Track topics on Twitter Track topics that are important to you
The purpose of this study was to develop and validate a radiomics model for evaluating immunohistochemical characteristics in patients with suspected thyroid nodules. A total of 103 patients (training cohort-to-validation cohort ratio, ≈ 3:1) with suspected thyroid nodules who had undergone thyroidectomy and immunohistochemical analysis were enrolled. The immunohistochemical markers were cytokeratin 19, galectin 3, thyroperoxidase, and high-molecular-weight cytokeratin. All patients underwent CT before surgery, and a 3D slicer was used to analyze images of the surgical specimen. Test-retest and Spearman correlation coefficient (ρ) were used to select reproducible and nonredundant features. The Kruskal-Wallis test ( < 0.05) was used for feature selection, and a feature-based model was built by support vector machine methods. The performance of the radiomic models was assessed with respect to accuracy, sensitivity, specificity, corresponding AUC, and independent validation. Eighty-six reproducible and nonredundant features selected from the 828 features were used to build the model. The best performance of the cytokeratin 19 model yielded accuracy of 84.4% in the training cohort and 80.0% in the validation cohort. The thyroperoxidase and galectin 3 predictive models yielded accuracies of 81.4% and 82.5% in the training cohort and 84.2% and 85.0% in the validation cohort. The performance of the high-molecular-weight cytokeratin predictive model was not good (accuracy, 65.7%) and could not be validated. A radiomics model with excellent performance was developed for individualized noninvasive prediction of the presence of cytokeratin 19, galectin 3, and thyroperoxidase based on CT images. This model may be used to identify benign and malignant thyroid nodules.
This article was published in the following journal.
Name: AJR. American journal of roentgenology
Thyroid nodules are common incidental findings. Ultrasonography and molecular testing can be used to assess risk of malignant neoplasm.
To study the ultrasonographic (US) differences between "mummified" thyroid nodules and malignant thyroid nodules in order to achieve a more accurate imaging-based diagnosis and to avoid unnecessary bi...
Thyroid nodules are a common clinical problem. Ultrasonography (US) is the main tool used to sensitively diagnose thyroid cancer. Although US is non-invasive and can accurately differentiate benign an...
Acute myeloid leukemia (AML) is a severe, mostly fatal hematopoietic malignancy. We were interested in whether transcriptomic-based machine learning could predict AML status without requiring expert i...
Thyroid nodules are routinely evaluated with ultrasound. Our aim was to determine if thyroid nodule location was a useful feature to predict thyroid cancer Methods: Retrospective review of patients wi...
Nowadays, the investigation of thyroid nodules is limited by the fact that up to 49% of the fine needle aspirations (FNA) performed on them are of "indeterminate cytological signification"...
Participants in this study will be patients diagnosed with or suspected to have a thyroid nodule or thyroid cancer. The main purpose of this study is to further understand the methods for...
Thyroid nodules are a common presentation in the clinic, with an increasing incidence, especially in women. Their clinical significance is mainly related to excluding malignancy (4.0 to 6....
Recently, targeted next generation sequencing (NGS) platforms have been introduced that allow inexpensive testing for hundreds of mutational hotspots at the same time. A number of addition...
Ultrasound-guided ethanol ablation is an effective treatment modality for patients with cystic thyroid nodules (cystic portion > 90%); however it is less effective in predominantly cystic ...
A MACHINE LEARNING paradigm used to make predictions about future instances based on a given set of unlabeled paired input-output training (sample) data.
A MACHINE LEARNING paradigm used to make predictions about future instances based on a given set of labeled paired input-output training (sample) data.
SUPERVISED MACHINE LEARNING algorithm which learns to assign labels to objects from a set of training examples. Examples are learning to recognize fraudulent credit card activity by examining hundreds or thousands of fraudulent and non-fraudulent credit card activity, or learning to make disease diagnosis or prognosis based on automatic classification of microarray gene expression profiles drawn from hundreds or thousands of samples.
Usually refers to the use of mathematical models in the prediction of learning to perform tasks based on the theory of probability applied to responses; it may also refer to the frequency of occurrence of the responses observed in the particular study.
A small circumscribed mass in the THYROID GLAND that can be of neoplastic growth or non-neoplastic abnormality. It lacks a well-defined capsule or glandular architecture. Thyroid nodules are often benign but can be malignant. The growth of nodules can lead to a multinodular goiter (GOITER, NODULAR).
The thyroid is a butterfly-shaped gland in the neck, just above thecollarbone and is an endocrine gland that make hormones. These Thyroid hormones control the rate of many activities in the body, including how fast the body burns calories and how fast th...
Surgery is a technology consisting of a physical intervention on tissues. All forms of surgery are considered invasive procedures; so-called "noninvasive surgery" usually refers to an excision that does not penetrate the structure being exci...