Radiomics Study of Thyroid Ultrasound for Predicting BRAF Mutation in Papillary Thyroid Carcinoma: Preliminary Results.

BACKGROUND AND PURPOSE: It is not known how radiomics using ultrasound images contribute to the detection of BRAF mutation. This study aimed to evaluate whether a radiomics study of gray-scale ultrasound can predict the presence or absence of B-Raf proto-oncogene, serine/threonine kinase (BRAF) mutation in papillary thyroid cancer. MATERIALS AND METHODS: The study retrospectively included 96 thyroid nodules that were surgically confirmed papillary thyroid cancers between January 2012 and June 2013. BRAF mutation was positive in 48 nodules and negative in 48 nodules. For analysis, ROIs from the nodules were demarcated manually on both longitudinal and transverse sonographic images. We extracted a total of 86 radiomics features derived from histogram parameters, gray-level co-occurrence matrix, intensity size zone matrix, and shape features. These features were used to build 3 different classifier models, including logistic regression, support vector machine, and random forest using 5-fold cross-validation. The performance including accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve, of the different models was evaluated. RESULTS: The incidence of high-suspicion nodules diagnosed on ultrasound was higher in the BRAF mutation-positive group than in the mutation-negative group (P = .004). The radiomics approach demonstrated that all classification models showed moderate performance for predicting the presence of BRAF mutation in papillary thyroid cancers with an area under the curve value of 0.651, accuracy of 64.3%, sensitivity of 66.8%, and specificity of 61.8%, on average, for the 3 models. CONCLUSIONS: Radiomics study using thyroid sonography is limited in predicting the BRAF mutation status of papillary thyroid carcinoma. Further studies will be needed to validate our results using various diagnostic methods.

Histogram analysis of greyscale sonograms to differentiate between the subtypes of follicular variant of papillary thyroid cancer.

AIM: To evaluate the diagnostic value of histogram analysis using ultrasound (US) to differentiate between the subtypes of follicular variant of papillary thyroid carcinoma (FVPTC). MATERIALS AND METHODS: The present study included 151 patients with surgically confirmed FVPTC diagnosed between January 2014 and May 2016. Their preoperative US features were reviewed retrospectively. Histogram parameters (mean, maximum, minimum, range, root mean square, skewness, kurtosis, energy, entropy, and correlation) were obtained for each nodule. RESULTS: The 152 nodules in 151 patients comprised 48 non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTPs; 31.6%), 60 invasive encapsulated FVPTCs (EFVPTCs; 39.5%), and 44 infiltrative FVPTCs (28.9%). The US features differed significantly between the subtypes of FVPTC. Discrimination was achieved between NIFTPs and infiltrative FVPTC, and between invasive EFVPTC and infiltrative FVPTC using histogram parameters; however, the parameters were not significantly different between NIFTP and invasive EFVPTC. CONCLUSION: It is feasible to use greyscale histogram analysis to differentiate between NIFTP and infiltrative FVPTC, but not between NIFTP and invasive EFVPTC. Histograms can be used as a supplementary tool to differentiate the subtypes of FVPTC.

What Is the Ideal Core Number for Ultrasonography-Guided Thyroid Biopsy of Cytologically Inconclusive Nodules?

BACKGROUND AND PURPOSE: Core needle biopsy of the thyroid under ultrasonographic guidance provides a larger tissue sample and may facilitate a more precise histologic diagnosis, reducing the need for repetitive fine-needle aspiration or a diagnostic operation. However, there is no consensus regarding the ideal number of specimens to be obtained for ultrasonography-guided core needle biopsy. The aim of this study was to decide the ideal core number for ultrasonography-guided core needle biopsy of cytologically inconclusive nodules. MATERIALS AND METHODS: Sixty consecutive biopsies were performed in 60 thyroid nodules with Bethesda Category I or III cytology. Three biopsy cores were obtained for each thyroid nodule. The first biopsy specimens were taken from the nodule, while the second and third specimens obtained included the nodular tissue, nodular capsule, and surrounding parenchyma. Diagnostic ability was evaluated according to the following: protocol A, first specimen; protocol B, first and second specimens; and protocol C, all specimens. The McNemar test was used for statistical analysis. RESULTS: Of the 60 nodules, diagnostic ability was achieved in 41 nodules (68%) with protocol A, in 56 nodules (93%) with protocol B, and in 58 nodules (97%) with protocol C. The diagnostic ability of protocols B and C was significantly higher than that of protocol A (all P values < .001). However, the diagnostic ability of protocol B was not significantly different from that of protocol C. CONCLUSIONS: Ultrasonography-guided core needle biopsy for cytologically inconclusive thyroid nodules should obtain at least 2 core specimens with intranodular and capsule targets.

Modified Core Biopsy Technique to Increase Diagnostic Yields for Well-Circumscribed Indeterminate Thyroid Nodules: A Retrospective Analysis.

BACKGROUND AND PURPOSE: The results of conventional core biopsy for some thyroid nodules with indeterminate cytology have still remained indeterminate. The aim of this study was to evaluate whether the ultrasonography-guided core needle biopsy technique containing the nodule, capsular portion, and surrounding parenchyma was more effective than a conventional method in enhancing diagnostic yield for circumscribed solid thyroid nodules without malignant sonographic features. MATERIALS AND METHODS: This retrospective comparative study evaluated 26 thyroid nodules in 26 consecutive patients between 2006 and 2010. They were biopsied by using a conventional method, and 61 nodules from 60 patients were biopsied by using a modified ultrasonography-guided core needle biopsy technique in 2013. The patients enrolled in this study presented with circumscribed solid thyroid nodules without malignant sonographic features, classified as nondiagnostic or atypia/follicular lesions of undetermined significance at previous cytology. The ultrasonography-guided core needle biopsy results of the 2 groups were compared. RESULTS: The rate of inconclusive ultrasonography-guided core needle biopsy results was 34.6% (9/26) in the conventional group and 11.4% (7/61) in the modified technique group (P = .018). There was no significant difference in the mean size of the nodules between the 2 groups (P = .134). The malignancy rate was 33% (3/9) for the conventional group and 52% (27/52) for the modified technique group (P = .473). The most common malignant pathology was a follicular variant of papillary thyroid carcinoma and follicular adenoma was the most common benign lesion. CONCLUSIONS: For circumscribed solid nodules without malignant sonographic features with indeterminate cytology, the ultrasonography-guided core needle biopsy technique containing the nodule, capsular portion, and surrounding parenchyma is more effective in diagnostic yield compared with a conventional method that biopsies the intranodular portion.

Ultrasonography-guided core needle biopsy for the thyroid nodule: does the procedure hold any benefit for the diagnosis when fine-needle aspiration cytology analysis shows inconclusive results?

OBJECTIVE: We evaluated the diagnostic role of ultrasonography-guided core needle biopsy (CNB) according to ultrasonography features of thyroid nodules that had inconclusive ultrasonography-guided fine-needle aspiration (FNA) results. METHODS: A total of 88 thyroid nodules in 88 patients who underwent ultrasonography-guided CNB because of previous inconclusive FNA results were evaluated. The patients were classified into three groups based on ultrasonography findings: Group A, which was suspicious for papillary thyroid carcinoma (PTC); Group B, which was suspicious for follicular (Hurthle cell) neoplasm; and Group C, which was suspicious for lymphoma. The final diagnoses of the thyroid nodules were determined by surgical confirmation or follow-up after ultrasonography-guided CNB. RESULTS: Of the 88 nodules, the malignant rate was 49.1% in Group A, 12.0% in Group B and 90.0% in Group C. The rates of conclusive ultrasonography-guided CNB results after previous incomplete ultrasonography-guided FNA results were 96.2% in Group A, 64.0% in Group B and 90.0% in Group C (p=0.001). 12 cases with inconclusive ultrasonography-guided CNB results were finally diagnosed as 8 benign lesions, 3 PTCs and 1 lymphoma. The number of previous ultrasonography-guided FNA biopsies was not significantly different between the conclusive and the inconclusive result groups of ultrasonography-guided CNB (p=0.205). CONCLUSION: Ultrasonography-guided CNB has benefit for the diagnosis of thyroid nodules with inconclusive ultrasonography-guided FNA results. However, it is still not helpful for the differential diagnosis in 36% of nodules that are suspicious for follicular neoplasm seen on ultrasonography. ADVANCES IN KNOWLEDGE: This study shows the diagnostic contribution of ultrasonography-guided CNB as an alternative to repeat ultrasonography-guided FNA or surgery.

Automated volumetric breast density estimation: a comparison with visual assessment.

AIM: To compare automated volumetric breast density (VBD) measurement with visual assessment according to Breast Imaging Reporting and Data System (BI-RADS), and to determine the factors influencing the agreement between them. MATERIALS AND METHODS: One hundred and ninety-three consecutive screening mammograms reported as negative were included in the study. Three radiologists assigned qualitative BI-RADS density categories to the mammograms. An automated volumetric breast-density method was used to measure VBD (% breast density) and density grade (VDG). Each case was classified into an agreement or disagreement group according to the comparison between visual assessment and VDG. The correlation between visual assessment and VDG was obtained. Various physical factors were compared between the two groups. RESULTS: Agreement between visual assessment by the radiologists and VDG was good (ICC value = 0.757). VBD showed a highly significant positive correlation with visual assessment (Spearman's ρ = 0.754, p < 0.001). VBD and the x-ray tube target was significantly different between the agreement group and the disagreement groups (p = 0.02 and 0.04, respectively). CONCLUSION: Automated VBD is a reliable objective method to measure breast density. The agreement between VDG and visual assessment by radiologist might be influenced by physical factors.