Internal content classification of ultrasound thyroid nodules based on textural features

Thyroid nodules have diversified internal components and dissimilar echo patterns in ultrasound images. Textural features are used to characterize these echo patterns. This paper presents a classification scheme that uses shearlet transform based textural features for the classification of thyroid nodules in ultrasound images. The study comprised of 60 thyroid ultrasound images (30 with benign nodules and 30 with malignant nodules). Total of 22 features are extracted. Support vector machine (SVM) and K nearest neighbor (KNN) are used to differentiate benign and malignant nodules. The diagnostic sensitivity, specificity, F1_score and accuracy of both the classifiers are calculated. A comparative study has been carried out with respect to their performances. The sensitivity of SVM with radial basis function (RBF) kernel is 100% as compared to that of KNN with 96.33%. The proposed features can increase the accuracy of the classifier and decrease the rate of misdiagnosis in thyroid nodule classification.

Download Full-text

The Accuracy of ACR TI-RADS Classification of Neck Ultrasound as a First-Line Diagnostic Approach for Thyroid Neoplasms in Pediatric Patients: A Retrospective Study

Oncopediatrics ◽

10.15690/onco.v5i1.1862 ◽

2018 ◽

Vol 5 (1) ◽

pp. 13-23

Author(s):

Nikolai S. Grachev ◽

Elena V. Feoktistova ◽

Igor N. Vorozhtsov ◽

Natalia V. Babaskina ◽

Ekaterina Yu. Iaremenko ◽

...

Keyword(s):

Thyroid Cancer ◽

Predictive Value ◽

Thyroid Nodules ◽

Pediatric Patients ◽

Thyroid Neoplasms ◽

Diagnostic Methods ◽

Diagnostic Approach ◽

First Line ◽

Neck Ultrasound

Background.Ultrasound (US)-guided fine-needle aspiration biopsy (FNAB) is the gold standard in diagnosing the pathological nature of undetermined thyroid nodules. However, in some instances limitations and shortcomings arise, making it insufficient for determining a specific diagnosis.Objective.Our aim was to evaluate the effectiveness of ACR TI-RADS classification of neck ultrasound as a first-line diagnostic approach for thyroid neoplasms in pediatric patients.Methods.A retrospective analysis was made of FNA and US protocols in 70 patients who underwent the examination and treatment at Dmitry Rogachev National Research Center between January 2012 and August 2017. In the retrospective series 70% (49/70) of patients undergone FNA and 43% (30/70) of them undergone repeated FNA. All US protocols were interpreted according to ACR TI-RADS system by the two independent experts. The clinical judgment was assessed using the concordance test and the reliability of preoperative diagnostic methods was analized.Results.According to histologic examination protocols, benign nodules reported greater multimorbidity 29% (20/70), compared with thyroid cancer 17% (12/70), complicating FNA procedure. A statistically significant predictor of thyroid cancer with a tumor size ACR TI-RADS showed a significant advantage of ACR TI-RADS due to higher sensitivity (97.6 vs 60%), specificity (78.6 vs 53.8%), positive predictive value (87.2 vs 71.4%), and negative predictive value (95.7 vs 41.2%). Concordance on the interpreted US protocols according to ACR TI-RADS classification between two experts was high, excluding accidental coincidence.Conclusion.The data support the feasibility of US corresponding to the ACR TI-RADS classification as a first-line diagnostic approach for thyroid neoplasm reducing the number of unnecessary biopsies for thyroid nodules.

Download Full-text

On the Classification of TI-RADS and Stratification of Signs of Thyroid Cancer According to Ultrasound Data

Medical Visualization ◽

10.24835/1607-0763-2017-5-29-38 ◽

2017 ◽

pp. 29-38 ◽

Cited By ~ 1

Author(s):

E. P. Fisenko ◽

J. P. Sich ◽

N. N. Vetsheva

Keyword(s):

Thyroid Cancer ◽

Retrospective Analysis ◽

Thyroid Nodules ◽

Thyroid Ultrasound ◽

High Reproducibility ◽

System 1

Objective:a comparative “blind” assessment of the thyroid nodules identified by ultrasound, according to the TI-RADS scale in various modifications.Materials and methods.Retrospective analysis of 149 echograms of thyroid nodules by three independent experts was performed (the experience of ultrasound of thyroid ultrasound for more than 7 years).Results. In solid nodules, high-specific large (more than 94%) and small (more than 90%) ultrasound signs of thyroid cancer have been identified. The nodes are stratified according to the TI-RADS system: 1 – in the modification J.Y. Kwak et al. (2011), 2 – according to the proposed system, taking into account small ultrasound signs of thyroid cancer. High reproducibility of both systems are obtained. In the first system 13.7% of cancer nodes fell into the category of TI- RADS 3 (benign formations), in the second system only 5% of cancers fell into the category of TI-RADS 3, which is important for biopsy selection. The sensitivity of the first system was TI-RADS 82.05%, of the second system – 94.87%.Conclusions.Classification of TI-RADS can be used to interpret the ultrasound results of thyroid nodules, taking into account both the main large and small ultrasound signs of cancer. For its validation in our country, it is necessary to further broad discussion of the proposed TI-RADS system.

Download Full-text

Application of the Bethesda system for reporting thyroid cytopathology for classification of thyroid nodules: A clinical and cytopathological characteristics in Bhutanese population

Diagnostic Cytopathology ◽

10.1002/dc.24843 ◽

2021 ◽

Author(s):

Sonam Choden ◽

Chimi Wangmo ◽

Sushna Maharjan

Keyword(s):

Thyroid Nodules ◽

Bethesda System ◽

Thyroid Cytopathology ◽

The Bethesda System

Download Full-text

A Phantom Study to Investigate Robustness and Reproducibility of Grey Level Co-Occurrence Matrix (GLCM)-Based Radiomics Features for PET

Applied Sciences ◽

10.3390/app11020535 ◽

2021 ◽

Vol 11 (2) ◽

pp. 535

Author(s):

Mahbubunnabi Tamal

Keyword(s):

Textural Features ◽

Strongly Correlated ◽

Segmentation Method ◽

Diagnosis And Prognosis ◽

Radiotracer Uptake ◽

Positron Emission ◽

Occurrence Matrix ◽

The Impact ◽

Robust To Noise

Quantification and classification of heterogeneous radiotracer uptake in Positron Emission Tomography (PET) using textural features (termed as radiomics) and artificial intelligence (AI) has the potential to be used as a biomarker of diagnosis and prognosis. However, textural features have been predicted to be strongly correlated with volume, segmentation and quantization, while the impact of image contrast and noise has not been assessed systematically. Further continuous investigations are required to update the existing standardization initiatives. This study aimed to investigate the relationships between textural features and these factors with 18F filled torso NEMA phantom to yield different contrasts and reconstructed with different durations to represent varying levels of noise. The phantom was also scanned with heterogeneous spherical inserts fabricated with 3D printing technology. All spheres were delineated using: (1) the exact boundaries based on their known diameters; (2) 40% fixed; and (3) adaptive threshold. Six textural features were derived from the gray level co-occurrence matrix (GLCM) using different quantization levels. The results indicate that homogeneity and dissimilarity are the most suitable for measuring PET tumor heterogeneity with quantization 64 provided that the segmentation method is robust to noise and contrast variations. To use these textural features as prognostic biomarkers, changes in textural features between baseline and treatment scans should always be reported along with the changes in volumes.

Download Full-text

Classification of Thyroid Nodules with Stacked Denoising Sparse Autoencoder

International Journal of Endocrinology ◽

10.1155/2020/9015713 ◽

2020 ◽

Vol 2020 ◽

pp. 1-8

Author(s):

Zexin Li ◽

Kaiji Yang ◽

Lili Zhang ◽

Chiju Wei ◽

Peixuan Yang ◽

...

Keyword(s):

Likelihood Ratio ◽

Predictive Value ◽

Thyroid Nodules ◽

Area Under The Curve ◽

Positive Likelihood Ratio ◽

Negative Likelihood Ratio ◽

Discriminative Ability ◽

Sparse Autoencoder ◽

Immune Related Genes

Purpose. Several commercial tests have been used for the classification of indeterminate thyroid nodules in cytology. However, the geographic inconvenience and high cost confine their widespread use. This study aims to develop a classifier for conveniently clinical utility. Methods. Gene expression data of thyroid nodule tissues were collected from three public databases. Immune-related genes were used to construct the classifier with stacked denoising sparse autoencoder. Results. The classifier performed well in discriminating malignant and benign thyroid nodules, with an area under the curve of 0.785 [0.638–0.931], accuracy of 92.9% [92.7–93.0%], sensitivity of 98.6% [95.9–101.3%], specificity of 58.3% [30.4–86.2%], positive likelihood ratio of 2.367 [1.211–4.625], and negative likelihood ratio of 0.024 [0.003–0.177]. In the cancer prevalence range of 20–40% for indeterminate thyroid nodules in cytology, the range of negative predictive value of this classifier was 37–61%, and the range of positive predictive value was 98–99%. Conclusion. The classifier developed in this study has the superb discriminative ability for thyroid nodules. However, it needs validation in cytologically indeterminate thyroid nodules before clinical use.

Download Full-text