Partially cystic thyroid cancer on conventional and elastographic ultrasound: a retrospective study and a machine learning—assisted system.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhao H
PROVIDER: S-EPMC7210215 | biostudies-literature | 2020 Apr
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background and purposeThere is no prospective study related to the sonographic differentiation of malignant PCTN from benign PCTN. This prospective study was designed to evaluate differentiation of benign from malignant PCTNs with thyroid sonography.Materials and methodsTwo hundred thirteen PCTNs in 196 patients who had consecutively undergone prospective sonographic diagnosis and US-FNAB were included. The PCTNs were evaluated according to their configuration and the presence of calcification, a free margin, vascularity, spongiform appearance or daughter cysts, colloid crystal, nodule shape, and echogenicity. Each PCTN was prospectively classified into 1 of 4 diagnostic categories: benign features, probably benign, suspicious for malignancy, and malignant features. We calculated the diagnostic efficacy of a prospective sonographic diagnosis for PCTNs by comparing it with cytopathologic results.ResultsAmong the 213 PCTNs, 53 underwent thyroid surgery. The sonographic classifications for 213 PCTNs included benign features (n = 182), probably benign (n = 19), suspicious for malignancy (n = 7), and malignant features (n = 5). When nonsurgical PCTNs (n = 160) with benign sonographic findings and benign cytology were considered negative, the sensitivity, specificity, PPV, NPV, and accuracy of the prospective diagnosis of PCTNs were 72.7%, 98.0%, 66.7%, 98.5%, and 96.7%, respectively. On the basis of individual analysis, eccentric configuration with an acute angle and microcalcifications were significantly associated with malignancy, but a concentric configuration, a smooth free margin, peripheral vascularity, spongiform appearance or daughter cysts, and intranodular colloid crystals showed a statistically significant association with benignity.ConclusionsOur prospective sonographic diagnoses of PCTNs, especially those >2 cm, were highly reliable.
| S-EPMC7964042 | biostudies-literature
Project description:MotivationIn a predictive modeling setting, if sufficient details of the system behavior are known, one can build and use a simulation for making predictions. When sufficient system details are not known, one typically turns to machine learning, which builds a black-box model of the system using a large dataset of input sample features and outputs. We consider a setting which is between these two extremes: some details of the system mechanics are known but not enough for creating simulations that can be used to make high quality predictions. In this context we propose using approximate simulations to build a kernel for use in kernelized machine learning methods, such as support vector machines. The results of multiple simulations (under various uncertainty scenarios) are used to compute similarity measures between every pair of samples: sample pairs are given a high similarity score if they behave similarly under a wide range of simulation parameters. These similarity values, rather than the original high dimensional feature data, are used to build the kernel.ResultsWe demonstrate and explore the simulation-based kernel (SimKern) concept using four synthetic complex systems-three biologically inspired models and one network flow optimization model. We show that, when the number of training samples is small compared to the number of features, the SimKern approach dominates over no-prior-knowledge methods. This approach should be applicable in all disciplines where predictive models are sought and informative yet approximate simulations are available.Availability and implementationThe Python SimKern software, the demonstration models (in MATLAB, R), and the datasets are available at https://github.com/davidcraft/SimKern.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC6792064 | biostudies-literature
Project description:Advanced stroke treatment is time-dependent and, therefore, relies on recognition by call-takers at prehospital telehealth services to ensure fast hospitalisation. This study aims to develop and assess the potential of machine learning in improving prehospital stroke recognition during medical helpline calls. We used calls from 1 January 2015 to 31 December 2020 in Copenhagen to develop a machine learning-based classification pipeline. Calls from 2021 are used for testing. Calls are first transcribed using an automatic speech recognition model and then categorised as stroke or non-stroke using a text classification model. Call-takers achieve a sensitivity of 52.7% (95% confidence interval 49.2-56.4%) with a positive predictive value (PPV) of 17.1% (15.5-18.6%). The machine learning framework performs significantly better (p < 0.0001) with a sensitivity of 63.0% (62.0-64.1%) and a PPV of 24.9% (24.3-25.5%). Thus, a machine learning framework for recognising stroke in prehospital medical helpline calls may become a supportive tool for call-takers, aiding in early and accurate stroke recognition.
| S-EPMC10730829 | biostudies-literature
Project description:PURPOSE:This study was conducted to evaluate the diagnostic performance of machine learning in differentiating follicular adenoma from carcinoma using preoperative ultrasonography (US). METHODS:In this retrospective study, preoperative US images of 348 nodules from 340 patients were collected from two tertiary referral hospitals. Two experienced radiologists independently reviewed each image and categorized the nodules according to the 2015 American Thyroid Association guideline. Categorization of a nodule as highly suspicious was considered a positive diagnosis for malignancy. The nodules were manually segmented, and 96 radiomic features were extracted from each region of interest. Ten significant features were selected and used as final input variables in our in-house developed classifier models based on an artificial neural network (ANN) and support vector machine (SVM). The diagnostic performance of radiologists and both classifier models was calculated and compared. RESULTS:In total, 252 nodules from 245 patients were confirmed as follicular adenoma and 96 nodules from 95 patients were diagnosed as follicular carcinoma. As measures of diagnostic performance, the average sensitivity, specificity, and accuracy of the two experienced radiologists in discriminating follicular adenoma from carcinoma on preoperative US images were 24.0%, 84.0%, and 64.8%, respectively. The sensitivity, specificity, and accuracy of the ANN and SVM-based models were 32.3%, 90.1%, and 74.1% and 41.7%, 79.4%, and 69.0%, respectively. The kappa value of the two radiologists was 0.076, corresponding to slight agreement. CONCLUSION:Machine learning-based classifier models may aid in discriminating follicular adenoma from carcinoma using preoperative US.
| S-EPMC7315296 | biostudies-literature
Project description: Not available
| S-EPMC11250354 | biostudies-literature
Project description:ObjectiveThe aim of this study is to identify risk factors of intra-cystic hemorrhage in microwave ablation of mixed solid and cystic microwave ablation s, and to design a preoperative nomogram to predict the risk value of intraoperative bleeding with the goal of individualizing the surgical approach toward different types of cystic and solid thyroid nodules.MethodsA total of 241 patients with cystic-solid thyroid nodules who underwent ultrasound-guided percutaneous microwave ablation were retrospectively divided into a bleeding group and a non-bleeding group to compare the diameter, cystic proportion, cystic fluid nature, color Doppler flow imaging, Contrast-enhanced ultrasound (CEUS) findings, and operative methods. Based on univariate and multivariate analysis, the important risk factors of nodular intracapsular hemorrhage in the ablation procedure were projected to a nomogram for predicting the possibility of intraoperative hemorrhage in the thyroid cystic solid nodules.ResultsIntra-cystic hemorrhage was developed in 37 cases during the ablation of mixed thyroid nodules with a total incidence of 15% (37/241). Significant differences were found statistically between the two groups on the diameter of the lesions, CEUS findings, the cystic fluid ratio, and operative methods (P = 0.000, P = 0.001, P = 0.024, P = 0.002). The possibility of intraoperative nodular intracapsular hemorrhage was predicted by the model based on the risk factors with the accuracy of 81% and prediction consistency index (C-index) of 0.78.ConclusionA new and efficient prediction model was developed based on the identified risk factors for intracapsular hemorrhage during microwave ablation of mixed thyroid nodules, which will aid in the development of targeted surgical planning for different types of cystic thyroid nodules, thus reducing the risk of hemorrhage during ablation.
| S-EPMC10374254 | biostudies-literature
Project description:BackgroundThyroid nodular disease is a common disorder. Ultrasonography has emerged as a powerful tool for the diagnosis of thyroid disease owing to its high operational simplicity, non-invasiveness and reproducibility. This study aimed to systematically evaluate the value of ultrasound elastography and conventional ultrasound for the diagnosis of thyroid nodules.MethodsThe PubMed, EMBASE, Cochrane Library, China National Knowledge Infrastructure, Wanfang and VIP databases were searched systematically. RevMan 5.3 software was used to draw a risk bias map, and Stata 16.0 was used to plot a sensitivity and specificity forest map. A summary receiver operating characteristics (SROC) curve was plotted, and the area under the curve (AUC) was calculated. Meta-regression was used to explore the sources of heterogeneity.ResultsThe sensitivity of conventional ultrasonography for detecting thyroid nodules was 0.55 [95% confidence interval (CI): 0.45-0.65], the specificity was 0.90 (95% CI: 0.87-0.93), the positive likelihood ratio was 5.8 (95% CI: 3.8-8.9), the negative likelihood ratio was 0.49 (95% CI: 0.39-0.6), and the AUC was 0.86 (95% CI: 0.82-0.88). The sensitivity of ultrasonic elastography for detecting thyroid nodules was 0.67 (95% CI: 0.60-0.73), the specificity was 0.93 (95% CI: 0.90-0.95), the positive likelihood ratio was 9.1 (95% CI: 6.3-13.3), the negative likelihood ratio was 0.36 (95% CI: 0.29-0.44), and the AUC was 0.89 (95% CI: 0.86-0.91). The sensitivity of conventional ultrasound combined with ultrasonic elastography for detecting thyroid nodules was 0.88 (95% CI: 0.84-0.90), the specificity of the combined approach was 0.96 (95% CI: 0.93-0.98), the positive likelihood ratio was 23.3 (95% CI: 12.4-43.6), the negative likelihood ratio was 0.13 (95% CI: 0.10-0.17), and the AUC was 0.92 (95% CI: 0.90-0.94). Age, region, research type, conventional ultrasound evaluation criteria and elastography evaluation criteria had specific effects on sensitivity and specificity when detecting thyroid nodules.ConclusionsConventional ultrasound can be used as a routine examination technique for the differential diagnosis of benign and malignant thyroid nodules, while ultrasound elastography can improve the sensitivity and specificity of the diagnosis. The diagnostic value of conventional ultrasound combined with ultrasound elastography is higher than that of a single diagnostic method.
| S-EPMC10006152 | biostudies-literature
Project description:The emergence of deep-learning methods in different computer vision tasks has proved to offer increased detection, recognition or segmentation accuracy when large annotated image datasets are available. In the case of medical image processing and computer-aided diagnosis within ultrasound images, where the amount of available annotated data is smaller, a natural question arises: are deep-learning methods better than conventional machine-learning methods? How do the conventional machine-learning methods behave in comparison with deep-learning methods on the same dataset? Based on the study of various deep-learning architectures, a lightweight multi-resolution Convolutional Neural Network (CNN) architecture is proposed. It is suitable for differentiating, within ultrasound images, between the Hepatocellular Carcinoma (HCC), respectively the cirrhotic parenchyma (PAR) on which HCC had evolved. The proposed deep-learning model is compared with other CNN architectures that have been adapted by transfer learning for the ultrasound binary classification task, but also with conventional machine-learning (ML) solutions trained on textural features. The achieved results show that the deep-learning approach overcomes classical machine-learning solutions, by providing a higher classification performance.
| S-EPMC7309124 | biostudies-literature
Project description:Thyroid tumors, one of the common tumors in the endocrine system, while the discrimination between benign and malignant thyroid tumors remains insufficient. The aim of this study is to construct a diagnostic model of benign and malignant thyroid tumors, in order to provide an emerging auxiliary diagnostic method for patients with thyroid tumors. The patients were selected from the Chongqing General Hospital (Chongqing, China) from July 2020 to September 2021. And peripheral blood, BRAFV600E gene, and demographic indicators were selected, including sex, age, BRAFV600E gene, lymphocyte count (Lymph#), neutrophil count (Neu#), neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), red blood cell distribution width (RDW), platelets count (PLT), red blood cell distribution width-coefficient of variation (RDW-CV), alkaline phosphatase (ALP), and parathyroid hormone (PTH). First, feature selection was executed by univariate analysis combined with least absolute shrinkage and selection operator (LASSO) analysis. Afterward, we used machine learning algorithms to establish three types of models. The first model contains all predictors, the second model contains indicators after feature selection, and the third model contains patient peripheral blood indicators. The four machine learning algorithms include extreme gradient boosting (XGBoost), random forest (RF), light gradient boosting machine (LightGBM), and adaptive boosting (AdaBoost) which were used to build predictive models. A grid search algorithm was used to find the optimal parameters of the machine learning algorithms. A series of indicators, such as the area under the curve (AUC), were intended to determine the model performance. A total of 2,042 patients met the criteria and were enrolled in this study, and 12 variables were included. Sex, age, Lymph#, PLR, RDW, and BRAFV600E were identified as statistically significant indicators by univariate and LASSO analysis. Among the model we constructed, RF, XGBoost, LightGBM and AdaBoost with the AUC of 0.874 (95% CI, 0.841-0.906), 0.868 (95% CI, 0.834-0.901), 0.861 (95% CI, 0.826-0.895), and 0.837 (95% CI, 0.802-0.873) in the first model. With the AUC of 0.853 (95% CI, 0.818-0.888), 0.853 (95% CI, 0.818-0.889), 0.837 (95% CI, 0.800-0.873), and 0.832 (95% CI, 0.797-0.867) in the second model. With the AUC of 0.698 (95% CI, 0.651-0.745), 0.688 (95% CI, 0.639-0.736), 0.693 (95% CI, 0.645-0.741), and 0.666 (95% CI, 0.618-0.714) in the third model. Compared with the existing models, our study proposes a model incorporating novel biomarkers which could be a powerful and promising tool for predicting benign and malignant thyroid tumors.
| S-EPMC9515945 | biostudies-literature
Project description:Although the clinical activity score (CAS) is a validated scoring system for identifying disease activity of thyroid-associated orbitopathy (TAO), it may produce differing results depending on the evaluator, and an experienced ophthalmologist is required for accurate evaluation. In this study, we developed a machine learning (ML)-assisted system to mimic an expert's CAS assessment using digital facial images and evaluated its accuracy for predicting the CAS and diagnosing active TAO (CAS ≥ 3). An ML-assisted system was designed to assess five CAS components related to inflammatory signs (redness of the eyelids, redness of the conjunctiva, swelling of the eyelids, inflammation of the caruncle and/or plica, and conjunctival edema) in patients' facial images and to predict the CAS by considering two components of subjective symptoms (spontaneous retrobulbar pain and pain on gaze). To train and test the system, 3,060 cropped images from 1020 digital facial images of TAO patients were used. The reference CAS for each image was scored by three ophthalmologists, each with > 15 years of clinical experience. We repeated the experiments for 30 randomly split training and test sets at a ratio of 8:2. The sensitivity and specificity of the ML-assisted system for diagnosing active TAO were 72.7% and 83.2% in the test set constructed from the entire dataset. For the test set constructed from the dataset with consistent results for the three ophthalmologists, the sensitivity and specificity for diagnosing active TAO were 88.1% and 86.9%. In the test sets from the entire dataset and from the dataset with consistent results, 40.0% and 49.9% of the predicted CAS values were the same as the reference CAS, respectively. The system predicted the CAS within 1 point of the reference CAS in 84.6% and 89.0% of cases when tested using the entire dataset and in the dataset with consistent results, respectively. An ML-assisted system estimated the clinical activity of TAO and detect inflammatory active TAO with reasonable accuracy. The accuracy could be improved further by obtaining more data. This ML-assisted system can help evaluate the disease activity consistently as well as accurately and enable the early diagnosis and timely treatment of active TAO.
| S-EPMC9772205 | biostudies-literature