Stepwise analysis of thyroid diagnostic modalities with genomic imprinting detection.

BACKGROUND: The current preoperative malignancy risk evaluation for thyroid nodules involves stepwise diagnostic modalities including ultrasonography, thyroid function serology and fine-needle aspiration (FNA) cytopathology, respectively. We aimed to substantiate the stepwise contributions of each diagnostic step and additionally investigate the diagnostic significance of quantitative chromogenic imprinted gene in-situ hybridization (QCIGISH)-an adjunctive molecular test based on epigenetic imprinting alterations. METHODS: A total of 114 cytopathologically-diagnosed and histopathologically-confirmed thyroid nodules with complete ultrasonographic and serological examination records were evaluated using QCIGISH in the study. Logistic regression models for thyroid malignancy prediction were developed with the stepwise addition of each diagnostic modality and the contribution of each step evaluated in terms of discrimination performance and goodness-of-fit. RESULTS: From the baseline model using ultrasonography [area under the receiver operating characteristics curve (AUROC): 0.79; 95% confidence interval (CI): 0.71-0.86], significant improvements in thyroid malignancy discrimination were observed with the stepwise addition of thyroid function serology (AUROC: 0.82; 95% CI: 0.74-0.90; P=0.23) and FNA cytopathology (AUROC: 0.88; 95% CI: 0.81-0.94; P=0.02), respectively. The inclusion of QCIGISH as an adjunctive molecular test further advanced the preceding model's diagnostic performance (AUROC: 0.95; 95% CI: 0.91-1.00, P=0.007). CONCLUSIONS: Our study demonstrated the significant stepwise diagnostic contributions of standard clinical assessments in the malignancy risk stratification of thyroid nodules. However, the addition of molecular imprinting detection further enabled a more accurate and definitive preoperative evaluation especially for morphologically indeterminate thyroid nodules and cases with potentially discordant results among standard modalities.

ThyroSeq overview on indeterminate thyroid nodules: An institutional experience.

BACKGROUND: Molecular triage of indeterminate thyroid aspirates offers the opportunity to stratify the risk of malignancy (ROM) more accurately. Here we examine our experience with ThyroSeq v3 testing. METHODS: We analyzed 276 of 658 (42%) fine needle aspiration samples classified as indeterminate thyroid nodules using ThyroSeq v3 (Sept 2017-Dec 2019). The test provides a ROM and detects specific mutations. Surgical diagnoses were reviewed. RESULTS: Of 276 ThyroSeq-tested cases, 42% (n = 116) harbored genetic alterations, whereas 64% (n = 74) had surgical follow-up. Notably, 79% cases within intermediate to higher risk mutations were highly associated with surgical intervention, resulting in a 77.5% ROM when including both cancer and noninvasive follicular thyroid neoplasia with papillary-like features (cancer+NIFTP) and 68% malignant diagnosis when excluding NIFTP. RAS-like alterations were most common (66%), exhibiting a 73.4% ROM and a 59% malignant diagnosis. Interestingly, this group included 24 encapsulated follicular variant papillary thyroid carcinomas (EFVPTCs), 1 infiltrative FVPTC, 9 follicular carcinomas, and 7 NIFTP. Additionally, three high-risk mutations and eight BRAF/V600E mutations had a 100% ROM, all diagnosed as classic-type papillary thyroid carcinoma (cPTC). Combined analysis of thyroid nodules from Bethesda III and IV categories revealed a 78.2% positive predictive value (PPV) and a 75.9% negative predictive value (NPV). CONCLUSION: ThyroSeq v3 effectively stratifies the ROM in indeterminate thyroid nodules based on specific genetic alterations, guiding appropriate surgical management. Notably, the BRAFV600E/high-risk group and RAS-like groups exhibited ROM of 100% and 77.5%, respectively, with promising predictive accuracy (PPV of 78.2% and NPV of 75.9%).

European experience with the Afirma Gene Expression Classifier for indeterminate thyroid nodules: A clinical utility study in the Netherlands.

BACKGROUND: The Gene Expression Classifier (GEC) and Genomic Sequencing Classifier (GSC) were developed to improve risk stratification of indeterminate nodules. Our aim was to assess the clinical utility in a European population with restrictive diagnostic workup. METHODS: Clinical utility of the GEC was assessed in a prospective multicenter cohort of 68 indeterminate nodules. Diagnostic surgical rates for Bethesda III and IV nodules were compared to a historical cohort of 171 indeterminate nodules. Samples were post hoc tested with the GSC. RESULTS: The GEC classified 26% as benign. Surgical rates between the prospective and historical cohort did not differ (72.1% vs. 76.6%). The GSC classified 59% as benign, but misclassified six malignant lesions as benign. CONCLUSION: Implementation of GEC in management of indeterminate nodules in a European country with restrictive diagnostic workup is currently not supported, especially in oncocytic nodules. Prospective studies with the GSC in European countries are needed to determine the clinical utility.

PET/CT May Assist in Avoiding Pointless Thyroidectomy in Indeterminate Thyroid Nodules: A Narrative Review.

Indeterminate thyroid nodules (ITN) are commonly encountered among the general population, with a malignancy rate of 10 to 40%. However, many patients may be overtreated with futile surgery for benign ITN. To avoid unnecessary surgery, PET/CT scan is a possible alternative to help differentiate between benign and malignant ITN. In this narrative review, the major results and limitations of the most recent studies on PET/CT efficacy (from PET/CT visual assessment to quantitative PET parameters and recent radiomic features analysis) and on cost-effectiveness (compared to other alternatives (such as surgery)) are presented. PET/CT can reduce futile surgery with visual assessment (around 40%; if ITN ≥ 10 mm). Moreover, PET/CT conventional parameters and radiomic features extracted from PET/CT imaging can be associated together in a predictive model to rule out malignancy in ITN, with a high NPV (96%) when certain criteria are met. Even though promising results were obtained in these recent PET/CT studies, further studies are needed to enable PET/CT to become the definitive diagnostic tool once a thyroid nodule is identified as indeterminate.

Comparison of S-Detect and thyroid imaging reporting and data system classifications in the diagnosis of cytologically indeterminate thyroid nodules.

Purpose: The aim of this study was to investigate the value of S-Detect for predicting the malignant risk of cytologically indeterminate thyroid nodules (CITNs). Methods: The preoperative prediction of 159 CITNs (Bethesda III, IV and V) were performed using S-Detect, Thyroid Imaging Reporting and Data System of American College of Radiology (ACR TI-RADS) and Chinese TI-RADS (C-TIRADS). First, Linear-by-Linear Association test and chi-square test were used to analyze the malignant risk of CITNs. McNemar's test and receiver operating characteristic curve were used to compare the diagnostic efficacy of S-Detect and the two TI-RADS classifications for CITNs. In addition, the McNemar's test was used to compare the diagnostic accuracy of the above three methods for different pathological types of nodules. Results: The maximum diameter of the benign nodules was significantly larger than that of malignant nodules [0.88(0.57-1.42) vs 0.57(0.46-0.81), P=0.002]. The risk of malignant CITNs in Bethesda system and the two TI-RADS classifications increased with grade (all P for trend<0.001). In all the enrolled CITNs, the diagnostic results of S-Detect were significantly different from those of ACR TI-RADS and C-TIRADS, respectively (P=0.021 and P=0.007). The sensitivity and accuracy of S-Detect [95.9%(90.1%-98.5%) and 88.1%(81.7%-92.5%)] were higher than those of ACR TI-RADS [87.6%(80.1%-92.7%) and 81.8%(74.7%-87.3%)] (P=0.006 and P=0.021) and C-TIRADS [84.3%(76.3%-90.0%) and 78.6%(71.3%-84.5%)] (P=0.001 and P=0.001). Moreover, the negative predictive value and the area under curve value of S-Detect [82.8% (63.5%-93.5%) and 0.795%(0.724%-0.855%)] was higher than that of C-TIRADS [54.8%(38.8%-69.8%) and 0.724%(0.648%-0.792%] (P=0.024 and P=0.035). However, the specificity and positive predictive value of S-Detect were similar to those of ACR TI-RADS (P=1.000 and P=0.154) and C-TIRADS (P=1.000 and P=0.072). There was no significant difference in all the evaluated indicators between ACR TI-RADS and C-TIRADS (all P>0.05). The diagnostic accuracy of S-Detect (97.4%) for papillary thyroid carcinoma (PTC) was higher than that of ACR TI-RADS (90.4%) and C-TIRADS (87.8%) (P=0.021 and P=0.003). Conclusion: The diagnostic performance of S-Detect in differentiating CITNs was similar to ACR TI-RADS and superior to C-TIRADS, especially for PTC.

Real-World Performance of the Afirma Genomic Sequencing Classifier (GSC)-A Meta-analysis.

CONTEXT: The Afirma® GSC aids in risk stratifying indeterminate thyroid nodule cytology (ITN). The 2018 GSC validation study (VS) reported a sensitivity (SN) of 91%, specificity (SP) of 68%, positive predictive value (PPV) of 47%, and negative predictive value (NPV) of 96%. Since then, 13 independent real-world (RW) postvalidation studies have been published. OBJECTIVE: This study's objective is to compare the RW GSC performance to the VS metrics. METHODS: Rules and assumptions applying to this analysis include: (1) At least 1 patient with molecular benign results must have surgery for that study to be included in SN, SP, and NPV analyses. (2) Molecular benign results without surgical histology are considered true negatives (TN) (as are molecular benign results with benign surgical histology). (3) Unoperated patients with suspicious results are either excluded from analysis (observed PPV [oPPV] and observed SP [oSP]) or assumed histology negatives (false positives; conservative PPV [cPPV] and conservative SP [cSP]) 4. Noninvasive follicular thyroid neoplasm with papillary-like nuclear features is considered malignant. RESULTS: In RW studies, the GSC demonstrates a SN, oSP, oPPV, and NPV of 97%, 88%, 65%, 99% respectively, and conservative RW performance showed cSP of 80% and cPPV of 49%, all significantly higher than the VS except for SN and cPPV. There was also a higher benign call rate (BCR) of 67% in RW studies compared to 54% in the VS (P < 0.05). CONCLUSION: RW data for the Afirma GSC demonstrates significantly better oSP and oPPV performance than the VS, indicating an increased yield of cancers for resected GSC suspicious nodules. The higher BCR likely increases the overall rate of clinical observation in lieu of surgery.

Stratifying indeterminate cytology thyroid nodules by combining Thyroid Imaging Reporting and Data Systems (TI-RADS) and The Bethesda System for Reporting Thyroid Cytopathology (TBSRTC)

Objective@#To determine the risk of malignancy of Bethesda System for Reporting Thyroid Cytopathology (TBSRTC) indeterminate Thyroid Nodules (Bethesda III, IV and V) by combining cytologic (TSBRTC) and Thyroid Imaging Reporting and Data Systems (TI-RADS) ultrasonographic features based on final histopathology.@*Methods@#Design: Retrospective review of records. Setting: Tertiary Private Training Hospital. Participants: 551 records. @*Results@#Among 81 eligible participants, 59 out of 84 nodules (70.24%) wer malignant on histopathology. The malignancy risk of Bethesda classification was 60.87% (28 out of 46) for Bethesda III, 57.14% (8 out of 14) for Bethesda IV and 95.83% for Bethesda V. The malignancy risk for TI-RADS categories was 0 % (0/1) for TI-RADS 2, 50% (10 out of 20) for TI-RADS 3, 71.05 % for TI-RADS 4 and 91.67 % for TI-RADS 5. The highest risk of malignancy (100%) was associated with [Bethesda IV/TI-RADS 1, 2, and 3], [Bethesda V/TI-RADS 1, 2 and 3 [Bethesda IV and V/TI-RADS 1, 2 and 3] and [Bethesda IV/TI-RADS 5]. The lowest risk of malignancy (33.33%) was associated with [Bethesda III/TI-RADS1, 2 and 3]. A high Bethesda classification (Bethesda V) was almost 5x more likely to have a malignant anatomorphology compared with Bethesda III (p = .05) while a TI-RADS 4 or 5 category was almost 5x more likely to have a malignant anatomorphology compared to TI-RADS 1, 2 or 3 (p = .026).@*Conclusion@#This study showed that TI-RADS scoring is a sensitive diagnostic classification in recognizing patients with thyroid cancer and combining Bethesda classification and TI-RADS scoring increases the sensitivity in the diagnosis of malignant thyroid nodules. A higher likelihood of malignancy is associated with higher Bethesda classification and TI-RADS scoring.

Cost-effectiveness analysis of molecular testing for cytologically indeterminate thyroid nodules.

BACKGROUND: Thyroid nodules affect up to 65% of the population. Although fine needle aspirate (FNA) cytology is the gold standard for diagnosis, 15-30% of results are indeterminate. Molecular testing may aid in the diagnosis of nodules and potentially reduce unnecessary surgery. However, these tests are associated with significant costs. The objective of this study was to evaluate the cost-effectiveness of Afirma, a commercially available molecular test, in cytologically indeterminate thyroid nodules. METHODS: The base case was a solitary thyroid nodule with no additional high-risk features and an indeterminate FNA. Decision tree analysis was performed from the single payer perspective with a 1-year time horizon. Costing data were collected through micro-costing methodology. A probabilistic sensitivity analysis was performed. The primary outcome was the incremental cost effectiveness ratio (ICER) of cost per thyroid surgery avoided. RESULTS: Over 1 year, mean cost estimates were $8176.28 with 0.58 effectiveness for the molecular testing strategy and $6016.83 with 0.07 effectiveness for current standard management. The ICER was $4234.22 per surgery avoided. At a willingness-to-pay (WTP) threshold of $5000 per surgery avoided, molecular testing is cost-effective with 63% certainty. CONCLUSION: This cost-effectiveness analysis suggests utilizing Afirma for indeterminate solitary thyroid nodules is a cost-effective strategy for avoiding unnecessary thyroid surgery. With a $5000 WTP threshold, molecular testing has a 63% chance of being the more cost-effective strategy. The cost effectiveness varies based on the cost of the molecular test and the value of Afirma for patients with indeterminate thyroid nodules depends on the WTP threshold to avoid unnecessary thyroid surgery.

Clinical decision support analysis of a microRNA-based thyroid molecular classifier: A real-world, prospective and multicentre validation study.

BACKGROUND: The diagnosis of cancer in Bethesda III/IV thyroid nodules is challenging as fine-needle aspiration (FNA) has limitations, and these cases usually require diagnostic surgery. As approximately 77% of these nodules are not malignant, a diagnostic test accurately identifying benign thyroid nodules can reduce "potentially unnecessary" surgery rates. We have previously reported the development and validation of a microRNA-based thyroid classifier (mir-THYpe) with high sensitivity and specificity, which could be performed directly from FNA smear slides. We sought to evaluate the performance of this test in real-world clinical routine to support clinical decisions and to reduce surgery rates. METHODS: We designed a real-world, prospective, multicentre study. Molecular tests were performed with FNA samples prepared at 128 cytopathology laboratories. Patients were followed-up from March 2018 until surgery or until March 2020 (patients with no indication for surgery). The final diagnosis of thyroid tissue samples was retrieved from postsurgical anatomopathological reports. FINDINGS: A total of 435 patients (440 nodules) classified as Bethesda III/IV were followed-up. The rate of avoided surgeries was 52·5% for all surgeries and 74·6% for "potentially unnecessary" surgeries. The test achieved 89·3% sensitivity, 81·65% specificity, 66·2% positive predictive value, and 95% negative predictive value. The test supported 92·3% of clinical decisions. INTERPRETATION: The reported data demonstrate that the use of the microRNA-based classifier in the real-world can reduce the rate of thyroid surgeries with robust performance and support clinical decision-making. FUNDING: The São Paulo Research-Foundation (FAPESP) and Onkos.

Machine Learning-Assisted Diagnostic System for Indeterminate Thyroid Nodules.

To develop an ultrasound-based machine learning classifier to diagnose benignity within indeterminate thyroid nodules (ITNs) by fine-needle aspiration, 180 patients with 194 ITNs (Bethesda classes III, IV and V) undergoing surgery over a 5-y study period were analyzed. The data set was randomly divided into training and testing data sets with 155 and 39 ITNs, respectively. All nodules were evaluated by ultrasound using the American College of Radiology Thyroid Imaging Reporting and Data System by manually scoring composition, echogenicity, shape, margin and echogenic foci. Nodule size, participant age and patient sex were recorded. A support vector machine (SVM) model with a cost-sensitive approach was developed using the aforementioned eight parameters with surgical histopathology as the reference standard. Surgical pathology determined 90 (46.4%) ITNs were malignant and 104 (53.6%) were benign. The SVM model classified 14 nodules as benign in the testing data set, of which 13 were correct (sensitivity = 93.8%, specificity = 56.5%). Considering malignancy prevalence by Bethesda group, the negative predictive values of this model for Bethesda III and IV categories were 93.9% and 93. 8%, respectively. The high negative predictive value of the SVM ultrasound-based model suggests a pathway by which surgical excision of Bethesda III and IV ITNs classified as benign may be avoided.

A machine-learning algorithm for distinguishing malignant from benign indeterminate thyroid nodules using ultrasound radiomic features.

Background: Ultrasound (US)-guided fine needle aspiration (FNA) cytology is the gold standard for the evaluation of thyroid nodules. However, up to 30% of FNA results are indeterminate, requiring further testing. In this study, we present a machine-learning analysis of indeterminate thyroid nodules on ultrasound with the aim to improve cancer diagnosis. Methods: Ultrasound images were collected from two institutions and labeled according to their FNA (F) and surgical pathology (S) diagnoses [malignant (M), benign (B), and indeterminate (I)]. Subgroup breakdown (FS) included: 90 BB, 83 IB, 70 MM, and 59 IM thyroid nodules. Margins of thyroid nodules were manually annotated, and computerized radiomic texture analysis was conducted within tumor contours. Initial investigation was conducted using five-fold cross-validation paradigm with a two-class Bayesian artificial neural networks classifier, including stepwise feature selection. Testing was conducted on an independent set and compared with a commercial molecular testing platform. Performance was evaluated using receiver operating characteristic analysis in the task of distinguishing between malignant and benign nodules. Results: About 1052 ultrasound images from 302 thyroid nodules were used for radiomic feature extraction and analysis. On the training/validation set comprising 263 nodules, five-fold cross-validation yielded area under curves (AUCs) of 0.75 [Standard Error (SE) = 0.04; P < 0.001 ] and 0.67 (SE = 0.05; P = 0.0012 ) for the classification tasks of MM versus BB, and IM versus IB, respectively. On an independent test set of 19 IM/IB cases, the algorithm for distinguishing indeterminate nodules yielded an AUC value of 0.88 (SE = 0.09; P < 0.001 ), which was higher than the AUC of a commercially available molecular testing platform (AUC = 0.81, SE = 0.11; P < 0.005 ). Conclusion: Machine learning of computer-extracted texture features on gray-scale ultrasound images showed promising results classifying indeterminate thyroid nodules according to their surgical pathology.

The role of thyroid sonographic malignancy risk features when the fine needle aspiration biopsy result is indeterminate.

INTRODUCTION: Although the role of the thyroid ultrasound is well established in the initial thyroid nodule work up, it is still equivocal whether the thyroid ultrasound pattern could have an impact on refining malignancy risk after an indeterminate cytopathology result. We aim to assess the possible supportive role of the thyroid nodule ultrasound malignancy risk features listed in the Polish guidelines when a biopsy result is indeterminate. MATERIAL AND METHODS: We retrospectively reviewed thyroid ultrasound scans from 175 adult patients with thyroid nodules and indeterminate cytopathology results, who underwent thyroid surgery. Sonographic malignancy risk features were reported in accordance with the guidelines of the Polish National Societies Diagnostics and Treatment of Thyroid Carcinoma and included the following: solid structure, hypoechogenicity, microcalcifications, taller than wide shape, irregular margins, features of extrathyroidal expansion, suspicious cervical lymph nodes. RESULTS: The malignancy risk in relevant cytological categories, estimated on the basis of histological verification, was 10.9% for Bethesda III category, 12.1% for Bethesda IV, and 71.4% for Bethesda V. The predominant type of thyroid malignancy was papillary thyroid carcinoma (79%). Thyroid nodules sonographic malignancy risk features provided high specificity but low sensitivity in selected groups of indeterminate thyroid nodules. Microcalcifications was the only characteristic that solely had a clinically relevant positive likelihood ratio (> 10) to suggest malignancy in the analysed cohort, but it was not observed in thyroid nodules eventually verified as follicular thyroid carcinoma. An accumulation of more than one sonographic risk feature yielded significant increase in malignancy risk only in Bethesda V category thyroid nodules. CONCLUSIONS: The impact of sonographic malignancy risk features on refining post-biopsy probability of thyroid cancer in thyroid nodule with indeterminate cytopathology, may be inadequate to sort patients (without any doubt) between those who require thyroid surgery and those who only require surveillance. There is an urgent need to search for new tools in the diagnostics of indeterminate thyroid nodules and to standardize thyroid ultrasound reports.

Risk of Complications in Patients Undergoing Completion Thyroidectomy after Hemithyroidectomy for Thyroid Nodule with Indeterminate Cytology: An Italian Multicentre Retrospective Study.

There is still controversy as to whether patients undergoing a completion thyroidectomy after a hemithyroidectomy for a thyroid nodule with an indeterminate cytology have a comparable, increased or decreased risk of complications compared to those submitted to primary thyroid surgery. The main aim of this study was to investigate this topic. Patients undergoing a thyroidectomy for thyroid nodular disease with an indeterminate cytology in four high-volume thyroid surgery centres in Italy, between January 2017 and December 2020, were retrospectively analysed. Based on the surgical procedure performed, four groups were identified: the TT Group (total thyroidectomy), HT Group (hemithyroidectomy), CT Group (completion thyroidectomy) and HT + CT Group (hemithyroidectomy with subsequent completion thyroidectomy). A total of 751 patients were included. As for the initial surgery, 506 (67.38%) patients underwent a total thyroidectomy and 245 (32.62%) a hemithyroidectomy. Among all patients submitted to a hemithyroidectomy, 66 (26.94%) were subsequently submitted to a completion thyroidectomy. No statistically significant difference was found in terms of complications comparing both the TT Group with the HT + CT Group and the HT Group with the CT Group. The risk of complications in patients undergoing a completion thyroidectomy after a hemithyroidectomy for a thyroid nodule with an indeterminate cytology was comparable to that of patients submitted to primary thyroid surgery (both a total thyroidectomy and hemithyroidectomy).

FDG-PET/CT in indeterminate thyroid nodules: cost-utility analysis alongside a randomised controlled trial.

PURPOSE: To evaluate cost-effectiveness of an [18F]FDG-PET/CT-driven diagnostic workup as compared to diagnostic surgery, for thyroid nodules with Bethesda III/IV cytology. [18F]FDG-PET/CT avoids 40% of futile diagnostic surgeries for benign Bethesda III/IV nodules. METHODS: Lifelong societal costs and quality-adjusted life years (QALYs) were assessed for 132 patients participating in a randomised controlled multicentre trial comparing [18F]FDG-PET/CT to diagnostic surgery. The observed 1-year trial results were extrapolated using a Markov model. The probability of cost-effectiveness was estimated using cost-effectiveness acceptability curves, taking uncertainty about sampling, imputation, and parameters into account. RESULTS: The observed 1-year cost difference of [18F]FDG-PET/CT as compared to diagnostic surgery was - €1000 (95% CI: - €2100 to €0) for thyroid nodule-related care (p = 0.06). From the broader societal perspective, the 1-year difference in total societal costs was - €4500 (- €9200 to €150) (p = 0.06). Over the modelled lifelong period, the cost difference was - €9900 (- €23,100 to €3200) (p = 0.14). The difference in QALYs was 0.019 (- 0.045 to 0.083) at 1 year (p = 0.57) and 0.402 (- 0.581 to 1.385) over the lifelong period (p = 0.42). For a willingness to pay of €50,000 per QALY, an [18F]FDG-PET/CT-driven work-up was the cost-effective strategy with 84% certainty. CONCLUSION: Following the observed reduction in diagnostic surgery, an [18F]FDG-PET/CT-driven diagnostic workup reduced the 1-year thyroid nodule-related and societal costs while sustaining quality of life. It is very likely cost-effective as compared to diagnostic surgery for Bethesda III/IV nodules. TRIAL REGISTRATION NUMBER: This trial is registered with ClinicalTrials.gov: NCT02208544 (5 August 2014), https://clinicaltrials.gov/ct2/show/NCT02208544 .

Serum TSH as a predictor of malignancy in indeterminate thyroid nodules.

INTRODUCTION: Thyroid nodules are lesions that are radiologically distinct from the thyroid parenchyma. Cervical ultrasound diagnoses 19-67% of nodules and is crucial in identifying those that lack cytological characterisation. Approximately 25% of biopsies reveal an indeterminate cytological result (Bethesda III), in which the risk of malignancy is variable (5-15%). The clinical importance of the diagnostic strategy used for thyroid nodules results from the need to exclude malignancy. The aim of this study was to evaluate the usefulness of serum thyroid-stimulating hormone (TSH) levels as a predictor of malignancy in cytologically indeterminate thyroid nodules. METHODS: Our retrospective study included 40 patients with cytologically indeterminate thyroid nodules seen in our hospital between January 2013 and December 2017. Clinical parameters were reviewed, including age, gender, serum TSH levels, family history of thyroid carcinoma, radiation exposure and some sonographic features of the nodules. Statistical analysis was performed using SPSS. Statistical significance was defined as p<0.05. RESULTS: Female gender was predominant (85%) and the mean (SD) age was 53.3 (15) years. Thyroid carcinoma was confirmed in 28% of patients. Median TSH levels were higher in patients with malignant (2.73µIU/ml) compared with benign (1.56µIU/ml) nodules (p<0.05). We demonstrated an increased risk of malignancy in patients with TSH levels of 2.68µIU/ml or above (p<0.05). CONCLUSION: Higher serum TSH levels are associated with an increased risk of thyroid carcinoma in cytologically indeterminate nodules. TSH can become a fundamental diagnostic tool in stratifying the risk of malignancy and assist in diagnostic and therapeutic approaches to these nodules.

Risk stratification of indeterminate thyroid nodules using ultrasound and machine learning algorithms.

BACKGROUND: Indeterminate thyroid nodules (Bethesda III) are challenging to characterize without diagnostic surgery. Auxiliary strategies including molecular analysis, machine learning models, and ultrasound grading with Thyroid Imaging, Reporting and Data System (TI-RADS) can help to triage accordingly, but further refinement is needed to prevent unnecessary surgeries and increase positive predictive values. DESIGN: Retrospective review of 88 patients with Bethesda III nodules who had diagnostic surgery with final pathological diagnosis. MEASUREMENTS: Each nodule was retrospectively scored through TI-RADS. Two deep learning models were tested, one previously developed and trained on another data set, mainly containing determinate cases and then validated on our data set while the other one trained and tested on our data set (indeterminate cases). RESULTS: The mean TI-RADS score was 3 for benign and 4 for malignant nodules (p = .0022). Radiological high risk (TI-RADS 4,5) and low risk (TI-RADS 2,3) categories were established. The PPV for the high radiological risk category in those with >10 mm nodules was 85% (CI: 70%-93%). The NPV for low radiological risk in patients >60 years (mean age was 100% (CI: 83%-100%). The area under the curve (AUC) value of our novel classifier was 0.75 (CI: 0.62-0.84) and differed significantly from the chance-level (p < .00001). CONCLUSIONS: Novel radiomic and radiologic strategies can be employed to assist with preoperative diagnosis of indeterminate thyroid nodules.

Risk Stratifying Indeterminate Thyroid Nodules With Machine Learning.

BACKGROUND: Up to 30% of thyroid nodules are classified as indeterminate after fine needle aspiration biopsy. These indeterminate thyroid nodules (ITNs) require surgical pathology for definitive diagnosis. Molecular testing provides additional pre-operative cancer risk stratification but adds expense and invasive testing. The purpose of this study is to utilize a machine learning (ML) algorithm to predict malignancy of ITNs using data available from less invasive tests. MATERIALS AND METHODS: We conducted a retrospective study using medical records from one academic and one community center. Thyroid nodules with an indeterminate diagnosis on fine needle aspiration biopsy and completed diagnostic pathology were included. Linear, non-linear, and non-linear-ensemble ML methods were tested for accuracy when predicting malignancy using 10-fold cross-validation. Classifiers were evaluated using area under the receiver operating characteristics curve (AUROC). RESULTS: A total of 355 nodules met inclusion criteria. Of these, 171 (48.2%) were diagnosed with cancer. A Random Forest classifier performed the best, producing an accuracy of 79.1%, a sensitivity of 75.5%, specificity of 82.4%, positive predicative value of 80.3%, negative predictive value of 79.0%, and an AUROC of 0.859. CONCLUSIONS: ML methods accurately risk stratify ITNs using data gathered from existing, non-invasive, and inexpensive diagnostic tests. Applying an ML model with existing data can become a cost-effective alternative to molecular testing. Future studies will prospectively evaluate the performance of this ML approach when combined with expert judgment.

Radiomics analysis improves 18FDG PET/CT-based risk stratification of cytologically indeterminate thyroid nodules.

PURPOSE: As ~25% of cytologically indeterminate thyroid nodules harbour malignancy, diagnostic lobectomy is still performed in many cases. 18FDG PET/CT rules out malignancy in visually negative nodules; however, none of the currently available interpretation criteria differentiates malignant from benign 18FDG-avid nodules. We evaluated the ability of PET metrics and radiomics features (RFs) to predict final diagnosis of 18FDG-avid cytologically indeterminate thyroid nodules. METHODS: Seventy-eight patients were retrospectively included. After volumetric segmentation of each thyroid lesion, 4 PET metrics and 107 RFs were extracted. A logistic regression was performed including thyroid stimulating hormone, PET metrics, and RFs to assess their predictive performance. A linear combination of the resulting parameters generated a radiomics score (RS) that was matched with cytology classes (Bethesda III and IV) and compared with final diagnosis. RESULTS: Two RFs (shape_Sphericity and glcm_Autocorrelation) differentiated malignant from benign lesions. A predictive model integrating RS and cytology classes effectively stratified the risk of malignancy. The prevalence of thyroid cancer increased from 5 to 37% and 79% in accordance with the number (score 0, 1 or 2, respectively) of positive biomarkers. CONCLUSIONS: Our multiparametric model may be useful for reducing the number of diagnostic lobectomies with advantages in terms of costs and quality of life for patients.

Evaluation of LMR, NLR and PLR as predictors of malignancy in indeterminate thyroid nodules.

OBJECTIVE: Thyroid nodules with indeterminate cytology represent 20% of all thyroid nodules. Inflammation plays an important role in cancer. Lymphocyte-to-monocyte ratio (LMR), neutrophil-to-lymphocyte ratio (NLR) and platelet-to-lymphocyte ratio (PLR) are independent prognostic scores in numerous cancers, although no study has documented their role in cytology indeterminate nodules. The aim of this study is to evaluate the role of LMR, NLR and PLR values as predictors of malignancy in patients with cytology indeterminate nodules. METHODS: This retrospective study analysed data from 298 patients with indeterminate thyroid nodule. Anatomopathological and haematological data were analysed, dividing the population into two groups. LMR, NLR and PLR values were determined using ROC curve and data were analysed using independent samples t-test, test of proportions, Fisher's exact test and univariate and multivariate logistic regression. RESULTS: We found that a baseline LMR value ≥ 4.09 was indicative of benignity of indeterminate nodule. The probability of malignancy in patients with LMR < 4.09 was 26 times higher than patients with a LMR value ≥ 4.09. CONCLUSIONS: This study showed that only LMR has shown a concrete probability to find a thyroid cancer in patients with indeterminate nodules. Further studies are necessary to implement tailored treatment.

Developing a tool that could reliably refute total thyroidectomy for solitary Bethesda IV thyroid nodules.

PURPOSE: To assess the reliability of a simple, accessible, cost-effective rule-out tool, for use in triaging patients with Bethesda IV nodules to appropriate surgery. METHODS: The diagnostic tool was assembled by combining the negativity for suspicious ultrasound features (irregular margins, microcalcification, and a taller-than-wide orientation), and mutational marker negativity (BRAF and NRAS). The tool, (US-/mutation-), was tested on 167 patients with solitary Bethesda IV nodules. The primary outcome was its negative predictive value (NPV) for lesions requiring total thyroidectomy (TT). The impact of mutational marker negativity, as part of the tool, was evaluated by comparing the NPV of (US-/mutation-) to that of (US-/mutation+). RESULTS: 10 out of 167 lesions were positive for a mutational marker. These underwent TT, and only 2/10 (20%) were benign, on final histology. In 6/8 malignant lesions, TT was concordant with current clinical guidelines. 157 patients comprised the negative study cohort, for both mutational markers and suspicious US features. These underwent thyroid lobectomy, and 17 cases resulted in malignancy, only 8 of which required completion thyroidectomy. Accordingly, the NPV of (US-/mutation-) for malignancy was 89% (140/157), and 95% (149/157) for malignancy requiring TT. However, the NPV of (US-/mutation+) was 20% for malignancy, and 40% for malignancy requiring TT. These differences were statistically significant (89% vs. 20%; p < 0.0001, and 95% vs. 40%; p < 0.0001). CONCLUSION: US-/mutation- is a reliable rule-out tool, with sufficient diagnostic accuracy to spare patients, with Bethesda IV nodules, an overly radical TT.