificity, positive predictive value, and negative predictive value provided by the experienced radiologist. First, this outcome may be due to both the complexity of the machine learning algorithms and the huge processing power required for so many data points. Actually, it is impossible to construct a model that both captures the regularities in the training cohort accurately and generalizes those data for the validation cohort well. When the training cohort data present with a large amount of noise, the prediction will be less accurate. Therefore, technically, constructing an ideal model with an assumed infinitely large dataset cannot be achieved by simply expanding the dataset. Second, some quantitative and reproducible ultrasoundbased classification systems, including the thyroid imaging reporting and data system, have been developed to improve the consistency and quality of radiologic reporting [30, 31]. With consideration of the findings of a previous study [10], in a sense, the outperformance of an experienced radiologist may also be attributed to the application of a sonographic scoring system. In addition, machine learning algorithms have more difficulty in accurately predicting malignancy in nodules with two concomitant pathologic diagnoses. The poor learning ability of the models for some histopathologic subtypes is attributed to the limited number of cases. The significant difference in the diagnostic accuracy of the two radiologists may be explained by variations in observer perception and interpretation on the basis of the ultrasound features. Inexperienced or nonspecialist radiologists may overestimate their knowledge and experience, making decisions on the basis of a limited number of conspicuous features. In addition, they may fail to consider all of the features systematically. Machine learning algorithms have the capability to consistently and comprehensively merge all of the variables and readily adjust in the context of noisy data. Therefore, a classifier model based on a machine learning algorithm could potentially facilitate decision making and case education for inexperienced radiologists, which is consistent with the conclusion of a previous study [10]. There were some limitations to the current study. First, the results were derived from a selected preoperative population; consequently, the malignancy rate of thyroid nodules was relatively high (52.3%) compared with those in other studies (45 51%) [10, 11]. In addition, the validated model must be fit for utilization in situations of clinical decision making with respect to operative indications, and most cases of malignancy involved papillary carcinoma, with fewer cases of other subtypes of thyroid carcinoma included. Second, because of the limited numbers of cases included, some ultrasound features, such as cystic and partly interrupted rim calcification, that showed no significant difference between malignant and benign nodules were regarded as suspicious invalid redundant features and then were pruned from model construction. The significance of including these ultrasound features should be validated in future comprehensive studies. Third, we retrospectively reviewed still images specifically selected by an investigator, rather than ultrasound images collected in real time. Further studies are needed to evaluate the validity and interobserver consistency for the classifier models based on machine learning algorithms. We have already started some preliminary work on creating a visual interface builder. By inputting the ultrasound features given by an experienced radiologist, a malignancy risk estimation system for thyroid nodule based on the developed classifier model will provide a real-time calculation of the probability for malignancy, which will play a valuable role for management decision in clinical practice. Conclusion In the current study, we have developed different machine learning algorithms for use in the differential diagnosis of suspicious thyroid nodules. Our results showed that the machine AJR:207, October
6 Wu et al. learning algorithms, using input from an experienced radiologist, performed better than an inexperienced radiologist but not as well as the experienced radiologist whose data were used to create the algorithms. In addition, a comparative study of the different models showed that the RBF-NN outperformed the other machine learning algorithms. References 1. Cooper DS, Doherty GM, Haugen BR, et al. Revised American Thyroid Association management guidelines for patients with thyroid nodules and differentiated thyroid cancer: the American Thyroid Association (ATA) guidelines taskforce on thyroid nodules and differentiated thyroid cancer. Thyroid 2009; 19: Frates MC, Benson CB, Charboneau JW, et al. Management of thyroid nodules detected at US: Society of Radiologists in Ultrasound Consensus Conference Statement 1. Radiology 2005; 237: Papini E, Guglielmi R, Bianchini A, et al. Risk of malignancy in nonpalpable thyroid nodules: predictive value of ultrasound and color-doppler features. J Clin Endocrinol Metab 2002; 87: Nam-Goong IS, Kim HY, Gong G, et al. Ultrasonography-guided fine-needle aspiration of thyroid incidentaloma: correlation with pathological findings. Clin Endocrinol (Oxf) 2004; 60: Kim EK, Park CS, Chung WY, et al. New sonographic criteria for recommending fine-needle aspiration biopsy of nonpalpable solid nodules of the thyroid. AJR 2002; 178: Moon WJ, Baek JH, Jung SL, et al.; Korean Society of Thyroid Radiology; Korean Society of Radiology. Ultrasonography and the ultrasound-based management of thyroid nodules: consensus statement and recommendations. Korean J Radiol 2011; 12: Seo JY, Kim EK, Baek JH, Shin JH, Han KH, Kwak JY. Can ultrasound be as a surrogate marker for diagnosing a papillary thyroid cancer? Comparison with BRAF mutation analysis. Yonsei Med J 2014; 55: Lim KJ, Choi CS, Yoon DY, et al. Computer-aided diagnosis for the differentiation of malignant from benign thyroid nodules on ultrasonography. Acad Radiol 2008; 15: Chen SJ, Chang CY, Chang KY, et al. Classification of the thyroid nodules based on characteristic sonographic textural feature and correlated histopathology using hierarchical support vector machines. Ultrasound Med Biol 2010; 36: Liu YI, Kamaya A, Desser TS, Rubin DL. A Bayesian network for differentiating benign from malignant thyroid nodules using sonographic and demographic features. AJR 2011; 196:[web] W598 W Stojadinovic A, Peoples GE, Libutti SK, et al. Development of a clinical decision model for thyroid nodules. BMC Surg 2009; 9: Chinese Society of Endocrinology. Guidelines taskforce on thyroid nodules and differentiated thyroid cancer. Chin J Endocrinol Metab 2012; 28: Park JP, Roh JL, Lee JH, et al. Risk factors for central neck lymph node metastasis of clinically noninvasive, node-negative papillary thyroid microcarcinoma. Am J Surg 2014; 208: Nam SY, Shin JH, Han BK, et al. Preoperative ultrasonographic features of papillary thyroid carcinoma predict biological behavior. J Clin Endocrinol Metab 2013; 98: Sohn YM, Kwak JY, Kim EK, Moon HJ, Kim SJ, Kim MJ. Diagnostic approach for evaluation of lymph node metastasis from thyroid cancer using ultrasound and fine-needle aspiration biopsy. AJR 2010; 194: Lee YH, Kim DW, In HS, et al. Differentiation between benign and malignant solid thyroid nodules using an US classification system. Korean J Radiol 2011; 12: Horvath E, Majlis S, Rossi R, et al. An ultrasonogram reporting system for thyroid nodules stratifying cancer risk for clinical management. J Clin Endocrinol Metab 2009; 94: Andrioli M, Carzaniga C, Persani L. Standardized ultrasound report for thyroid nodules: the endocrinologist s viewpoint. Eur Thyroid J 2013; 2: Chan BK, Desser TS, McDougall IR, Weigel RJ, Jeffrey RB Jr. Common and uncommon sonographic features of papillary thyroid carcinoma. J Ultrasound Med 2003; 22: Cappelli C, Castellano M, Pirola I, et al. The predictive value of ultrasound findings in the management of thyroid nodules. QJM 2007; 100: Moon WJ, Jung SL, Lee JH, et al. Benign and malignant thyroid nodules: US differentiation multicenter retrospective study. Radiology 2008; 247: Li LN, Ouyang JH, Chen HL, Liu DY. A computer aided diagnosis system for thyroid disease using extreme learning machine. J Med Syst 2012; 36: Gopinath B, Shanthi N. Computer-aided diagnosis system for classifying benign and malignant thyroid nodules in multi-stained FNAB cytological images. Australas Phys Eng Sci Med 2013; 36: Jajroudi M, Baniasadi T, Kamkar L, Arbabi F, Sanei M, Ahmadzade M. Prediction of survival in thyroid cancer using data mining technique. Technol Cancer Res Treat 2014; 13: Tsantis S, Cavouras D, Kalatzis I, Piliouras N, Dimitropoulos N, Nikiforidis G. Development of a support vector machine-based image analysis system for assessing the thyroid nodule malignancy risk on ultrasound. Ultrasound Med Biol 2005; 31: Domingos P, Pazzani M. On the optimality of the simple Bayesian classifier under zero-one loss. Mach Learn 1997; 29: Hu YH, Hwang JN. Handbook of neural networks signal processing. New York, NY: CRC Press, 2001: Unkelbach J, Sun Y, Schmidhuber J. An EM based training algorithm for recurrent neural networks. In: Alippi C, Polycarpou M, Panayiotou C, Ellinas G, eds. ICANN 2009: 19th International Conference on Artificial Neural Networks. Limassol, Cyprus: European Neural Network Society, 2009: Tsihrintzis GA, Jain LC, eds. Multimedia services in intelligent environments: advanced tools and methodologies. Berlin, Germany: Springer, Science & Business Media, 2008: Park JY, Lee HJ, Jang HW, et al. A proposal for a thyroid imaging reporting and data system for ultrasound features of thyroid carcinoma. Thyroid 2009; 19: Kwak JY, Han KH, Yoon JH, et al. Thyroid imaging reporting and data system for US features of nodules: a step in establishing better stratification of cancer risk. Radiology 2011; 260: AJR:207, October 2016
Sonographic Features of Thyroid Nodules & Guidelines for Management
Sonographic Features of Thyroid Nodules & Guidelines for Management Mark A. Lupo, MD, FACE, ECNU Thyroid & Endocrine Center of Florida Assistant Clinical Professor of Medicine Florida State University,
More informationThyroid Nodules: US Risk Stratification and FNA Guidelines
Thyroid Nodules: US Risk Stratification and FNA Guidelines Mark A. Lupo, MD, FACE, ECNU Thyroid & Endocrine Center of Florida Assistant Clinical Professor of Medicine Florida State University, College
More informationThyroid Nodules: US Risk Stratification. Alex Tessnow, MD, FACE, ECNU University of Texas Southwestern Associate Professor of Medicine Dallas, Texas
Thyroid Nodules: US Risk Stratification Alex Tessnow, MD, FACE, ECNU University of Texas Southwestern Associate Professor of Medicine Dallas, Texas Which of the following is true? A. All echogenic foci
More informationSonographic Differentiation of Thyroid Nodules With Eggshell Calcifications
Article Sonographic Differentiation of Thyroid Nodules With Eggshell Calcifications Byung Moon Kim, MD, Min Jung Kim, MD, Eun-Kyung Kim, MD, Jin Young Kwak, MD, Soon Won Hong, MD, Eun Ju Son, MD, Ki Hwang
More informationSonographic differentiation of benign and malignant thyroid nodules: Prospective study
Sonographic differentiation of benign and malignant thyroid nodules: Prospective study Poster No.: C-1720 Congress: ECR 2010 Type: Scientific Exhibit Topic: Head and Neck Authors: D. W. Kim, Y. H. Lee;
More informationThyroid Nodule Risk Stratification and FNA Guidelines
Thyroid Nodule Risk Stratification and FNA Guidelines Mark A. Lupo, MD, FACE, ECNU Thyroid & Endocrine Center of Florida Assistant Clinical Professor of Medicine Florida State University, College of Medicine
More informationKorean Thyroid Imaging Reporting and Data System features of follicular thyroid adenoma and carcinoma: a single-center study
Korean Thyroid Imaging Reporting and Data System features of follicular thyroid adenoma and carcinoma: a single-center study Jung Won Park 1, Dong Wook Kim 1, Donghyun Kim 1, Jin Wook Baek 1, Yoo Jin Lee
More informationSu-kyoung Jeh, MD 1 So Lyung Jung, MD 2 Bum Soo Kim, MD 2 Yoen Soo Lee, MD 3
Evaluating the Degree of Conformity of Papillary Carcinoma and Follicular Carcinoma to the Reported Ultrasonographic Findings of Malignant Thyroid Tumor Su-kyoung Jeh, MD 1 So Lyung Jung, MD 2 Bum Soo
More informationRepeat Ultrasound-Guided Fine-Needle Aspiration for Thyroid Nodules 10 mm or Larger Can Be Performed 10.7 Months After Initial Nondiagnostic Results
Neuroradiology/Head and Neck Imaging Original Research Moon et al. Repeat US-Guided FNA of Thyroid Nodules After Nondiagnostic Results Neuroradiology/Head and Neck Imaging Original Research Hee Jung Moon
More informationThe Thyroid Imaging Reporting and Data System (TIRADS) for ultrasound of the thyroid : a pratical approach
The Thyroid Imaging Reporting and Data System (TIRADS) for ultrasound of the thyroid : a pratical approach Poster No.: C-2425 Congress: ECR 2015 Type: Educational Exhibit Authors: M. Ben Lassoued, B. Souissi,
More informationIndex terms: Thyroid Ultrasonography Pathology Cancer. DOI: /kjr
Histopathologic Findings Related to the Indeterminate or Inadequate Results of Fine-Needle Aspiration Biopsy and Correlation with Ultrasonographic Findings in Papillary Thyroid Carcinomas So Lyung Jung,
More informationPractical Approach to Thyroid Nodules:Ultrasound Criteria for Performing FNA Revisited
Practical Approach to Thyroid Nodules:Ultrasound Criteria for Performing FNA Revisited Poster No.: C-0100 Congress: ECR 2013 Type: Educational Exhibit Authors: S. Kuzmich, S. Sritharan, S. MUKUNDHAN, M.
More informationEndocrinology and Metabolic Disorder Unit Regina Apostolorum Hospital
Enrico Papini Endocrinology and Metabolic Disorder Unit Regina Apostolorum Hospital Albano Laziale, Italy The Following Faculty have provide no information regarding significant relationship with commercial
More informationEuropean Journal of Radiology
European Journal of Radiology 82 (2013) 321 326 Contents lists available at SciVerse ScienceDirect European Journal of Radiology jo ur n al hom epage: www.elsevier.com/locate/ejrad Ultrasonographic criteria
More informationPrincipal Site Investigator ENHANCE (Evaluation of Thyroid FNA Genomic Signature) study: An IRB approved study with funding to Rochester Regional
October 20 th 2018 Principal Site Investigator ENHANCE (Evaluation of Thyroid FNA Genomic Signature) study: An IRB approved study with funding to Rochester Regional Health from Veracyte Review ultrasound
More informationImaging-cytology correlation of thyroid nodules with initially benign cytology
Imaging-cytology correlation of thyroid nodules with initially benign cytology Poster No.: C-1815 Congress: ECR 2013 Type: Scientific Exhibit Authors: S. H. Hwang, E.-K. Kim, J. Y. Kwak; Seoul/KR Keywords:
More informationTHYROID NODULES: THE ROLE OF ULTRASOUND
THYROID NODULES: THE ROLE OF ULTRASOUND NOVEMBER 2017 DR. DEAN DURANT DEFINITION Thyroid nodule: Focal area within the thyroid gland with echogenicity different from surrounding parenchyma. THYROID NODULES
More informationThe Thyroid Nodule: From the Ultrasound Image to the Anatomopathological Diagnosis
The Thyroid Nodule: From the Ultrasound Image to the Anatomopathological Diagnosis Poster No.: C-2229 Congress: ECR 2014 Type: Educational Exhibit Authors: T. González de la Huebra Labrador, A. Herrero
More informationBRAF Mutation Analysis and Sonography as Adjuncts to Fine- Needle Aspiration Cytology of Papillary Thyroid Carcinoma: Their Relationships and Roles
Neuroradiology/Head and Neck Imaging Original Research Moon et al. BRAF Analysis and Sonography to Diagnose PTC Neuroradiology/Head and Neck Imaging Original Research Won-Jin Moon 1 Nami Choi 1 Jin Woo
More informationTaller-Than-Wide Sign of Thyroid Malignancy: Comparison Between Ultrasound and CT
Neuroradiology/Head and Neck Imaging Original Research Yoon et al. Taller-Than-Wide Sign of Thyroid Malignancy Neuroradiology/Head and Neck Imaging Original Research Soo Jeong Yoon 1 Dae Young Yoon 1,2
More informationORIGINAL ARTICLE. 304 Ultrasonography 34(4), October 2015 e-ultrasonography.org
Differentiation of benign and malignant thyroid nodules based on the proportion of sponge-like areas on ultrasonography: imaging-pathologic correlation Jee Young Kim 1, So Lyung Jung 2, Mee Kyung Kim 3,
More informationThe Comparison of Scintigraphic and Ultrasonographic Evaluation Criteria of Thyroid Nodules with Histopathologic Findings
Research Article The Comparison of Scintigraphic and Ultrasonographic Evaluation Criteria of Thyroid Nodules with Histopathologic Findings Seracettin Eğin * Department of General Surgery, University of
More informationISSN X (Print) Research Article. *Corresponding author Dr Kumud Julka
Scholars Journal of Applied Medical Sciences (SJAMS) Sch. J. App. Med. Sci., 2015; 3(2A):568-573 Scholars Academic and Scientific Publisher (An International Publisher for Academic and Scientific Resources)
More informationUS-FNA is an easy-to-use and accurate tool for evaluating
Published September 15, 2011 as 10.3174/ajnr.A2686 ORIGINAL RESEARCH D.W. Kim E.J. Lee S.J. Jung J.H. Ryu Y.M. Kim Role of Sonographic Diagnosis in Managing Bethesda Class III Nodules BACKGROUND AND PURPOSE:
More informationSonographic Features of Benign Thyroid Nodules
Article Sonographic Features of Benign Thyroid Nodules Interobserver Reliability and Overlap With Malignancy Jeffrey R. Wienke, MD, Wui K. Chong, MD, Julia R. Fielding, MD, Kelly H. Zou, PhD, Carol A.
More informationIndications for Fine Needle Aspiration in Thyroid Nodules
Review Article Endocrinol Metab 2013;28:81-85 http://dx.doi.org/10.3803/enm.2013.28.2.81 pissn 2093-596X eissn 2093-5978 Indications for Fine Needle Aspiration in Thyroid Nodules Jin Young Kwak Department
More informationWarinthorn Phuttharak*, Charoonsak Somboonporn, Gatenapa Hongdomnern
Colour Doppler Ultrasonography in the Diagnosis of Malignancy in Thyroid Nodules RESEARCH COMMUNICATION Diagnostic Performance of Gray-scale versus Combined Grayscale with Colour Doppler Ultrasonography
More informationA Bayesian Network for Differentiating Benign From Malignant Thyroid Nodules Using Sonographic and Demographic Features
Medical Physics and Informatics Original Research Liu et al. Bayesian Network for Diagnosing Thyroid Nodules Medical Physics and Informatics Original Research A Bayesian Network for Differentiating Benign
More informationDifferentiation of Thyroid Nodules With Macrocalcifications
CME Article Differentiation of Thyroid Nodules With Macrocalcifications Role of Suspicious Sonographic Findings Min Jung Kim, MD, Eun-Kyung Kim, MD, Jin Young Kwak, MD, Cheong Soo Park, MD, Woong Youn
More informationBiopsy of Thyroid Nodules: Comparison of Three Sets of Guidelines
Neuroradiology/Head and Neck Imaging Original Research Ahn et al. Biopsy of Thyroid Nodules Neuroradiology/Head and Neck Imaging Original Research FOCUS ON: Sung Soo Ahn 1 Eun-Kyung Kim 1 Dae Ryong Kang
More informationInterpreting the Thyroid Ultrasound Report
Interpreting the Thyroid Ultrasound Report Michael Neuman, MD Radiology Specialists of the Northwest February 2, 2018 Goals Review indications for thyroid ultrasound Review the role of ultrasound in evaluation
More informationCase-based discussion:
Case-based discussion: Pailin Kongmebhol, M.D. Department of Radiology Faculty of Medicine Chiang Mai University There are many guidelines for managing thyroid nodules Two important guidelines: 2015 American
More informationPapillary Thyroid Carcinoma Manifested Solely as Microcalcifications on Sonography
Sonography of Papillary Thyroid Carcinoma Head and Neck Imaging Clinical Observations Jin Young Kwak 1 Eun-Kyung Kim 1 Eun Ju Son 1 Min Jung Kim 1 Ki Keun Oh 1 Ji Young Kim 2 Kwang Il Kim 2 Kwak JY, Kim
More informationEvaluation of diagnostic efficacy of ultrasound scoring system to select thyroid nodules requiring fine needle aspiration biopsy
Int J Clin Exp Med 2013;6(8):641-648 www.ijcem.com /ISSN:1940-5901/IJCEM1304014 Original Article Evaluation of diagnostic efficacy of ultrasound scoring system to select thyroid nodules requiring fine
More informationPredicting the Size of Benign Thyroid Nodules and Analysis of Associated Factors That Affect Nodule Size
Original Article www.cmj.ac.kr Predicting the Size of Benign Thyroid Nodules and Analysis of Associated Factors That Affect Nodule Size Seok Ho Seo, Tae Hyun Kim*, Soon Ho Kim, Seung Hyun Lee, Jong Taek
More informationApproach to Thyroid Nodules
Approach to Thyroid Nodules Alice Y.Y. Cheng, MD, FRCPC Twitter: @AliceYYCheng Copyright 2017 by Sea Courses Inc. All rights reserved. No part of this document may be reproduced, copied, stored, or transmitted
More informationEvaluation of thyroid nodules: prediction and selection of malignant nodules for FNA (cytology)
Evaluation of thyroid nodules: prediction and selection of malignant nodules for FNA (cytology) Poster No.: C-0221 Congress: ECR 2014 Type: Authors: Keywords: DOI: Scientific Exhibit E. Papadaki, I. Tritou,
More informationContrast-enhanced ultrasound of solitary thyroid nodules - qualitative and quantitative evaluation: initial results
Contrast-enhanced ultrasound of solitary thyroid nodules - qualitative and quantitative evaluation: initial results Poster No.: C-2436 Congress: ECR 2015 Type: Authors: Keywords: DOI: Scientific Exhibit
More informationTHI-RADS. US differentiation of thyroid lesions.
THI-RADS. US differentiation of thyroid lesions. Poster No.: C-0864 Congress: ECR 2015 Type: Scientific Exhibit Authors: A. N. Sencha, Y. Patrunov, M. S. Mogutov, E. Penyaeva, A. 1 1 1 2 1 1 1 2 Gruzdev,
More informationTHI-RADS. US differentiation of thyroid lesions.
THI-RADS. US differentiation of thyroid lesions. Poster No.: C-0864 Congress: ECR 2015 Type: Scientific Exhibit Authors: A. N. Sencha, Y. Patrunov, M. S. Mogutov, E. Penyaeva, A. 1 1 1 2 1 1 1 2 Gruzdev,
More informationSonographic Patterns of Benign Thyroid Nodules: Verification at Our Institution
Neuroradiology/Head and Neck Imaging Original Research Virmani and Hammond Sonographic Patterns of enign Thyroid Nodules Neuroradiology/Head and Neck Imaging Original Research Vivek Virmani 1 Ian Hammond
More informationUltrasound Evaluation of Thyroid Nodules. October 2016
Ultrasound Evaluation of Thyroid Nodules October 2016 Thyroid Nodules Primary goal is to determine if a nodule is malignant and needs surgery, or is benign and does not need surgery. Concerning Clinical
More informationPositive predictive value and inter-observer agreement of TIRADS for ultrasound features of thyroid nodules
Positive predictive value and inter-observer agreement of TIRADS for ultrasound features of thyroid nodules Poster No.: C-0594 Congress: ECR 2014 Type: Scientific Exhibit Authors: C. Anuradha, K. Abhishek,
More informationCompliance of British Thyroid Ultrasound "U" Guidelines Are we all speaking the "Unified" Thyroid language?
Compliance of British Thyroid Ultrasound "U" Guidelines Are we all speaking the "Unified" Thyroid language? Poster No.: C-1158 Congress: ECR 2016 Type: Scientific Exhibit Authors: P. Gopalan, S. Singh,
More informationThyroid in a Nutshell Dublin Catherine Kirkpatrick Consultant Sonographer ULHT
Thyroid in a Nutshell Dublin 2017 Catherine Kirkpatrick Consultant Sonographer ULHT Acknowledgements Dr. Steve Colley Dr. Rhodri Evans Dr. Rhian Rhys Dr. Andrew McQueen Aims Anatomy & Physiology Incidence
More informationPre-operative Ultrasound of Lymph Nodes in Thyroid Cancer
Pre-operative Ultrasound of Lymph Nodes in Thyroid Cancer AACE - Advances in Medical and Surgical Management of Thyroid Cancer - 2018 Robert A. Levine, MD, FACE, ECNU Thyroid Center of New Hampshire Geisel
More informationRisk of Thyroid Cancer Based on Thyroid Ultrasound Imaging Characteristics
Risk of Thyroid Cancer Based on Thyroid Ultrasound Imaging Characteristics Diabetes Update and Advances in Endocrinology & Metabolism Vickie A Feldstein MD Rebecca Smith- Bindman MD Department of Radiology
More informationDong Wook Kim, MD 1 Auh Whan Park, MD 1 Eun Joo Lee, MD 1 Hye Jung Choo, MD 1 Sang Hyo Kim, MD 2 Sang Hyub Lee, MD 2 Jae Wook Eom, MD 3
Ultrasound-Guided Fine-Needle Aspiration Biopsy of Thyroid Nodules Smaller Than 5 mm in the Maximum Diameter: Assessment of Efficacy and Pathological Findings Dong Wook Kim, MD 1 Auh Whan Park, MD 1 Eun
More informationEndocrine University, 2016 AACE-ACE-MAYO CLINIC
Endocrine University, 2016 AACE-ACE-MAYO CLINIC Dev Abraham MD, MRCP (UK), ECNU Professor of Medicine (clinical), Division of Endocrinology Adjunct Professor of Surgery and Pathology Medical Director,
More informationof Thyroid Lesions Comet Tail Crystals
2 Ultrasound Features of Thyroid Lesions There are many different features indicating a certain benign or malignant tumor type, but many of these are overlapping signs. Combining several features is considered
More informationIntroduction: Ultrasound guided Fine Needle Aspiration: When and how
International Course of Thyroid Ultrasonography and minimally invasive procedure 7-8 October 2016 University of Pisa, Italy Introduction: Ultrasound guided Fine Needle Aspiration: When and how Teresa Rago
More informationUltrasonographic Findings of Medullary Thyroid Carcinoma: a Comparison with Papillary Thyroid Carcinoma
Ultrasonographic Findings of Medullary Thyroid Carcinoma: a Comparison with Papillary Thyroid Carcinoma Sung-Hun Kim, MD 1 Bum-Soo Kim, MD 1 So-Lyung Jung, MD 1 Jung-Whee Lee, MD 1 Po-Sung Yang, MD 1 Bong-Joo
More informationRole of ultrasonography in recognition of malignant potential of thyroid nodules on the basis of their internal composition
Role of ultrasonography in recognition of malignant potential of thyroid nodules on the basis of their internal composition Nodular thyroid is a common clinical entity. All patients were evaluated by grey
More informationThyroid nodules, when to perform a fine needle aspiration
Thyroid nodules, when to perform a fine needle aspiration Poster No.: C-1828 Congress: ECR 2015 Type: Educational Exhibit Authors: A. I. Fernández Martín, E. Pertusa Santos, E. Dominguez 1 1 1 2 1 Franjo,
More informationDownloaded from by John Hanna on 11/09/15 from IP address Copyright ARRS. For personal use only; all rights reserved
Neuroradiology/Head and Neck Imaging Original Research Zhu et al. Ultrasound Versus Afirma Testing of FNA-Indeterminate Thyroid Nodules Neuroradiology/Head and Neck Imaging Original Research Qing-Li Zhu
More informationQuality Initiative Project assessing the impact of TIRADS on net number of thyroid biopsies and adherence of TIRADS-reporting by radiologists
Quality Initiative Project assessing the impact of TIRADS on net number of thyroid biopsies and adherence of TIRADS-reporting by radiologists Tetyana Maniuk BSc, Ania Kielar MD, FRCPC Joseph O Sullivan
More informationPapillary Thyroid Carcinoma With BRAF V600E Mutation: Sonographic Prediction
Neuroradiology/Head and Neck Imaging Original Research Hwang et al. Papillary Thyroid Carcinoma Neuroradiology/Head and Neck Imaging Original Research Jiyoung Hwang 1 Jung Hee Shin 1 Boo-Kyung Han 1 Eun
More informationThyroid Nodules with Macrocalcification: Sonographic Findings Predictive of Malignancy
Original Article http://dx.doi.org/10.3349/ymj.2014.55.2.339 pissn: 0513-5796, eissn: 1976-2437 Yonsei Med J 55(2):339-344, 2014 Thyroid Nodules with Macrocalcification: Sonographic Findings Predictive
More informationCMEArticle A method in the madness in ultrasound evaluation of thyroid nodules
Singapore Med J 2012; 53(11) : 766 CMEArticle A method in the madness in ultrasound evaluation of thyroid nodules Amogh Hegde 1, MD, FRCR, Anil Gopinathan 1, MD, FRCR, Rafidah Abu Bakar 2, MMedUS, BSc,
More informationUltrasound for Pre-operative Evaluation of Well Differentiated Thyroid Cancer
Ultrasound for Pre-operative Evaluation of Well Differentiated Thyroid Cancer Its Not Just About the Nodes AACE Advances in Medical and Surgical Management of Thyroid Cancer - 2017 Robert A. Levine, MD,
More informationAdina Alazraki, MD, FAAP Assistant Professor Radiology and Pediatrics Emory University and Children s Healthcare of Atlanta
Adina Alazraki, MD, FAAP Assistant Professor Radiology and Pediatrics Emory University and Children s Healthcare of Atlanta Review recently published pediatric guidelines for management of thyroid nodules
More informationThyroid Ultrasound Physics and Doppler
Thyroid Ultrasound Physics and Doppler Advanced AACE-ACE US training course 2017 Dev Abraham MD, MRCP(UK), ECNU, FACE Professor of Medicine, University of Utah No Disclosures Natural Ability to see with
More informationThyroid nodules with minimal cystic changes have a low risk of malignancy
Thyroid nodules with minimal cystic changes have a low risk of malignancy Dong Gyu Na 1, Ji-hoon Kim 2, Dae Sik Kim 1,3, Soo Jin Kim 1,4 1 Department of Radiology, Human Medical Imaging and Intervention
More informationColumnar Cell Variant of Papillary Thyroid Carcinoma: Ultrasonographic and Clinical Differentiation between the Indolent and Aggressive Types
Brief Communication Thyroid https://doi.org/10.3348/kjr.2018.19.5.1000 pissn 1229-6929 eissn 2005-8330 Korean J Radiol 2018;19(5):1000-1005 Columnar Cell Variant of Papillary Thyroid Carcinoma: Ultrasonographic
More informationRetrospective Evaluation of Ultrasound Features of Thyroid Nodules to Assess Malignancy Risk: A Step Toward TIRADS
Special Articles Original Research Zayadeen et al. Ultrasound Features of Thyroid Nodules Special Articles Original Research JOURNAL CLUB Adnan R. Zayadeen 1 Monzer Abu-Yousef 2 Kevin Berbaum 2 Zayadeen
More informationMedicine. Observational Study. 1. Introduction. 2. Materials and methods. 3. Results OPEN
Observational Study Medicine Ultrasonographic features and clinicopathologic characteristics of macrofollicular variant papillary thyroid carcinoma Yong Sang Lee, MD a,c, Soo Young Kim, MD a,c, Soon Won
More informationHigh thyroglobulin (Tg) in a lymph node indicates metastatic
ORIGINAL RESEARCH HEAD & NECK Optimized Cutoff Value and Indication for Washout Thyroglobulin Level According to Ultrasound Findings in Patients with Well-Differentiated Thyroid Cancer J.Y. Jung, J.H.
More informationUltrasonography of the Neck as an Adjunct to FNA. Nicole Massoll M.D.
Ultrasonography of the Neck as an Adjunct to FNA Nicole Massoll M.D. Basic Features of Head and Neck Ultrasound and Anatomy Nicole Massoll M.D. University of Arkansas for Medical Sciences, Little Rock
More informationNeuroradiology/Head and Neck Imaging Original Research
Neuroradiology/Head and Neck Imaging Original Research Hobbs et al. FNA of Thyroid Nodules Neuroradiology/Head and Neck Imaging Original Research Hasan A. Hobbs 1 Manisha Bahl 1 Rendon C. Nelson 1,2 James
More informationImproving the Long Term Management of Benign Thyroid Nodules
25 th Annual Scientific AACE Clinical Congress Improving the Long Term Management of Benign Thyroid Nodules Stephanie L. Lee, MD, PhD Director, Thyroid Health Center Section of Endocrinology, Diabetes
More informationCompressibility of Thyroid Masses: A Sonographic Sign Differentiating Benign From Malignant Lesions?
Neuroradiology/Head and Neck Imaging Original Research Seo et al. Ultrasound of Thyroid Masses Neuroradiology/Head and Neck Imaging Original Research Young Lan Seo 1,2 Dae Young Yoon 1,2 Soo Jeong Yoon
More informationEchogenic Foci in Thyroid Nodules: Significance of Posterior Acoustic Artifacts
Neuroradiology/Head and Neck Imaging Original Research Malhi et al. Echogenic Foci in Thyroid Nodules Neuroradiology/Head and Neck Imaging Original Research Harshawn Malhi 1 Michael D. Beland 2 Steven
More informationCan Color Doppler Sonography Aid in the Prediction of Malignancy of Thyroid Nodules?
Article Can Color Doppler Sonography Aid in the Prediction of Malignancy of Thyroid Nodules? Mary C. Frates, MD, Carol B. Benson, MD, Peter M. Doubilet, MD, PhD, Edmund S. Cibas, MD, Ellen Marqusee, MD
More informationCharacteristics of thyroid nodules in infant with congenital hypothyroidism. Seoul, Korea
Characteristics of thyroid nodules in infant with congenital hypothyroidism Seo Young Youn, MD 1, Jeong Ho Lee, MD 1, Yun-Woo Chang, MD 2, Dong Hwan Lee, MD 1. Department of 1 Pediatrics, and 2 Radiology,
More informationThyroid Nodules: What to do next?
Thyroid Nodules: What to do next? Ally P. H. Prebtani Professor of Medicine Internal Medicine, Endocrinology & Metabolism McMaster University Canada Copyright 2017 by Sea Courses Inc. All rights reserved.
More informationStudy of validity of ultrasonographic diagnosis in relation to Fine Needle Aspiration Cytology (FNAC) diagnosis
Original article: Study of validity of ultrasonographic diagnosis in relation to Fine Needle Aspiration Cytology (FNAC) diagnosis *Dr Rajvi Matalia, ** Dr Y.P.Sachdev, ***Dr D.S.Kulkarni *Junior Resident,
More informationRadiologic Findings of Mucocele-like Tumors of the breast: Can we differentiate pure benign from associated with high risk lesions?
Radiologic Findings of Mucocele-like Tumors of the breast: Can we differentiate pure benign from associated with high risk lesions? Poster No.: C-0332 Congress: ECR 2014 Type: Educational Exhibit Authors:
More informationMixed Echoic Thyroid Nodules on Ultrasound: Approach to Management
Original Article http://dx.doi.org/10.3349/ymj.2012.53.4.812 pissn: 0513-5796, eissn: 1976-2437 Yonsei Med J 53(4):812-819, 2012 Mixed Echoic Thyroid Nodules on Ultrasound: Approach to Management Yu-Mee
More informationQuantification of solid hypo-echoic thyroid nodule enhancement with contrast-enhanced ultrasound
Original Article on Translational Imaging in Cancer Patient Care Quantification of solid hypo-echoic thyroid nodule enhancement with contrast-enhanced ultrasound Xuehong Diao, Jia Zhan, Lin Chen, Yue Chen,
More informationThyroid nodule sonography: assessment for risk of malignancy
Thyroid nodule sonography: assessment for risk of malignancy Fine-needle aspiration (FNA) is the most reliable diagnostic tool for diagnosing thyroid cancer and should be performed on nodules considered
More informationELIZABETH CEDARS DR. KOREY HOOD Available September 29
ELIZABETH CEDARS DR. KOREY HOOD Available September 29 Title and Investigators Optimizing Surgical Management of Thyroid Cancer: Using Surgeon-performed Ultrasound to Predict Extrathyroidal Extension of
More informationThe radiological spectrum of thyroid malignancy
The radiological spectrum of thyroid malignancy Poster No.: C-2575 Congress: ECR 2012 Type: Educational Exhibit Authors: K. Cortis, W. Scicluna, A. Mizzi ; Rabat/MT, Birkirkara/MT Keywords: Ultrasound-Colour
More informationReliability of the ultrasound classification system of thyroid nodules in predicting malignancy
ORIGINAL ARTICLE Reliability of the ultrasound classification system of thyroid nodules in predicting malignancy Farihah Abd Ghani, MB BCh BAO (NUI) 1, Nurismah Md Isa, MPath 2, Husyairi Harunarashid,
More informationShearWave elastography in lymph nodes
ShearWave elastography in lymph nodes Poster No.: B-0158 Congress: ECR 2015 Type: Authors: Keywords: DOI: Scientific Paper F. Houari, O. Lucidarme, J. Gabarre, F. Charlotte, C. Pellot- Barakat, M. Lefort,
More informationRole of Ultrasonography to Differentiate Benign and Malignant Thyroid Nodules in Correlation with Fine-needle Aspiration Cytology
Original Article Print ISSN: 2321-6379 Online ISSN: 2321-595X DOI: 10.17354/ijss/2016/434 Role of Ultrasonography to Differentiate Benign and Malignant Thyroid Nodules in Correlation with Fine-needle Aspiration
More informationAACE/ACE Advanced Endocrine Neck Ultrasound Training Course 2016
AACE/ACE Advanced Endocrine Neck Ultrasound Training Course 2016 This 9mm left inferior nodule should remind us all why we re here! There is no absolute number of images required for documentation
More informationCLINICAL GUIDELINES. Introductory notes:
CLINICAL GUIDELINES Thyroid Ultrasound Reporting Guideline Recommendations Thomas Gilbert, M.D., M.P.P., Robert Kanterman, M.D., Erik Rockswold, MHA Updated June, 2017 Introductory notes: Thyroid nodules
More informationDiffuse Sclerosing Variant of Papillary Thyroid Carcinoma
PITORL ESSY iffuse Sclerosing Variant of Papillary Thyroid arcinoma Sonography and Specimen Radiography Hyun Kyung Jung, M, Soon Won Hong, M, Eun-Kyung Kim, M, Jung Hyun Yoon, M, Jin Young Kwak, M The
More informationThyroid Nodules and Ultrasound. Patrick Vos Department of Radiology St. Paul s Hospital Vancouver, BC
Thyroid Nodules and Ultrasound Patrick Vos Department of Radiology St. Paul s Hospital Vancouver, BC No Financial Disclosures Patrick Vos Department of Radiology St. Paul s Hospital Vancouver, BC Acknowledgements
More informationGray Scale and Colour Doppler Sonography in the Evaluation of Follicular Neoplasms of Thyroid
DOI: 10.7860/IJARS/2018/24979:2393 Radiology Section Original Article Gray Scale and Colour Doppler Sonography in the Evaluation of Follicular Neoplasms of Thyroid Pradeep Hagalahalli Nagarajegowda, VISHWANATH
More informationIntroduction ORIGINAL ARTICLE. Sang Yu Nam 1,2, Jung Hee Shin 1, Eun Young Ko 1, Soo Yeon Hahn 1
A comparison of lymphocytic thyroiditis with papillary thyroid carcinoma showing suspicious ultrasonographic findings in a background of heterogeneous parenchyma Sang Yu Nam 1,2, Jung Hee Shin 1, Eun Young
More informationThyroid Nodule Management
Thyroid Nodule Management Shane O. LeBeau, MD Clinical Associate Professor of Medicine Clinical Lead, Endocrine Thyroid Unit Division of Endocrinology, Diabetes and Metabolism University of Pittsburgh
More informationContents. Basic Ultrasound Principles and Terminology. Ultrasound Nodule Characteristics
Contents Basic Ultrasound Principles and Terminology Basic Ultrasound Principles... 1 Ultrasound System... 2 Linear Transducer for Superficial Images and Ultrasound-Guided FNA... 3 Scanning Planes... 4
More informationArticleInfo. Spring School of Thyroidology organized by the Polish Thyroid Association 2014: abstracts of invited lectures
Ultrasound and cytological diagnostics of thyroid - its proper application in case of coexisting disturbing clinical signs and symptoms, suggestive of active proliferative lesion Andrzej Lewiński, Aff1
More informationOh, I get it, the TSH goes up and down
Evaluation and Management of the Thyroid Nodule Oh, I get it, the TSH goes up and down UCSF Head and Neck Conference October 24, 2008 Peter A. Singer, M.D. Professor and Chief Clinical Endocrinology University
More informationThyroid and Parathyroid Ultrasound Protocol
Thyroid and Parathyroid Ultrasound Protocol Reviewed By: Anna Ellermeier, MD Last Reviewed: December 2017 Contact: (866) 761-4200, Option 1 **NOTE for all examinations: 1. If documenting possible flow
More informationThyroid US. Background: Thyroid/Neck US. Use of Office Ultrasound in the Thyroid Surgery Practice
2010 UCSF Head and Neck Endocrine Surgery Course Use of Office Ultrasound in the Thyroid Surgery Practice Lisa A. Orloff, MD FACS Dept of Otolaryngology-Head and Neck Surgery University of California,
More informationReliability of the ultrasound classification system of thyroid nodules in predicting malignancy
ORIGINAL ARTICLE Reliability of the ultrasound classification system of thyroid nodules in predicting malignancy Farihah Abd Ghani, MB BCh BAO 1, Nurismah Md Isa, Mpath 3, Husyairi Harunarashid, MClinEpid
More informationObjectives. 1)To recall thyroid nodule ultrasound characteristics that increase the risk of malignancy
Evaluation and Management of Thyroid Nodules in Primary Care Chris Sadler, MA, PA C, CDE, DFAAPA Medical Science Outcomes Liaison Intarcia Diabetes and Endocrine Associates La Jolla, CA Past President
More information