Predicting Thyroid Malignancy Research Articles

The value of non-punctate echogenic foci in the ultrasonic diagnosis of thyroid nodules.

To evaluate the diagnostic value of different subtypes of non-punctate echogenic foci in thyroid malignancy. Retrospective research of 342 thyroid nodules with calcification was performed. The echogenic foci were divided into punctate echogenic foci (type I) and non-punctate echogenic foci (type II), and type II were further divided into four subtypes: macrocalcification (type IIa), continuous peripheral calcification (type IIb), discontinuous peripheral calcification (type IIc) and isolated calcification (type IId). Postoperative histopathological results were used as the gold standard to evaluate the correlation between non-punctate echogenic foci subtypes and thyroid malignancy. The malignant risk of nodules with echogenic foci was type I (82.1%) > type IIa (66.2%) > type IIc (52.9%) > type IId (16.7%) > type IIb (13.9%), P < 0.001. Type I and type IIa echogenic foci were independent risk factors for thyroid cancer (OR = 16.593, 7.785). Solid, hypoechogenicity/marked hypoechogenicity and a single lesion in a unilateral thyroid lobe were independently associated with malignant thyroid nodules with macrocalcification(OR = 6.825, 40.042, 5.201). Irregular margins and uneven calcification thickness were independent factors for malignant thyroid nodules with peripheral calcification (OR = 5.676, 2.750). Type IIa echogenic foci could independently predict thyroid malignancy. The diagnostic value of non-punctate echogenic foci depended on the differentiated combination of ultrasound characteristics. Type IIa nodules with solid composition, irregular margins, and a single lesion in a unilateral thyroid lobe implied a higher risk of malignancy; peripheral calcified nodules with irregular margins and uneven calcification thickness suggested an increased risk of malignancy.

Efficacy of machine learning model in predicting thyroid malignancy risk

Efficacy of machine learning model in predicting thyroid malignancy risk

Accuracy of ultrasound in predicting thyroid malignancy: a comparative analysis of the ACR TI-RADS and ATA risk stratification systems.

Thyroid nodules are very common in clinical practice, and ultrasound has long been used as a screening tool for their evaluation. Several risk assessment systems based on ultrasonography have been developed to stratify the risk of malignancy and determine the need for fine-needle aspiration in thyroid nodules, including the American Thyroid Association (ATA) system and the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS). The aim of this study was to compare the performance of the ATA and ACR TI-RADS systems in predicting malignancy in thyroid nodules based on the nodules' final histopathology reports. We performed a retrospective review of medical records to identify patients who underwent thyroid surgery at King Abdulaziz University from 2017 to 2022. The ultrasound features of the nodules with confirmed histopathology (benign versus malignant) were evaluated. Both ATA and ACR TI-RADS scores were documented. The analysis included 191 patients who underwent thyroid surgery and fulfilled the inclusion criteria. Hemithyroidectomy was performed in 22.5% of the patients, and total thyroidectomy was performed in 77.0% of them. In all, 91 patients (47.6%) were found to have malignant nodules on histopathology. We then compared the histopathology reports with the preoperative ultrasonographic risk scores. The estimated sensitivity and specificity in identifying malignant nodules were, respectively, 52% and 80% with the ATA system and 51.6% and 90% with the ACR TI-RADS system. Both ATA and ACR TI-RADS risk stratification systems are valuable tools for assessing the malignancy risk in thyroid nodules. In our study, the ACR TI-RADS system had superior specificity compared with the ATA system in predicting malignancy among high-risk lesions.

Correlation of serum thyroid stimulating hormone level to predict benign or malignant nature of thyroid swelling

Background: Thyroid enlargement is a common clinical problem encountered in ENT practice, thyroid cancer, by contrast is less common. Several imaging modalities, FNAB and biomarkers are available but a simple clinical or biochemical diagnostic criterion is still lacking. Serum TSH is a well- established growth factor for thyroid nodules and thus can be used as a simple and reliable test to predict the risk of having a thyroid malignancy in a patient with thyroid swelling. Objectives were to correlate serum TSH level with benign or malignant nature of thyroid swelling and to evaluate the use of TSH level in predicting thyroid malignancy. Methods: This was a prospective observational study conducted over a period of one year at department of otorhinolaryngology and head and neck surgery of a tertiary care center in Nepal involving a total of 61 patients with thyroid swelling who underwent thyroid surgery. Pre-operative serum TSH level was measured and correlated with final HPE diagnosis. Results: The study included 61 patients of which 30 (49.2%) were malignant on histopathology report. The mean TSH level for benign cases was 1.97 mIU/l±0.99 and that for malignant cases was 3.85 mIU/l±1.20 (p=0.000), thus showing higher level of mean serum TSH in malignant group and also more in differentiated thyroid cancer. Conclusions: Patients with higher range of TSH levels were more likely to have thyroid malignancy as compared to lower range even within normal value. Hence, serum TSH level can be a reliable marker to predict malignancy in thyroid swelling.

Thyroid nodules and the risk of cancer based on fine-needle aspiration using Bethesda classification in Riyadh, Saudi Arabia

Background: The presence of thyroid nodules is common and can only be diagnosed through radiographic examination. Fine needle aspiration is an essential technique to identify the type of nodules and their malignancy categorization. This study aims to evaluate the effectiveness of the Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) method in the Security Force Hospital, Riyadh, Saudi Arabia, and to estimate the frequency of Bethesda categorization in reporting fine needle aspiration sampling and predicting the malignancy risk in Riyadh. Methods: This is a retrospective chart review that included records of patients with sonographic thyroid nodules and an indicator for fine needle aspiration based on the American Thyroid Association guideline recommendations. The results of FNA were then classified based on the Bethesda system. Data analysis was executed through the Statistical Package for the Social Sciences (SPSS) version 26. Results: This study included 519 patients over three years. The average age was 49.71±12.4. 74.4% were asymptomatic, 50.7% had a thyroid nodule, while 33.9% had a multinodular goiter. 30.6% of the nodules had a size between 1 to 1.49 cm. 42% had smooth borders. The nodules most commonly had a low suspicion of malignancy by sonography, and 22.7% of the patients underwent thyroid surgery; of them, 54.2% had malignancy. Higher Bethesda classes and a sonographic pattern of intermediate suspicion were common predictors associated with a significantly higher risk of malignancy (p-value &amp;lt; 0.001). Conclusion: Thyroid malignancy is commonly detected by thyroid surgery; the use of Bethesda classification is a predictor of thyroid malignancy, and its application in Saudi hospitals should be improved.

Evaluating Diagnostic Efficiency of Thyroid Imaging Reporting and Data Systems proposed by the American College of Radiology in Surgically Resected Thyroid Nodules.

Thyroid nodules are one of the most common clinical findings, with a prevalence of 68% in adults. Thyroid cancer is the fifth most common cancer in women. The purpose of this study is to evaluate the diagnostic efficacy of Thyroid Imaging Reporting and Data Systems proposed by the American College of Radiology (ACR-TIRADS) for the diagnosis of malignancy in surgically resected thyroid nodules. In this retrospective study, patients who underwent thyroid nodules resected surgically from 2018-2020 were included. Before resection, an ultrasound was performed for TIRADS scores, and after resection histopathology, thyroid mass was obtained. The outcomes of the two systems were statistically compared. The mean age of the 146 included patients was 47.6 ± 14.08 years, of which 109 (74.7%) were female. Based on TIRADS, 47 patients (32.2%) were in TI-RADS TR3, 36 patients (24.7%) were in TIRADS TR2, 34 (23.3%) in TIRADS 4, 24 (16.4%) in TIRADS TR5 and 5 patients (3.4%) were in TIRADS TR1. The overall sensitivity was 79.9% when ACR-TIRADS TR4 was set as a diagnostic cutoff value. Considering the total of TIRADS TR4 and TIRADS TR5 as predictors of thyroid malignancy, the sensitivity was 74.5% and the specificity was 76.8%. The positive and negative predictive value was 60.3% and 76.8%. ACR-TIRADS 4 and 5 can be considered good predictors of malignancy in thyroid nodules. More studies, including larger samples, are required to obtain a better conclusion.

Diagnostic performance of the EU TI-RADS and ACR TI-RADS scoring systems in predicting thyroid malignancy.

Several ultrasound scoring systems have been developed to stratify the risk of malignancy of thyroid nodules, including ACR (American College of Radiology) and EU (European) TI-RADS. This study aimed to assess the diagnostic performance of these two classifications using histology as a reference standard. It was a single-centre, retrospective study including 156 patients who underwent thyroidectomy. Ultrasound data of 198 nodules (99 malignant nodules and 99 benign nodules) were analysed. Both classifications were applied for all nodules. Ultrasound criteria associated with malignancy were solid composition (OR=7.81; p < 10-3 ), hypoechoic character (OR=16.42; p < 10-3 ), irregular contours (OR=7.47; p < 10-3 ), taller-than-wide shape (OR=3.58; p = 0.02), microcalcifications (OR=3.02; p = .006) and the presence of cervical adenopathy (OR=3.89; p = .006). The prevalence of malignancy was 15.5%, 69% and 76.9% for EU TI-RADS categories 3, 4 and 5, respectively. It was 33.3%, 57% and 91.1% for ACR TI-RADS categories 3, 4 and 5, respectively. For category 5, EU TI-RADS and ACR TI-RADS had sensitivities of 60% and 41%, specificities of 82% and 96%, respectively. For categories 4 and 5 combined, the diagnostic performance of these two classification systems became comparable with a sensitivity of 89% and 86% for EU-TIRADS and ACR-TIRADS, respectively. The area under the ROC curve was 0.81 for the EU TI-RADS classification and 0.82 for the ACR TI-RADS classification. EU TI-RADS and ACR TI-RADS scoring systems seem to be comparable in predicting malignancy in thyroid nodules.

Who needs a fine‐needle biopsy? A comparison of the ATA and ACR TI‐RADS guidelines in a single‐centre retrospective study

AbstractThe 2015 American Thyroid Association (ATA) and 2017 American College of Radiology: Thyroid Imaging, Reporting and Data System (ACR TI‐RADS) guidelines are two popular guidelines adopted to stratify sonographic risk of malignancy for thyroid nodules, and to select cases for fine‐needle aspiration (FNA). To understand the test performance of the two systems in predicting thyroid malignancy, 164 thyroidectomy cases performed in a regional hospital in Hong Kong between January 2021 and June 2022 were reviewed. Sonographic images of the index nodule in each case were retrospectively classified into different risk categories using the ATA and ACR TI‐RADS guidelines, respectively, followed by retrieval of cytological and pathological results, for comparison. The index nodule was proven malignant in 26.8% of cases in the final pathology. There was a strong and positive correlation between the ATA and ACR TI‐RADS risk categories assignment (rs = .931, p &lt; .001). Recommending FNA according to the ATA had a better sensitivity for malignancy than using the ACR TI‐RADS (81.8% vs 72.7%), at the expense of a lower specificity (10.8% vs 40.8%). The sensitivity for malignancy of both systems could be further improved if all fluorodeoxyglucose (FDG)‐avid nodules were investigated with FNA regardless of sonographic features and size. There was a statistically significant association between “nodules with FDG avidity and nodules recommended for FNA by the ACR TI‐RADS guideline” and an eventual malignant thyroid nodule (p = .002).

The diagnostic value of a new ultrasonographic method for the measurement of a taller-than-wide shape of benign and malignant thyroid nodules.

To evaluate the diagnostic value of a new ultrasonographic method in the measurement of thyroid nodules with a taller-than-wide (TTW) shape. A total of 982 thyroid nodules were analysed, 571 of which were malignant thyroid nodules and 411 of which were benign nodules. Nodules were divided into two groups by size: Group A (<1 cm, n = 627) and Group B (≥1 cm, n = 355). The angle between the maximum diameter of each nodule and the horizontal axis was measured by image analysis software. The best cut-off value for distinguishing between benign and malignant thyroid nodules and the diagnostic accuracy of the new ultrasonographic method in the measurement of TTW shapes were determined by receiver operating characteristic (ROC) curve analysis. The cut-off value for distinguishing benign and malignant thyroid nodules was 44.5 degrees. The area under the ROC curve (AUC) was 0.849 (95% CI: 0.822~0.875), and the sensitivity and specificity of the diagnosis of malignant thyroid nodules were 86.9% and 84.4%, respectively. Regarding the angle between the maximum diameter and the transverse axis of the thyroid nodules, an angle greater than 45 degrees was a significant indicator of a diagnosis of malignant thyroid nodules. The AUC for distinguishing malignant from benign thyroid nodules with the new ultrasonographic method in the measurement of TTW shapes was higher than that with the first method (FM) in the whole group, Group A and Group B (respectively, 0.849 vs. 0.812, 0.853 vs. 0.808, 0.852 vs. 0.828). The diagnostic sensitivity of a TTW shape measured by the new ultrasonographic method for predicting thyroid malignancy was significantly higher than that measured by the FM in the whole group, Group A and Group B (respectively, 0.858 vs. 0.760, 0.764 vs. 0.669, 0.890 vs. 0.815). A TTW shape measured by our new ultrasonographic method showed superior performance for predicting thyroid malignancy.

Diagnostic performance of artificial intelligence-based computer-aided diagnosis system in longitudinal and transverse ultrasonic views for differentiating thyroid nodules.

To evaluate the diagnostic performance of different ultrasound sections of thyroid nodule (TN) using computer-aided diagnosis system based on artificial intelligence (AI-CADS) in predicting thyroid malignancy. This is a retrospective study. From January 2019 to July 2019, patients with preoperative thyroid ultrasound data and postoperative pathological results were enrolled, which were divided into two groups: lower risk group (ACR TI-RADS 1, 2 and 3) and higher risk group (ACR TI-RADS 4 and 5). The malignant risk scores (MRS) of TNs were obtained from longitudinal and transverse sections using AI-CADS. The diagnostic performance of AI-CADS and the consistency of each US characteristic were evaluated between these sections. The receiver operating characteristic (ROC) curve and the Cohen κ-statistic were performed. A total of 203 patients (45.61 ± 11.59 years, 163 female) with 221 TNs were enrolled. The area under the ROC curve (AUC) of criterion 3 [0.86 (95%CI: 0.80~0.91)] was lower than criterion 1 [0.94 (95%CI: 0.90~ 0.99)], 2 [0.93 (95%CI: 0.89~0.97)] and 4 [0.94 (95%CI: 0.90, 0.99)] significantly (P<0.001, P=0.01, P<0.001, respectively). In the higher risk group, the MRS of transverse section was higher than longitudinal section (P<0.001), and the agreement of extrathyroidal extension and shape was moderate and fair (κ =0.48, 0.31 respectively). The diagnostic agreement of other ultrasonic features was substantial or almost perfect (κ >0.60). The diagnostic performance of computer-aided diagnosis system based on artificial intelligence (AI-CADS) in longitudinal and transverse ultrasonic views for differentiating thyroid nodules (TN) was different, which was higher in the transverse section. It was more dependent on the section for the AI-CADS diagnosis of suspected malignant TNs.

Role of Serum TSH Levels in Predicting Thyroid Malignancy

Role of Serum TSH Levels in Predicting Thyroid Malignancy

Predicting coexisting thyroid cancer with primary hyperparathyroidism in an endemic region of multinodular goiter: evaluating the effectiveness of preoperative inflammatory markers.

The aim is to examine the efficacy of inflammatory indicators to predict thyroid cancer in patients with primary hyperparathyroidism (PHPT) in an endemic region of nodular goiter. The prospective database was reviewed to identify patients operated on with the diagnosis of PHPT and thyroid disease between April 2015 and June 2021. Permanent pathologic reports were used as the gold standard for diagnosis. Detailed imaging data with peripheral blood inflammation indices were analyzed to assess their predictive values for concomitant PHPT with thyroid cancer. Postoperative complications and the duration of hospitalization were also reviewed. Thyroid malignancy accompanying PHPT was found in 13 patients (26.0%) out of 50 who had concurrent surgery. The analysis regarding inflammatory indexes revealed nothing significant between thyroid cancer and preoperative blood biochemistry (P > 0.05). In the concurrent surgery group, recurrent laryngeal nerve injury was observed in 1 patient (2.0%) and the mean hospital stay was longer. In endemic regions of nodular thyroid disease, thyroid cancer might accompany PHPT. The value of inflammatory indexes to predict thyroid malignancy in PHPT is controversial and should not be employed in the surgical decision-making process.

PSAT379 Performance of a Raman Fingerprint in Thyroid Nodules with Indeterminate Cytology: A Prospective Blinded Monocentric Study

Abstract Background Molecular analysis of thyroid fine-needle aspiration biopsy (FNA) was proposed to improve indeterminate nodules management. However, sensibility and specificity as well as the cost of molecular diagnostics require to be improved to increase their cost-effectiveness for medical practice setting. Raman spectroscopy (RS) demonstrated ability in separating benign from malignant thyroid lesions in surgically removed tissues, based on specific RS profile. This study aimed to investigate the diagnostic performance of RS on cytological samples obtained by thyroid FNA. Methods In this prospective, blinded monocentric study, we enrolled 123 patients with indeterminate or worse cytological diagnosis, candidate to surgery according to international guidelines, and submitted to RS analysis of FNA samples. Cytology specimens were evaluated in agreement to Italian Reporting System for Thyroid Cytology1 as follows: TIR1 (non-diagnostic), TIR1C (non-diagnostic-cystic), TIR 2 non-malignant/benign, TIR3A (low-risk indeterminate lesion), TIR3B (high-risk indeterminate lesion), TIR 4 (suspicious of malignancy), or TIR 5 (malignant). As previously published2, the two diagnostic subcategories referred to indeterminate nodules with low (TIR3A) and high risk (TIR3B) of malignancy, may be respectively compared to the class III and Class IV of The Bethesda System for Reporting Thyroid Cytopathology. We compared RS, cytology and final histology, as reference standard, using various statistical approaches. Findings: Our study population included 37 TIR3A, 32 TIR3B, 16 TIR4 and 38 TIR5; the 30.9% of patients had benign histological diagnosis after surgery. In particular, 72.9% of patients classified TIR3A and 31.3% TIR3B had benign histological diagnosis. RS analysis of FNA samples had overall specificity of 86.8% in predicting thyroid malignancy. In indeterminate cytological categories, RS specificity was 86.5%. In patients with TI-RADS score four or five, the specificity of RS increased to 87.5% for TIR3A and reached 100% in TIR3B.; if considering RS positive test, unnecessary surgery was reduced to 7.4% in the whole sample, 33.3% in TIR3A, and 6.7% in TIR 3B. Interpretation: We demonstrated for the first time that RS represents a valuable tool for thyroid cytology and a valid alternative to molecular analyses, able to improve management and reduce unnecessary surgery in indeterminate nodules. Funding: This study was supported by Ministero della Salute, through TIRAMA project (RF-2018-12366568). 1 J Endocrinol Invest. 2014;37(6): 593-599. doi: 10.1007/s40618-014-0062-0 2Cytopathology. 2021;32(6): 714-717. Presentation: Saturday, June 11, 2022 1:00 p.m. - 3:00 p.m.

Clinical Use of Raman Spectroscopy Improves Diagnostic Accuracy for Indeterminate Thyroid Nodules

Molecular analysis of thyroid fine-needle aspiration (FNA) specimens is believed to improve the management of indeterminate nodules. Raman spectroscopy (RS) can differentiate benign and malignant thyroid lesions in surgically removed tissues, generating distinctive structural profiles. Herein, the diagnostic performance of RS was tested on FNA biopsies of thyroid gland. Prospective, blinded, and single-center study. We enrolled 123 patients with indeterminate or more ominous cytologic diagnoses (TIR3A-low-risk indeterminate lesion, TIR3B-high-risk indeterminate lesion, TIR4-suspicious of malignancy, TIR5-malignant). All subjects were surgical candidates (defined by international guidelines) and submitted to FNA procedures for RS analysis. We compared RS data, cytologic findings, and final histologic assessments (as reference standard) using various statistical techniques. The distribution of our study population was as follows: TIR3A:37, TIR3B:32, TIR4:16, and TIR5:38. In 30.9% of patients, histologic diagnoses were benign. For predicting thyroid malignancy in FNA samples, the overall specificity of RS was 86.8%, with 86.5% specificity in indeterminate cytologic categories. In patients with high-risk ultrasound categories, the specificity of RS increased to 87.5% for TIR3A, reaching 100% for TIR3B. Benign histologic diagnoses accounted for 72.9% of patients classified as TIR3A and 31.3% of those classified as TIR3B. Based on positive RS testing, unnecessary surgery was reduced to 7.4% overall (TIR3A-33.3%, TIR3B-6.7%). This premier use of RS for thyroid cytology confirms its role as a valuable diagnostic tool and a valid alternative to molecular studies, capable of improving the management of indeterminate nodules and reducing unnecessary surgery.

The reliability of TIRADS classification in predicting thyroid malignancy based on ultrasound findings in Mosul city

Introduction and Aim: Ultrasound of the thyroid gland is a routine procedure. Nodules are the most common disorders seen and analyzed by ultrasound. The study purpose was to show how accurate ultrasonography was at identifying benign from malignant nodules using (Thyroid Imaging Reporting and Data System TIRADS) categories. High-frequency ultrasonography scanning of the neck and thyroid glands offers useful information and anatomical images. Materials and Methods: This study involved 495 patients who were subjected to a thyroid ultrasound imaging from December 2019 to December 2020. The ultrasound and evaluation was performed by a professional Radiologist by means of a transducer with linear-array (between 5 - 12 MHz) (DC-30, Shenzhen Mindray Bio-Medical Electronics Co., Ltd). Nodules detected were evaluated for composition, echogenicity, boundary, shape and echogenic foci. Each attribute was recorded using the standardized scoring system provided by the ACR Thyroid Imaging Reporting and Data System (ACR TI-RADS). The scores obtained, were used in classifying the nodules as TI-RADS 1, 2, 3, 4a, 4b, and 5 to define risk levels of malignant nodule. Results: TIRADS approach was used to assess the thyroid ultrasound data obtained and the nodules categorized created on ultrasound features such as irregular edges, shape, tall rather wide, hypo echogenic, calcified, and vascular. The TIRAD 3 category was the most common accounting for about 251 cases (52.73 percent of the calculated diagnostic results, which included specificity (50%), sensitivity (96.59%), positive (97.21%) and negative (55.17%) predictive values. The study revealed 26 (4.25%) of the nodules to be cancerous. Conclusion: Since the TIRADS system of categorization is a good technique for predicting malignancies in thyroid nodules, we employ ultrasound as the first diagnostic tool for efficiently finding and classifying thyroid nodules.

Accuracy of the ‘CUT’ Score for Assessing Malignancy in Bethesda 3 and 4 Thyroid Nodules in North American population: a retrospective study.

Background The CUT score is a thyroid nodule malignancy risk assessment scoring system intended to guide surgeons in treating Bethesda 3 and 4 thyroid nodules. It is based on clinical (C) and ultrasonographic (U) features and a five-tiered (T) representing cytology. Purpose Our study aimed to assess the utility of the CUT score in predicting thyroid malignancy in the North American population. The main reason for creating this score is to reduce unnecessary surgeries on these challenging thyroid nodules. Materials and Methods A retrospective record review study applied the CUT score to 219 Bethesda 3 and 4 thyroid nodules. A total of 203 Bethesda 3 and 16 Bethesda 4 nodules from patients treated between January 2015 and December 2019 at a single institution were assessed. A receiver operating characteristic (ROC) curve analysis was performed to evaluate the CUT diagnostic test. Binary logistic regression analysis was performed. Iteration of analysis was performed after stratification according to body mass index to assess CUT score accuracy in obese and non-obese patients. Results Of 219 nodules analyzed, 148 were characterized as benign and 71 as malignant. Prevalence rates of malignancy were 29.6% (n = 60) and 68.8% (n = 11) in Bethesda 3 and 4 nodules, respectively. The mean CU (clinical, ultrasonography) score was 5.35 ± 1.38 in benign nodules versus 4.96 ± 1.5 in malignant nodules (p = 0.08). The area under the curve (AUC =0.433) for the association of CUT scores with nodule malignancy was not significant (p = 0.13). The CUT score was insignificant as a diagnostic test for nodule malignancy in obese (AUC =0.45; p = 0.72) and non-obese patients (AUC =0.39; p = 0.08). Conclusion The CUT score did not correlate with preoperative malignancy risk estimates in Bethesda 3 thyroid nodules and, therefore, may have limited utility as a predictor of malignancy in these thyroid nodules.

Thyroid nodule ultrasound accuracy in predicting thyroid malignancy based on TIRADS system.

A frequent prevalence of thyroid nodules in patients prioritizes the need for an accurate method that characterizes them as benign or malignant. Fine-needle aspiration biopsy (FNAB) and thyroid ultrasonography (USG) are currently used for this purpose. However, since FNAB is complicated, time-consuming and expensive, thyroid USG, a fast and highly sensitive method, is preferably used. Although USG is reported as a suitable method for characterization of thyroid nodules, there are some contrasting studies available which report its limited use in the differentiation of benign and malignant thyroid nodules. This meta-analysis aims to assess the accuracy of ultrasound in predicting thyroid cancer in terms of sensitivity, specificity and diagnostic odds ratios (ORs) for positive and negative results. Systematic and extensive literature search on the use of ultrasound (US) to predict thyroid cancer was conducted in the databases of Scopus, CINAHL (via EBSCO), MEDLINE (via PubMed), and Web of Science, covering the period from 2010 till 2021. The morphological features of thyroid nodules observed during the USG were analyzed based on Thyroid Imaging Reporting And Data System (TIRADS) guidelines. The accuracy of thyroid US was determined using parameters such as sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), and diagnostic ORs. Moreover, the respective forest plot and hierarchical summary receiver operating characteristics (HSROC) curve were plotted. A total of 2765 reference studies were examined, and among them, 15 relevant references were selected. The selected studies were heterogeneous and included retrospective and prospective studies. The risk of publication bias is low as the p-value for both Egger's and Begg's tests is >0.05. The overall sensitivity of 92.53% (95% confidence interval (95% CI): [84.55%; 96.33%]), specificity of 33.88% (95% CI: [23.16%; 45.53%]) and diagnostic OR of 12.36 (95% CI: [3.90%; 54.11%]) are achieved. These results were statistically significant with a p-value < 0.001 and are predictive of US accuracy in detecting cancer. The present meta-analysis, on the basis of statistically significant results, demonstrated the high accuracy of thyroid ultrasound in detection of malignant nature of nodules in patients suspected with a worrisome thyroid nodule.

Pattern of Thyroid Cancer and its Associated Factors among Thyroid Patients Underwent Thyroidectomy at Jimma Medical Center, Southwest Ethiopia; A Four Years Retrospective Review

Background: Thyroid cancer is the most common malignant disease of endocrine system and its incidence is rapidly increasing globally (about three to four times higher among females and accounts the sixth most common malignancy diagnosed in women). Among the four major types of thyroid cancer, papillary thyroid cancer (PTC) accounts 85-90% from all thyroid cases, followed by follicular thyroid cancer (FTC) which accounts for 5-10% of cases. Objective: The present study aimed to assess the pathologic patterns of thyroid disease at Jimma medical center (JMC). Materials and Methods: A retrospective data of 260 patients who underwent thyroid surgery from 2015 to 2019 were included in the study and the status of the disease (clinical manifestations, laboratory/pathology findings (thyroid function tests (TFTs) and biopsy) were reviewed from patient cards. The pattern of thyroid cancer was discriminated based on histo-pathological biopsy results. Descriptive and analytical statistics were applied to express the finding and reported by tables, figures and narration. Cross tabulation and logistic regression was applied to determine the association between thyroid CA and its predictors. A p-value of &lt;0.05 was declared as statistically significant. Results: From the total sample of 260 patients underwent thyroid surgery, majority of them were females 219(84.2%), belong to age interval of 31-40 years (34.6%), dwellers of Oromia region (91.2%) and Jimma zone (83.8%). Colloid goiter was the most prevalent pattern of thyroid disease (74.6%) followed by follicular CA (4.2%), papillary CA (1.9%) and medullary CA (0.77%) while biopsy results of 48(18.46%) patients were not known. In general, about 194(91.5%) of the thyroid lesion was identified as benign type and malignancy accounts for 18(8.5%) from the total conducted biopsy results of 212 patients. Five variables (marital status, family history of the disease, nodularity, surface and border of the thyroid mass) were the predictors of thyroid malignancy in univariate and finally, two variables (thyroid tissue with surface (rough) and border (irregular)) were identified as the predictors of thyroid malignancy in multivariate [1.9(95%CI; 1.17 to 5.8) P=0.012 and 2.5(95%CI; 1.13 to 16.16) P&lt;0.001] respectively. Conclusion and Recommendation: The burden of malignancy was higher and alarming among thyroid diseases and warrants early screening and management.

An Artificial Intelligence Ultrasound Platform for Screening and Staging of Thyroid Cancer

<h3>Purpose/Objective(s)</h3> Thyroid cancer is one of the most rapidly increasing cancer in the US, largely due to increased detection. BRAF mutation (V600E) is common in papillary thyroid carcinoma (PTC) and is associated with poor prognosis. The purpose of this study was to establish a multimodal artificial intelligence (AI) ultrasound platform that consists of radiomics, topological data analysis (TDA), TI-RADS features, and deep learning (DL) to predict malignancy and pathological outcome in patients with papillary thyroid cancer. <h3>Materials/Methods</h3> Between 2010 and 2021, 464 patients (511 nodules) underwent fine needle biopsy at our institution. The median age was 49 years. The dataset was divided into an internal training (103 malignant, 259 benign nodules), an internal validation (51 malignant and 98 benign nodules), and an external validation (270 malignant and 50 benign nodules) datasets. High-resolution ultrasonography (sagittal and transverse views) was performed preoperatively for all patients. We employed multimodal machine learning (ML) methods: radiomics (a high-throughput quantitative analysis of image features), TDA (a rapidly growing ML pipeline that analyzes geometric relationships between data points in images), and deep learning (where algorithms run data through layers of neural network to achieve prediction). One hundred and four quantitative radiomics features, 476 topological algebraic-geometric features), and TI-RADS features were obtained for all patients. Linear discriminant analysis (LDA) along with the Pearson correlation coefficient (0.85 threshold) were employed for feature extraction. Support vector machine (SVM) was chosen as the machine learning classifier. <h3>Results</h3> For malignancy prediction, radiomics, TDA, TI-RADS, and deep learning model achieves an accuracy of 88.7% (0.87 AUC), 81.5% (0.81 AUC), 80% (0.76 AUC), and 87.4% (0.92 AUC), respectively. Our multimodal AI platform which utilizes radiomics, TDA, TI-RADS, and deep learning achieves a 98.7% accuracy (0.99 AUC), which is significantly improved when compared to individual model (radiomics, TDA, TI-RADS: p<0.001, deep learning: p=0.002). On the external validation dataset, our model achieves a 91.4% accuracy (0.94 AUC) for malignancy prediction. Using multimodal that consists of radiomics, TDA, and TI-RADS, an accuracy of 93% accuracy (0.93 AUC), 89% accuracy (0.88 AUC), and 98% (0.96 AUC) is achieved for T, N, and extrathyroidal extension, respectively. Employing a 5-fold cross validation, we achieve an accuracy of 96% (0.97 AUC) for predicting BRAF mutation. <h3>Conclusion</h3> We established a robust AI platform for predicting thyroid malignancy, pathological stage, and BRAF mutation using routine ultrasonography. This low-cost reproducible approach would allow developing of personalized treatment planning, especially in countries where resources are limited.

The predictive value of hematologic parameters in the risk of thyroid malignancy in cases with atypia/follicular lesion of undetermined significance.

Atypia/follicular lesion of undetermined significance (AUS/FLUS) is still the most challenging category in the Bethesda System for Reporting Thyroid Cytopathology. Therefore, the aim of the current study was to investigate the value of the neutrophil-to-lymphocyte ratio (NLR), platelet-to-lymphocyte ratio (PLR), and mean platelet volume (MPV) in predicting malignancy in cases with AUS/FLUS nodules. A total of 200 patients with AUS/FLUS nodules who underwent thyroidectomy were included in this study. Preoperative hemogram parameters, ultrasonographic findings, fine-needle aspiration results, and postoperative final histopathological diagnoses of the patients were recorded retrospectively. Thyroid malignancies were detected in 122 of the patients (61.0%). Patients in the benign group (BG) were older than those in the malignancy group (MG) (52.0 ± 11.3 vs. 45.9 ± 12.3years, p < 0.001). The median TSH values of the two groups were comparable. Statistically significant differences were obtained between the two groups in respect of mean WBC of 7.53 ± 1.44 in MG and 6.87 ± 1.35 (103/mm3) in BG, mean neutrophil of 4.65 ± 1.12 in MG and 3.95 ± 0.99 (103/mm3) in BG, and median NLR of 2.18 (0.71-4.57) in MG and 1.75 (0.80-3.42) in BG (p < 0.001). The median PLR and MPV values of the two groups were similar. When NLR cut-off point was designated as 2.24, the accuracy of NLR in distinguishing malignancy from the benign condition was 0.65 in ROC analysis (area under the curve, 0.665; specificity, 0.808; sensitivity, 0.492). High NLR values may provide limited help in predicting thyroid malignancy in the AUS/FLUS nodule population, while PLR and MPV are not reliable parameters.