Identification method of thyroid nodule ultrasonography based on self-supervised learning dual-branch attention learning framework

Thyroid ultrasound is a widely used diagnostic technique for thyroid nodules in clinical practice. However, due to the characteristics of ultrasonic imaging, such as low image contrast, high noise levels, and heterogeneous features, detecting and identifying nodules remains challenging. In addition, high-quality labeled medical imaging datasets are rare, and thyroid ultrasound images are no exception, posing a significant challenge for machine learning applications in medical image analysis. In this study, we propose a Dual-branch Attention Learning (DBAL) convolutional neural network framework to enhance thyroid nodule detection by capturing contextual information. Leveraging jigsaw puzzles as a pretext task during network training, we improve the network's generalization ability with limited data. Our framework effectively captures intrinsic features in a global-to-local manner. Experimental results involve self-supervised pre-training on unlabeled ultrasound images and fine-tuning using 1216 clinical ultrasound images from a collaborating hospital. DBAL achieves accurate discrimination of thyroid nodules, with a 88.5% correct diagnosis rate for malignant and benign nodules and a 93.7% area under the ROC curve. This novel approach demonstrates promising potential in clinical applications for its accuracy and efficiency.

Localization and Risk Stratification of Thyroid Nodules in Ultrasound Images Through Deep Learning

OBJECTIVE

Deep learning algorithms have commonly been used for the differential diagnosis between benign and malignant thyroid nodules. The aim of the study described here was to develop an integrated system that combines a deep learning model and a clinical standard Thyroid Imaging Reporting and Data System (TI-RADS) for the simultaneous segmentation and risk stratification of thyroid nodules.

METHODS

Three hundred four ultrasound images from two independent sites with TI-RADS 4 thyroid nodules were collected. The edge connection and Criminisi algorithm were used to remove manually induced markers in ultrasound images. An integrated system based on TI-RADS and a mask region-based convolution neural network (Mask R-CNN) was proposed to stratify subclasses of TI-RADS 4 thyroid nodules and to segment thyroid nodules in the ultrasound images. Accuracy and the precision-recall curve were used to evaluate stratification performance, and the Dice similarity coefficient (DSC) between the segmentation of Mask R-CNN and the radiologist's contour was used to evaluate the segmentation performance of the model.

RESULTS

The combined approach could significantly enhance the performance of the proposed integrated system. Overall stratification accuracy of TI-RADS 4 thyroid nodules, mean average precision and mean DSC of the proposed model in the independent test set was 90.79%, 0.8579 and 0.83, respectively. Specifically, stratification accuracy values for TI-RADS 4a, 4b and 4c thyroid nodules were 95.83%, 84.21% and 77.78%, respectively.

CONCLUSION

An integrated system combining TI-RADS and a deep learning model was developed. The system can provide clinicians with not only diagnostic assistance from TI-RADS but also accurate segmentation of thyroid nodules, which improves the applicability of the system in clinical practice.

Comparison of Micro-flow Imaging and Contrast-Enhanced Ultrasound in Ultrasound-Guided Microwave Ablation of Benign Thyroid Nodules

OBJECTIVE

The study described here was aimed at ascertaining the utility of micro-flow imaging (MFI) during ultrasound (US)-guided microwave ablation (MWA) of thyroid nodules by contrasting its effectiveness with that of contrast-enhanced ultrasound (CEUS).

METHODS

Seventy-three patients with eighty-eight thyroid nodules who underwent US-guided MWA were included in our study from January 2020 to June 2023. Thirty-five patients underwent CEUS during the MWA process, and thirty-eight patients underwent MFI during the MWA process. We compared the two groups' baseline characteristics, tumor volume (V), volume reduction rate (VRR), complications and clinical characteristics.

RESULTS

Both groups exhibited similar outcomes with respect to V and VRR at 1, 3, 6, 12 and 18 mo after MWA (p > 0.05). Consistency was observed with respect to post-operative complications, supplementary ablation times and surgical duration (p > 0.05). It is worth noting that the MFI group had lower treatment costs compared with the CEUS group (11,337.64 ± 80.93 yuan for the MFI group versus 12,971.23 ± 254.89 yuan for the CEUS group, p < 0.05).

CONCLUSION

In the MWA procedure for thyroid nodules, MFI is similar to CEUS with respect to safety and efficacy. Simultaneously, it offers the advantage of reducing surgical expenses, which lessens the economic burden for patients.

Cost-Effectiveness of the ACR TIRADS Compared to the ATA 2015 Risk Stratification Systems in the Evaluation of Incidental Thyroid Nodules

RATIONALE AND OBJECTIVES

Thyroid nodules are a common incidental imaging finding and prone to overdiagnosis. Several risk stratification systems have been developed to reduce unnecessary work-up, with two of the most utilized including the American Thyroid Association 2015 (ATA2015) and the newer American College of Radiology Thyroid Imaging, Reporting and Data System (TIRADS) guidelines. The purpose of this study is to evaluate the cost-effectiveness of the ATA2015 versus the TIRADS guidelines in the management of incidental thyroid nodules.

METHODS

A cost-utility analysis was conducted using decision tree modeling, evaluating adult patients with incidental thyroid nodules < 4 cm. Model inputs were populated using published literature, observational data, and expert opinion. Single-payer perspective, Canadian dollar currency, five-year time horizon, willingness to pay (WTP) threshold of $50,000, and discount rate of 1.5% per annum were utilized. Scenario, deterministic and probabilistic sensitivity analyses were performed. The primary outcome was the incremental cost-effectiveness ratio (ICER) expressed as incremental cost per quality-adjusted life year (QALY) gained.

RESULTS

For the base case scenario, TIRADS dominated the ATA2015 strategy by a slim margin, producing 0.005 more QALYs at $25 less cost. Results were sensitive to the malignancy rate of biopsy and the utilities of a patient with a benign nodule/subclinical malignancy or under surveillance. Probabilistic sensitivity analysis showed that TIRADS was the more cost-effective option 79.7% of the time.

CONCLUSION

The TIRADS guidelines may be the more cost-effective strategy by a small margin compared to ATA2015 in most scenarios when used to risk stratify incidental thyroid nodules.

Fully-Automatic Detection and Diagnosis System for Thyroid Nodules Based on Ultrasound Video Sequences by Artificial Intelligence

Background

Interpretation of ultrasound findings of thyroid nodules is subjective and labor-intensive for radiologists. Artificial intelligence (AI) is a relatively objective and efficient technology. We aimed to establish a fully automatic detection and diagnosis system for thyroid nodules based on AI technology by analyzing ultrasound video sequences.

Patients and Methods

We prospectively acquired dynamic ultrasound videos of 1067 thyroid nodules (804 for training and 263 for validation) from December 2018 to January 2021. All the patients underwent hemithyroidectomy or total thyroidectomy. Dynamic ultrasound videos were used to develop an AI system consisting of two deep learning models that could automatically detect and diagnose thyroid nodules. Average precision (AP) was used to estimate the performance of the detection model. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of the diagnostic model.

Results

Location and shape were accurately detected with a high AP of 0.914 in the validation cohort. The AUC of the diagnostic model was 0.953 in the validation cohort. The sensitivity and specificity of junior and senior radiologists were 76.9% vs 78.3% and 68.4% vs 81.1%, respectively. The diagnostic performance of the AI diagnostic model was superior to that of junior radiologists (P = 0.016) and was not significantly different from that of senior radiologists (P = 0.281).

Conclusion

We established a fully automatic detection and diagnosis system for thyroid nodules based on ultrasound video using an AI approach that can be conveniently applied to optimize the management of patients with thyroid nodules.

Prevalence and risk factors of thyroid nodules in breast cancer women with different clinicopathological characteristics: a cross-sectional study

BACKGROUND

Association between breast cancer (BC) and thyroid nodules (TNs) is still unclear. This research was to estimate the prevalence and risk factors of TN in Chinese BC women at initial diagnosis.

METHODS

1731 Chinese early-stage BC women at initial diagnosis underwent thyroid ultrasound and 1:1 age-matched Chinese healthy women underwent health examination in corresponding period were enrolled for analysis.

RESULTS

Prevalence of TN and TI-RADS ≥ 4 TN in BC patients (56.27% and 9.76%) were higher than healthy people (46.04% and 5.49%), respectively, P < 0.001. Among BC patients, prevalence of TN and TI-RADS ≥ 4 TN in hormone receptor (HR)-positive patients (59.57% and 11.81%) were higher than HR-negative patients (48.77% and 5.10%), respectively, P < 0.001, while without difference between HR-negative patients and healthy people. After adjusting for age and BMI, HR-positive patients had higher risk of TN (OR = 1.546, 95%CI 1.251-1.910, P < 0.001) and TI-RADS ≥ 4 TN (OR = 3.024, 95%CI 1.943-4.708, P < 0.001) than HR-negative patients. Furthermore, the risk of TI-RADS ≥ 4 TN was higher in patients with estrogen receptor (ER) positive (OR = 2.933, 95%CI 1.902-4.524), progesterone receptor (PR) positive (OR = 1.973, 95%CI 1.378-2.826), Ki-67 < 20% (OR = 1.797, 95%CI 1.280-2.522), and tumor size < 2 cm (OR = 1.804, 95%CI 1.276-2.552), respectively, P < 0.001.

CONCLUSIONS

Prevalence of TN, especially TI-RADS ≥ 4 TN, in Chinese early-stage BC women was higher than healthy people. HR-positive patients had higher prevalence and risk of TN, while without difference between HR-negative patients and healthy people. The increased risk of TN was correlated with ER-positive, PR-positive, lower Ki-67 expression, and smaller tumor size.

Comparison of Cytological Adequacy between 23- and 25-Gauge in Ultrasound-Guided Fine-Needle Aspiration of Thyroid Nodules: A Single-Center Prospective Study

INTRODUCTION

Approximately 15% of fine-needle aspiration (FNA) of thyroid nodules are considered nondiagnostic. Several factors are potentially involved, including clinical and nodule features but also the gauge (G) of the needle used. However, few studies have compared the cytological adequacy obtained with different gauge needles and the data are controversial. We aimed to evaluate cytological adequacy results using 23- or 25-G needles.

METHODS

This study is an observational and prospective study of thyroid nodules submitted to ultrasound-guided FNA. The procedure was performed randomly using 23- or 25-G needles. The samples were reported by different cytopathologists who were blinded to the information of the gauge of the needle used. Statistical analysis was performed to compare cytological adequacy of FNA between the two groups.

RESULTS

A total of 177 thyroid nodules were included - 98 (55.4%) using 23-G and 79 (44.6%) using 25-G needles. The 23-G group presented a higher rate of cytological adequacy (69.4% [68/98] vs. 46.8% [37/79], p = 0.002). No differences were found between the two groups regarding patient or nodule characteristics. On logistic regression, 23-G needles correlated with better cytological adequacy (unadjusted OR 2.57 [95% CI: 1.39-4.77]), even after adjusting for nodule dimension, location, and type of cytology (slides +/- additional liquid-based cytology) (adjusted OR 2.44 [95% CI: 1.23-4.84]).

CONCLUSION

The gauge of the needle used was found to be an independent predictor of cytological adequacy, with 23-G needles providing more adequate samples. Further investigation is needed to confirm our results in order to stablish the optimal diagnosis technique.

Deep learning to assist composition classification and thyroid solid nodule diagnosis: a multicenter diagnostic study

OBJECTIVES

This study aimed to propose a deep learning (DL)-based framework for identifying the composition of thyroid nodules and assessing their malignancy risk.

METHODS

We conducted a retrospective multicenter study using ultrasound images from four hospitals. Convolutional neural network (CNN) models were constructed to classify ultrasound images of thyroid nodules into solid and non-solid, as well as benign and malignant. A total of 11,201 images of 6784 nodules were used for training, validation, and testing. The area under the receiver-operating characteristic curve (AUC) was employed as the primary evaluation index.

RESULTS

The models had AUCs higher than 0.91 in the benign and malignant grading of solid thyroid nodules, with the Inception-ResNet AUC being the highest at 0.94. In the test set, the best algorithm for identifying benign and malignant thyroid nodules had a sensitivity of 0.88, and a specificity of 0.86. In the human vs. DL test set, the best algorithm had a sensitivity of 0.93, and a specificity of 0.86. The Inception-ResNet model performed better than the senior physicians (p < 0.001). The sensitivity and specificity of the optimal model based on the external test set were 0.90 and 0.75, respectively.

CONCLUSIONS

This research demonstrates that CNNs can assist thyroid nodule diagnosis and reduce the rate of unnecessary fine-needle aspiration (FNA).

CLINICAL RELEVANCE STATEMENT

High-resolution ultrasound has led to increased detection of thyroid nodules. This results in unnecessary fine-needle aspiration and anxiety for patients whose nodules are benign. Deep learning can solve these problems to some extent.

KEY POINTS

• Thyroid solid nodules have a high probability of malignancy. • Our models can improve the differentiation between benign and malignant solid thyroid nodules. • The differential performance of one model was superior to that of senior radiologists. Applying this could reduce the rate of unnecessary fine-needle aspiration of solid thyroid nodules.

Hyperfunctioning papillary thyroid carcinoma - a case report and literature review

BACKGROUND

Malignant hyperfunctioning thyroid nodules are rare and more likely to occur in follicular cancer types rather than papillary variants. The authors present a case of a papillary thyroid carcinoma associated with a hyperfunctioning nodule.

METHODS

A single adult patient submitted to total thyroidectomy with the presence of thyroid carcinoma within hyperfunctioning nodules was selected. Additionally, brief literature was conducted.

RESULTS

An asymptomatic 58-year-old male was subjected to routine blood analysis and a TSH level of <0.003 mIU/L was found. Ultrasonography revealed a 21 mm solid, hypoechoic, and heterogenous nodule with microcalcifications in the right lobe. A fine needle aspiration guided by ultrasound resulted in a follicular lesion of undetermined significance. A 99mTc thyroid scintigram was followed and identified a right-sided hyperfunctioning nodule. Another cytology was performed and a papillary thyroid carcinoma was derived as a result. The patient underwent a total thyroidectomy. Postoperative histology confirmed the diagnosis and a tumor-free margin with no vascular or capsular invasions.

CONCLUSION

Hyperfunctioning malignant nodules are a rare association, although a careful approach should be led since major clinical implications arise. Selective fine needle aspiration in all suspicious ≥1 cm nodules should be considered.

Efficacy of HIFU for the treatment of benign thyroid nodules: a systematic review and meta-analysis

OBJECTIVE

Thyroid nodules are common and sometimes associated with cosmetic issues. Surgical treatment has several disadvantages, including visible scarring. High-intensity focused ultrasound (HIFU) is a recent noninvasive treatment for thyroid nodules. The present study aims to evaluate the effectiveness and safety of HIFU for the treatment of benign thyroid nodules.

METHODS

We searched PubMed, Embase, and Cochrane Library for studies evaluating the outcomes of HIFU for patients with benign thyroid nodules. We conducted a meta-analysis by using a random effects model and evaluated the volume reduction ratio, treatment success rate, and incidence of treatment-related complications.

RESULTS

Thirty-two studies were included in the systematic review. Only 14 studies were used in the meta-analysis because the other 18 involved data collected during overlapping periods. The average volume reduction ratios at 3, 6, and 12 months after treatment were 39.02% (95% CI: 27.57 to 50.47%, I2: 97.9%), 48.55% (95% CI: 35.53 to 61.57%, I2: 98.2%), and 55.02% (95% CI: 41.55 to 68.48%, I2: 99%), respectively. Regarding complications, the incidences of vocal cord paresis and Horner's syndrome after HIFU were 2.1% (95% CI: 0.2 to 4.1%, I2: 14.6%) and 0.7% (95% CI: 0 to 1.9%, I2: 0%), respectively.

CONCLUSIONS

HIFU is an effective and safe treatment option for patients with benign thyroid nodules. However, the effects of HIFU on nodules of large sizes and with different properties require further investigation. Additional studies, particularly randomized controlled trials involving long-term follow-up, are warranted.

CLINICAL RELEVANCE STATEMENT

Surgical treatment for thyroid nodules often results in permanent visible scars and is associated with a risk of bleeding, nerve injury, and hypothyroidism. High-intensity focused ultrasound may be an alternative for patients with benign thyroid nodules.

KEY POINTS

• The success rate of HIFU treatment for thyroid nodules is 75.8% at 6 months. Average volume reduction ratios are 48.55% and 55.02% at 6 and 12 months. • The incidence of complications such as vocal fold paresis, Horner's syndrome, recurrent laryngeal nerve palsy, hypothyroidism, and skin redness is low. • HIFU is both effective and safe as a treatment for benign thyroid nodules.

Validating the Modified McGill Thyroid Nodule Score for Assessment of Preoperative Risk of Pediatric Thyroid Malignancy

OBJECTIVE

The McGill Thyroid Nodule Score (MTNS) is a preoperative tool used to predict the risk for well-differentiated thyroid cancer in adults. It was developed by a multidisciplinary team using established evidence-based risk factors for thyroid cancer. The modified McGill Thyroid Nodule Score (mMTNS) was developed to predict malignancy risk in children. A pilot study suggested the mMTNS was able to assess malignancy risk in children with indeterminate cytology on fine needle aspiration (FNA). This study seeks to validate these findings.

METHODS

Retrospective chart review identified subjects who underwent FNA biopsy and subsequent resection. Each patient was assigned a score to compare to final pathology. Statistical analysis was performed with SPSS. All tests were 2-tailed and statistical significance defined p < 0.05. Logistic regression used to determine predictive values of scores.

RESULTS

46 patients ≤21 years of age underwent resection of a thyroid nodule. Female predominance of 85% (n = 39). 78% (n = 36) of patients had palpable nodule. 65% (n = 30) found to have benign pathology and 35% (n = 16) found to have malignancy. Malignant nodules associated with greater mean mMTNS compared to benign [13.63 vs 7.23]. An mMTNS greater >12 had sensitivity of 86.7%, specificity of 90.3%, positive predictive value of 81.3%, and negative predictive value of 93.3%.

CONCLUSION

Our data suggests the mMTNS continues to be a useful adjunct in predicting malignancy risk of pediatric thyroid nodules. An mMTNS >12 has a high risk for malignancy, which can aid in counseling and clinical decision making, particularly when there is indeterminate cytology on FNA.

LEVEL OF EVIDENCE

IV.

Chronic infectious unilateral giant thyroid cyst related to diabetes mellitus: A case report

BACKGROUND

Patients rarely develop complicated infections in thyroid cysts. Here, we describe a patient with chronic infected unilateral giant thyroid cyst related to diabetes mellitus (DM).

CASE SUMMARY

A 66-year-old male was admitted due to an evident neck lump for 5 d after approximately 40 years of gradually progressive neck mass and 7 years of DM. Doppler ultrasound and computed tomography scan showed a giant lump in the left thyroid gland lobe. He was diagnosed with a large thyroid nodule complicated by tracheal dislocation and had surgical indications. Surgical exploration revealed evident inflammatory edema and exudation between the left anterior neck muscles, the nodule and glandular tissue. Fortunately, inflammatory lesions did not affect major neck vessels. Finally, a left partial thyroidectomy was performed. Macroscopic observation showed that the cystic thyroid mass consisted of extensive cystic wall calcification and was rich in massive rough sand-like calculi content and purulent matter. Postoperative pathology confirmed benign thyroid cyst with chronic infection.

CONCLUSION

The progression of this chronic infectious unilateral giant thyroid cyst may have been related to DM, and identifying blood vessels involvement can prevent serious complications during operation.

Histopathology of telomerase reverse transcriptase promoter (TERT) mutated indeterminate thyroid nodules

Objective

The objective of this study was to analyze the risk of malignancy and the histopathology of telomerase reverse transcriptase promoter (TERT) mutated cytologically indeterminate thyroid nodules (ITN).

Methods

A PUBMED search of molecularly tested ITN was conducted and data on TERT mutated ITN with histopathology correlation were extracted.

Results

Twenty-six manuscripts (published between 2014 and 2022) reported on 77 TERT mutated ITN. Sixty-five nodules were malignant (84 %), with 16 (25 %) described with high-risk histopathology, 5 (8 %) described as low-risk, and most without any description. Isolated TERT mutations were malignant in 26/30 ITNs (87 %) with 9 (35 %) described as high risk and none described as low risk. TERT + RAS mutated ITNs were malignant in 29/34 ITNs (85 %) with 3 (10 %) described as high risk and 4 (14 %) described as low risk. Finally, all 5 TERT + BRAFV600E mutated nodules were malignant and 3/5 (60 %) were described as high risk.

Conclusion

TERT mutated ITNs have a high risk of malignancy (84 %), and the current data does not show a difference in malignancy rate between isolated TERT mutations and TERT + RAS co-mutated ITNs. When described, TERT + RAS co-mutated ITNs did not have a higher rate of high-risk histopathology as compared to isolated TERT mutated lesions. Most TERT mutated ITNs did not have a description of histopathology risk and the oncologic outcomes, including rate of recurrence, metastases, and disease specific survival, are unknown. Further data is needed to determine if TERT mutated ITNs should be subjected to aggressive initial treatment.

Malignancy risk stratification and subcategorization of K-TIRADS intermediate suspicion thyroid nodules: a retrospective multicenter study

PURPOSE

This study aimed to develop the ultrasonography (US) criteria for risk stratification of the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) 4 nodules, and to evaluate the diagnostic yield of a modified biopsy criterion in a multicenter cohort.

METHODS

In total, 1,542 K-TIRADS 4 nodules (≥1 cm) were included in the study. US criteria for the subcategorization of K-TIRADS 4 nodules were developed based on high-risk US features. The diagnostic yields and false referral rates of biopsy criterion 1 (size cut-off of 1 cm), biopsy criterion 2 (size cut-off of 1.5 cm), and modified biopsy criterion 3 (size cut-off of 1 cm for K-TIRADS 4B and 1.5 cm for K-TIRADS 4A) were evaluated.

RESULTS

The five high-risk US features (solid composition, marked hypoechogenicity, macrocalcification, punctate echogenic foci, and irregular margin) independently increased the malignancy risk of the K-TIRADS 4 nodules (P<0.001). The K-TIRADS 4 nodules could be subcategorized into higher- and lower-risk subcategories according to the number of high-risk US features: K-TIRADS 4B (≥2 US features) and K-TIRADS 4A (≤1 US feature). The modified biopsy criterion increased the diagnostic yield by 7.8% compared with criterion 2 and reduced the false referral rate by 15.3% compared with criterion 1 (P<0.001).

CONCLUSION

The K-TIRADS 4 nodules were subcategorized as K-TIRADS 4B and K-TIRADS 4A based on high-risk US features. The modified biopsy criterion 3 showed a similar diagnostic yield and reduced false referral rate compared to criterion 1.

Volume reduction rate of radiofrequency ablation in ≤ 2 cm Bethesda IV thyroid nodules

OBJECTIVE

This prospective observational study aimed to evaluate the efficacy of radiofrequency ablation (RFA) in treating ≤ 2 cm thyroid nodules with Bethesda IV cytology and C-TIRADS 4A categorization. Additionally, the factors influencing the completed absorption of ablation (CAA) were examined.

METHODS

A total of 62 cases with 62 nodules underwent ultrasound-guided RFA and were included in the study. The volume reduction rate (VRR), CAA, and incomplete absorption of ablation (IAA) were assessed at the 1st, 3rd, 6th, and subsequent 6-month follow-ups. Clinical and ultrasound features were compared between the CAA and IAA groups at the 12th month follow-up.

RESULTS

The average VRR at the 1st, 3rd, 6th, 12th month, and last follow-up were -88.6%, 16.0%, 59.7%, 82.0%, and 98.2%, respectively. More than half of the nodules achieved a 90% VRR after 1 year of RFA, with 88.7% demonstrating CAA at the end of the study (follow-up duration of 14 to 63 months). Nodules with grade 3 vascularity and those associated with chronic thyroiditis showed delayed CAA at the 12th month follow-up (p = 0.036 and 0.003, respectively).

CONCLUSION

RFA is an effective technique for treating ≤ 2 cm thyroid nodules with Bethesda IV cytology and C-TIRADS 4A categorization. Nodules with grade 3 blood supply and patients with chronic thyroiditis exhibited an impact on the completed absorption following RFA.

CLINICAL RELEVANCE STATEMENT

Our study has shown that radiofrequency ablation is an effective treatment for ≤ 2 cm thyroid nodules classified as Bethesda IV cytology. However, we identified that high vascularity of the nodule and chronic thyroiditis are adverse factors affecting the completed absorption of the ablation.

KEY POINTS

•Radiofrequency ablation (RFA) is an effective technique for treatment of ≤ 2 cm Bethesda IV category thyroid nodules. •Higher blood supply and chronic thyroiditis influence the completed absorption after RFA.

Surgical safety and effectiveness of bilateral axillo-breast approach robotic thyroidectomy: a systematic review and meta-analysis

OBJECTIVES

To assess the safety and effectiveness of bilateral axillo-breast approach robotic thyroidectomy in thyroid tumor.

METHODS

Bilateral axillo-breast approach robotic thyroidectomy and other approaches (open thyroidectomy, transoral robotic thyroidectomy, and bilateral axillo-breast approach endoscopic thyroidectomy) were compared in studies from 6 databases.

RESULTS

Twenty-two studies (8830 individuals) were included. Bilateral axillo-breast approach robotic thyroidectomy had longer operation time, greater cosmetic satisfaction, and reduced transient hypoparathyroidism than conventional open thyroidectomy. Compared to bilateral axillo-breast approach endoscopic thyroidectomy, bilateral axillo-breast approach robotic thyroidectomy had greater amount of drainage, lower chances of transient vocal cord palsy and permanent hypothyroidism, and better surgical completeness (postopertive thyroblobulin level and lymph node removal). Bilateral axillo-breast approach robotic thyroidectomy induced greater postoperative drainage and greater patient dissatisfaction than transoral robotic thyroidectomy.

CONCLUSION

Bilateral axillo-breast approach robotic thyroidectomy is inferior to transoral robotic thyroidectomy in drainage and cosmetic satisfaction but superior to bilateral axillo-breast approach endoscopic thyroidectomy in surgical performance. Its operation time is longer, but its cosmetic satisfaction is higher than open thyroidectomy.

Outcomes of cytologically indeterminate thyroid nodules managed with Genomic Sequencing Classifier

CONTEXT

Molecular testing can refine the risk of malignancy in thyroid nodules with indeterminate cytology to decrease unnecessary diagnostic surgery.

OBJECTIVE

This study was performed to evaluate the outcomes of cytologically indeterminate thyroid nodules managed with Afirma genomic sequencing classifier (GSC) testing.

DESIGN, SETTING, PATIENTS, AND INTERVENTION

Adult patients who underwent a biopsy at three major academic centers between July 2017 and June 2021 with Bethesda III or IV cytology were included. All patients had surgery or minimum follow-up of 1 year ultrasound surveillance.

MAIN OUTCOME MEASURES

The primary outcomes were the sensitivity, specificity, PPV, and NPV of GSC in Bethesda III and IV nodules.

RESULTS

The median nodule size of the 834 indeterminate nodules was 2.1 cm and the median follow-up was 23 months. GSC's sensitivity, specificity, PPV, and NPV across all institutions were 95%, 81%, 50%, and 99% for Bethesda III nodules and 94%, 82%, 65%, and 98% for Bethesda IV nodules, respectively. The overall false negative rate was 2%. The NPV of GSC in thyroid nodules with oncocytic predominance was 100% in Bethesda III nodules and 98% in Bethesda IV nodules. However, the PPV of oncocytic nodules was low (17% in Bethesda III nodules and 45% in Bethesda IV nodules). Only 22% of thyroid nodules with benign GSC results grew during surveillance.

CONCLUSIONS

GSC is a key tool for managing patients with indeterminate cytology, including the higher-risk Bethesda IV category. GSC benign thyroid nodules can be observed similarly to thyroid nodules with benign cytology.

Is the nodule location a predictive risk factor for cancer in AUS/FLUS thyroid nodules? A retrospective cohort study

BACKGROUND

Atypia of undetermined significance/follicular lesion of undetermined significance (AUS/FLUS) is a heterogeneous category of thyroid nodules with uncertain cytology and controversial management. This study aimed to assess the association between nodule location and malignancy risk and whether the location can be used as a predictive risk factor for cancer in AUS/FLUS nodules.

METHODS

A cohort of 102 patients (79 [77.5%] women, 23 [22.5%] men) was retrospectively analyzed. Only patients with a final histopathology of benign or well-differentiated thyroid cancer and an available nodule location were included. Sociodemographic, histopathological, and sonographic data were statistically evaluated and correlated.

RESULTS

Based on pathology findings, 54 (52.9%) and 48 (47.1%) nodules were benign and malignant, respectively. Most nodules were right-sided (54.9%). Considering the nodule location, 41.2% of nodules occupied the whole lobe, 20.6% only the lower pole, 15.7% only the upper pole, and 2.9% the isthmus. Cases with nodules occupying only the upper, middle, or lower pole showed significant associations with cancer risk (odds ratio, [95% confidence interval]: 2.6, [1.1-5.7]; 2.0, [1.0-4.7]; and 1.9, [1.0-3.9], respectively). Male sex and the presence of a peripheral halo were significantly associated with malignancy risk (3.3, [1.2-9.1], P = 0.014; and 2.7, [1.0-9.5], P = 0.049, respectively). Isthmic nodules had the highest malignancy level (66.7%).

CONCLUSIONS

Nodule location is a promising predictor of malignancy in AUS/FLUS nodules. Furthermore, isthmic nodules had the highest malignancy level, emphasizing the significance of careful evaluation of these nodules. Further large prospective studies are required to confirm these findings.

Prediction model based on MRI morphological features for distinguishing benign and malignant thyroid nodules

BACKGROUND

The low specificity of Thyroid Imaging Reporting and Data System (TI-RADS) for preoperative benign-malignant diagnosis leads to a large number of unnecessary biopsies. This study developed and validated a predictive model based on MRI morphological features to improve the specificity.

METHODS

A retrospective analysis was conducted on 825 thyroid nodules pathologically confirmed postoperatively. Univariate and multivariate logistic regression were used to obtain β coefficients, construct predictive models and nomogram incorporating MRI morphological features in the training cohort, and validated in the validation cohort. The discrimination, calibration, and decision curve analysis of the nomogram were performed. The diagnosis efficacy, area under the curve (AUC) and net reclassification index (NRI) were calculated and compared with TI-RADS.

RESULTS

572 thyroid nodules were included (training cohort: n = 397, validation cohort: n = 175). Age, low signal intensity on T2WI, restricted diffusion, reversed halo sign in delay phase, cystic degeneration and wash-out pattern were independent predictors of malignancy. The nomogram demonstrated good discrimination and calibration both in the training cohort (AUC = 0.972) and the validation cohort (AUC = 0.968). The accuracy, sensitivity, specificity, PPV, NPV and AUC of MRI-based prediction were 94.4%, 96.0%, 93.4%, 89.9%, 96.5% and 0.947, respectively. The MRI-based prediction model exhibited enhanced accuracy (NRI>0) in comparison to TI-RADSs.

CONCLUSIONS

The prediction model for diagnosis of benign and malignant thyroid nodules demonstrated a more notable diagnostic efficacy than TI-RADS. Compared with the TI-RADSs, predictive model had better specificity along with a high sensitivity and can reduce overdiagnosis and unnecessary biopsies.

Interobserver variability in thyroid ultrasound

PURPOSE

Ultrasound evaluation of thyroid nodules is the preferred technique, but it is dependent on operator interpretation, leading to inter-observer variability. The current study aimed to determine the inter-physician consensus on nodular characteristics, risk categorization in the classification systems, and the need for fine needle aspiration puncture.

METHODS

Four endocrinologists from the same center blindly evaluated 100 ultrasound images of thyroid nodules from 100 different patients. The following ultrasound features were evaluated: composition, echogenicity, margins, calcifications, and microcalcifications. Nodules were also classified according to ATA, EU-TIRADS, K-TIRADS, and ACR-TIRADS classifications. Krippendorff's alpha test was used to assess interobserver agreement.

RESULTS

The interobserver agreement for ultrasound features was: Krippendorff's coefficient 0.80 (0.71-0.89) for composition, 0.59 (0.47-0.72) for echogenicity, 0.73 (0.57-0.88) for margins, 0.55 (0.40-0.69) for calcifications, and 0.50 (0.34-0.67) for microcalcifications. The concordance for the classification systems was 0.7 (0.61-0.80) for ATA, 0.63 (0.54-0.73) for EU-TIRADS, 0.64 (0.55-0.73) for K-TIRADS, and 0.68 (0.60-0.77) for K-TIRADS. The concordance in the indication of fine needle aspiration puncture (FNA) was 0.86 (0.71-1), 0.80 (0.71-0.88), 0.77 0.67-0.87), and 0.73 (0.64-0.83) for systems previously described respectively.

CONCLUSIONS

Interobserver agreement was acceptable for the identification of nodules requiring cytologic study using various classification systems. However, limited concordance was observed in risk stratification and many ultrasonographic characteristics of the nodules.

A Narrative Review of the 2023 Korean Thyroid Association Management Guideline for Patients with Thyroid Nodules

The 2023 Korean Thyroid Association (KTA) Management Guideline for Patients with Thyroid Nodules constitute an update of the 2016 KTA guideline for thyroid nodules and cancers that focuses specifically on nodules. The 2023 guideline aim to offer updated guidance based on new evidence that reflects the changes in clinical practice since the 2016 KTA guideline. To update the 2023 guideline, a comprehensive literature search was conducted from January 2022 to May 2022. The literature search included studies, reviews, and other evidence involving human subjects that were published in English in MEDLINE (PubMed), Embase, and other relevant databases. Additional significant clinical trials and research studies published up to April 2023 were also reviewed. The limitations of the current evidence are discussed, and suggestions for areas in need of further research are identified. The purpose of this review is to provide a summary of the 2023 KTA guideline for the management of thyroid nodules released in May 2023 and to give a balanced insight with comparison of recent guidelines from other societies.

Molecular testing for thyroid nodules: Where are we now?

Approximately 25% of the fine needle aspiration samples (FNAB) of thyroid nodules are classified as "indeterminate samples", that means, Bethesda III and IV categories. Until the last decade, most of these cases underwent diagnostic surgery, although only a minority (13-34%) confirmed malignancy postoperatively. In view of this, with the objective of improving the preoperative diagnosis in these cases, the molecular tests emerged, which are validated from the diagnostic point of view, presenting good performance, with good diagnostic accuracy, being able to avoid diagnostic surgeries. With the advancement of knowledge of the role of each of the mutations and gene rearrangements in thyroid oncogenesis, molecular markers have left to play only a diagnostic role and have been gaining more and more space both in defining the prognostic role of the tumor, as well as in the indication of target therapy. Thus, the objective of this review is to show how to use the tool of molecular tests, now commercially available in the world, in the management of indeterminate cytological nodules, assessing the pre-test malignancy risk of the nodule, through clinical, ultrasonographic and cytological characteristics, and decide on the benefit of molecular testing for each patient. In addition, to discuss its new and promising prognostic and therapeutic role in thyroid cancer.

Novel and Advanced Ultrasound Techniques for Thyroid Thermal Ablation

Thyroid radiofrequency ablation and microwave ablation are widely adopted minimally invasive treatments for diverse thyroid conditions worldwide. Fundamental skills such as the trans-isthmic approach and the moving shot technique are crucial for performing thyroid ablation, and advanced techniques, including hydrodissection and vascular ablation, improve safety and efficacy and reduce complications. Given the learning curve associated with ultrasound-guided therapeutic procedures, operators need training and experience. While training models exist, limited attention has been given to ultrasound maneuvers in ablation needle manipulation. This article introduces two essential maneuvers, the zigzag moving technique and the alienate maneuver, while also reviewing the latest ultrasound techniques in thyroid ablation, contributing valuable insights into this evolving field.

US of thyroid nodules: can AI-assisted diagnostic system compete with fine needle aspiration?

OBJECTIVES

Artificial intelligence (AI) systems can diagnose thyroid nodules with similar or better performance than radiologists. Little is known about how this performance compares with that achieved through fine needle aspiration (FNA). This study aims to compare the diagnostic yields of FNA cytopathology alone and combined with BRAFV600E mutation analysis and an AI diagnostic system.

METHODS

The ultrasound images of 637 thyroid nodules were collected in three hospitals. The diagnostic efficacies of an AI diagnostic system, FNA-based cytopathology, and BRAFV600E mutation analysis were evaluated in terms of sensitivity, specificity, accuracy, and the κ coefficient with respect to the gold standard, defined by postsurgical pathology and consistent benign outcomes from two combined FNA and mutation analysis examinations performed with a half-year interval.

RESULTS

The malignancy threshold for the AI system was selected according to the Youden index from a retrospective cohort of 346 nodules and then applied to a prospective cohort of 291 nodules. The combination of FNA cytopathology according to the Bethesda criteria and BRAFV600E mutation analysis showed no significant difference from the AI system in terms of accuracy for either cohort in our multicenter study. In addition, for 45 included indeterminate Bethesda category III and IV nodules, the accuracy, sensitivity, and specificity of the AI system were 84.44%, 95.45%, and 73.91%, respectively.

CONCLUSIONS

The AI diagnostic system showed similar diagnostic performance to FNA cytopathology combined with BRAFV600E mutation analysis. Given its advantages in terms of operability, time efficiency, non-invasiveness, and the wide availability of ultrasonography, it provides a new alternative for thyroid nodule diagnosis.

CLINICAL RELEVANCE STATEMENT

Thyroid ultrasonic artificial intelligence shows statistically equivalent performance for thyroid nodule diagnosis to FNA cytopathology combined with BRAFV600E mutation analysis. It can be widely applied in hospitals and clinics to assist radiologists in thyroid nodule screening and is expected to reduce the need for relatively invasive FNA biopsies.

KEY POINTS

• In a retrospective cohort of 346 nodules, the evaluated artificial intelligence (AI) system did not significantly differ from fine needle aspiration (FNA) cytopathology alone and combined with gene mutation analysis in accuracy. • In a prospective multicenter cohort of 291 nodules, the accuracy of the AI diagnostic system was not significantly different from that of FNA cytopathology either alone or combined with gene mutation analysis. • For 45 indeterminate Bethesda category III and IV nodules, the AI system did not perform significantly differently from BRAFV600E mutation analysis.

Ultrasound microflow patterns help in distinguishing malignant from benign thyroid nodules

BACKGROUND

Vascular features are not commonly used to evaluate thyroid nodules by conventional ultrasound due to the low sensitivity. Superb Microvascular Imaging (SMI) is a new ultrasonic Doppler technology that specializes in depicting microvessels and low-speed flow. The objective of this study was to explore the value of microflow features on SMI in differentiating malignant from benign thyroid nodules.

METHODS

One hundred and seventy-seven adult patients with thyroid nodules in our center from October 2021 to June 2022 with available histopathological results were recruited, including 125 malignant nodules and 123 benign nodules. Preoperative ultrasound was performed using greyscale, Color Doppler Flow Imaging (CDFI), monochrome SMI (mSMI) and color SMI (cSMI). Vascular features such as flow richness, microflow distribution and microflow patterns of malignant thyroid nodules were compared with those of benign nodules.

RESULTS

Penetrating vessel ≥ 1 (82.4% in the malignant group vs. 30.9% in the benign group, P < 0.001), the crab claw-like pattern (64.0% vs. 10.6%, P < 0.001) and the root hair-like pattern (8.0% vs. 2.4%, P = 0.049) were common in malignant thyroid nodules, among which the crab claw-like pattern was an independent risk factor for malignant thyroid nodules. The wheel-like pattern (1.6% in the malignant group vs. 33.3% in the benign group, P < 0.001) and the arborescent pattern (0 vs. 19.5%, P < 0.001) were more likely to appear in benign nodules. The diagnostic specificities of the crab claw-like pattern and the root hair-like pattern for malignant thyroid nodules were 0.894, 0.976, and the positive predictive values were 0.860, 0.769. The diagnostic specificities of the wheel-like pattern and the arborescent pattern for benign thyroid nodules were 0.984, 1.000, and the positive predictive values were 0.953, 1.000.

CONCLUSIONS

The crab claw-like pattern and the root hair-like pattern were microflow characteristics of malignant thyroid nodules. The wheel-like pattern and the arborescent pattern could help exclude the diagnosis of thyroid cancer.

Comparison of artificial intelligence, elastic imaging, and the thyroid imaging reporting and data system in the differential diagnosis of suspicious nodules

Background

Ultrasound is widely used for detecting thyroid nodules in clinical practice. This retrospective study aimed to assess the diagnostic efficacy of the American College of Radiology Thyroid Imaging Reporting and Data System (ACR-TIRADS), S-Detect, and elastography of the carotid artery for suspicious thyroid nodules and to determine the complementary value of artificial intelligence and elastography.

Methods

Between January 2021 and November 2021, 101 consecutive patients with 138 thyroid nodules were enrolled in The First Hospital of China Medical University. All nodules were evaluated using ACR-TIRADS categories (TR), S-Detect, and elastography, and then the diagnostic performance of the different methods and the combined assessment were compared. The inclusion criteria were the following: (I) TR3, TR4, and TR5 nodules, which were defined as "suspicious nodules"; (II) patients who had surgical or cytopathological results after ultrasound examination; and (III) voluntary enrollment in this study. Meanwhile, the exclusion criteria were the following: (I) TR1 and TR2 nodules, (II) patients who had undergone fine-needle aspiration before ultrasound examination, and (III) inconclusive cytologic findings.

Results

A total of 71 patients (12 men and 59 women) with 94 suspicious thyroid nodules (42 benign nodules and 52 malignant nodules) were finally included in this study. S-Detect had a significantly better sensitivity than did ACR-TIRADS [S-Detect: 98.1%, 95% confidence interval (CI): 89.7-100.0%; ACR-TIRADS: 84.6%, 95% CI: 71.9-93.1%; P=0.036], but its specificity was much lower (S-Detect: 19.0%; 95% CI: 8.6-34.1%; ACR-TIRADS: 40.5%, 95% CI: 25.6-56.7%; P=0.032). The accuracy was not significantly different between S-Detect (62.8%; 95% CI: 52.2-72.5%) and ACR-TIRADS (64.9%; 95% CI: 54.4-74.5%) (P=0.761). The elasticity contrast index (ECI) was not definitively useful in identifying suspicious thyroid nodules (P=0.592). Compared with the use of ACR-TIRADS and S-Detect alone, the specificity (45.2%; 95% CI: 29.8-61.3%), positive predictive value (65.2%; 95% CI: 52.4-76.5%), accuracy (66.0%; 95% CI: 55.5-75.4%), and the area under the receiver operating characteristic curve (0.640; 95% CI: 0.534-0.736) of their combination were higher but not significantly so.

Conclusions

At present, S-Detect cannot replace manual diagnosis, and the value of elastography of the carotid artery in diagnosing suspected thyroid nodules remains unclear.

The Diagnostic Role of Repeated Biopsy of Thyroid Nodules with Atypia of Undetermined Significance with Architectural Atypia on Core-Needle Biopsy

Background

We aimed to evaluate the utility of repeat biopsy of thyroid nodules classified as atypia of undetermined significance with architectural atypia (IIIB) on core-needle biopsy (CNB).

Methods

This retrospective study evaluated patients with thyroid nodules categorized as IIIB on CNB between 2013 and 2015. Demographic characteristics, subsequent biopsy results, and ultrasound (US) images were evaluated. The malignancy rates of nodules according to number of CNBs and the number of IIIB diagnoses was compared. Demographic and US features were evaluated to determine factors predictive of malignancy.

Results

Of 1,003 IIIB nodules on CNB, the final diagnosis was determined for 328 (32.7%) nodules, with 121 of them confirmed as malignant, resulting in a malignancy rate of 36.9% (95% confidence interval, 31.7% to 42.1%). Repeat CNB was performed in 248 nodules (24.7%), with 75 (30.2%), 131 (52.8%), 13 (5.2%), 26 (10.5%), one (0.4%), and two (0.8%) reclassified into categories II, IIIB, IIIA, IV, V, and VI, respectively. Malignancy rates were not significantly affected by the number of CNBs (P=0.291) or the number of IIIB diagnoses (P=0.473). None of the nodules confirmed as category II on repeat CNB was malignant. US features significantly associated with malignancy (P<0.003) included solid composition, irregular margins, microcalcifications, and high suspicion on the US risk stratification system.

Conclusion

Repeat biopsy of nodules diagnosed with IIIB on CNB did not increase the detection of malignancy but can potentially reduce unnecessary surgery. Repeat biopsy should be performed selectively, with US features guiding the choice between repeat biopsy and diagnostic surgery.

Metastatic thyroid follicular carcinoma presenting as pathological left clavicle fracture: An unusual skeletal metastasis at the time of diagnosis

INTRODUCTION

Thyroid carcinoma is the most common endocrine malignancy, accounting for 3 % of recent malignancies in world wide. Differentiated thyroid carcinoma constitutes 90 % thyroid malignancies, within that follicular type constitutes 10-15 %.

CLINICAL PRESENTATION

A 55-year-old female presented with left-sided neck pain and swelling over medial end of clavicle, following normal manual work. Physical examination revealed swelling on medial end of left clavicle and palpable nodule in left thyroid lobe. Imaging studies showed two nodules in both thyroid lobes with left level IV lymphadenopathy and osteolytic lesion with pathological fracture in medial end of clavicle. Histopathological evaluation confirmed well-differentiated follicular thyroid carcinoma with clavicular metastasis. The patient underwent total thyroidectomy, followed by radioiodine therapy for medial end of left clavicle.

DISCUSSION

Follicular thyroid carcinoma (FTC) is metastasis through the bloodstream, predominantly to flat bones and upper end of long bones, but clavicular deposits are very rarely reported. FNAC only diagnosed the follicular neoplasm. Further tissue evaluation needed to confirm the malignancy. Therefore, hemithyroidectomy of the lesion side is usually carried out for histopathological diagnosis. But in this case, follicular thyroid carcinoma was confirmed through core biopsy from medial end of clavicle, leading to total thyroidectomy and left cervical block dissection, followed by radioiodine therapy for metastatic clavicular involvement.

CONCLUSION

Clavicular metastasis of follicular thyroid carcinoma is very rare. Early detection and proper management of suspicious thyroid carcinoma in uncommon skeletal sites, like the clavicle, is crucial for enhancing patient outcomes, despite the rarity of follicular carcinoma metastasis to this area.

Thyroid US-guided FNA techniques: A prospective,randomized controlled study

BACKGROUND

Thyroid nodules are common in the general population. Ultrasonography is the most efficient diagnostic approach to evaluate thyroid nodules. The US FNAC procedure can be performed using either the short axis (perpendicular), or a long axis (parallel) approach to visualize the needle as it is advanced toward the desired nodule. The main aim of this study was to compare the percentage of non-diagnostic results between the long and short axis approach.

METHODS

A prospective study that included a randomized controlled trial and was divided into two arms-the short axis and the long axis-was conducted. A total of 245 thyroid nodules were collected through the fine needle aspiration cytology, performed with ultrasound, from march 2021 to march 2022. The patient's demographic information were collected and also nodules characteristics.

RESULTS

Of 245 nodules sampled, 122 were sampled with the long axis method, while 123 with the short axis method. There is not significantly less non diagnostic approach with either method compared to the other (11.5 % vs 16.3 % respectively).

DISCUSSION

Previous studies came to the conclusion that the long axis method yields fewer non diagnostic samples. This study evaluated the two FNA approaches which were proceeded by the same physician who is expert in both techniques.

CONCLUSION

The US FNAC performed in the long axis approach will not produce more conclusive results and less non diagnostic results (Bethesda category 1) than the short axis approach one.

Thyroid nodule characterization using Spectral Detector Computed Tomography (SDCT) in comparison to ultrasound

OBJECTIVE

To characterize thyroid nodules seen on Spectral Detector computed tomography (SDCT) in respect to their Thyroid Imaging Reporting and Data System (TI-RADS) category on Ultrasound (US).

METHODS

We included patients that underwent US examination for the evaluation of thyroid nodules and contrast-enhanced SDCT examination of the neck/thorax, between the years 2018-2020. The SDCT and US were performed within 6 months of each other. Only patients with a visible thyroid nodule on SDCT were included. Attenuation measurements of the nodules in Hounsfield units (HU) were performed on the conventional CT images, virtual non-contrast (VNC) images and virtual monoenergetic images of 40 keV and 100 keV. The Iodine concentration, spectral slope and enhancement estimation results of the nodules were measured. We compared the spectral results between two groups of nodules, according to the US report: TI-RADS 2-3 and TI-RADS 4-5 groups.

RESULTS

Thirty-eight nodules were included in the study, 22 nodules in the TI-RADS 2-3 group and 16 in the TI-RADS 4-5 group. The nodules of the TI-RADS 4-5 group had significantly higher Iodine concentration measurement, 4.6 ± 1.8 mg/ml, compared to 2.3 ± 1.2 mg/ml in the TI-RADS 2-3 group; significantly higher estimated enhancement, 3.9 ± 1.5, compared to 2.2 ± 0.7; and significantly higher calculated spectral slope, 5.6 ± 2.2 compared to 2.9 ± 1.5 (p < 0.001).

CONCLUSION

Spectral results of SDCT may assist in differentiating intermediate-high risk (TI-RADS 4-5) from low risk (TI-RADS 2-3) thyroid nodules.

ADVANCES IN KNOWLEDGE

SDCT offers additional information for the characterization of thyroid nodules.

Binary subclassification scheme (AUS-Nuclear versus AUS-Other) adequately risk-stratifies thyroid fine needle aspiration specimens classified as Atypia of Undetermined Significance

INTRODUCTION

The Bethesda System for Reporting Thyroid Cytopathology previously described 4 subclasses of atypia within the Atypia of Undetermined Significance (AUS) category: nuclear (AUS-Nuc), architectural (AUS-A), oncocytic (AUS-Onc), and atypia not otherwise specified (AUS-NOS). Accumulating evidence supports a binary AUS subclassification scheme based primarily on the presence of nuclear atypia only. The purpose of this study is to compare the risk stratification of binary versus 4-tier AUS subclassification systems among AUS nodules with molecular and/or histologic follow-up.

MATERIALS AND METHODS

Thyroid aspirates classified as AUS and tested using Afirma (Veracyte, Inc.) between 6/2013 and 7/2021 were included. For resected nodules, histological classification was considered as the final outcome. For unresected nodules, benign Afirma results were considered low-risk outcomes, similar to histologically benign nodules. Suspicious or nondiagnostic Afirma results were considered indeterminate outcomes. The prevalence of outcomes warranting surgery (noninvasive follicular thyroid neoplasm with papillary-like nuclear features [NIFTP] or cancer) was calculated for each AUS subclass.

RESULTS

A total of 559 AUS nodules with Afirma testing were identified. Excluding nodules with indeterminate molecular outcomes, NIFTP/cancer prevalence for AUS-Nuc was 21% (57/266), which was higher than that for AUS-A (6%, 11/188), AUS-Onc (8%, 4/53), and AUS-NOS (0%, 0/9). A binary AUS subclassification scheme based on nuclear atypia showed a significant difference in NIFTP/cancer prevalence (21% versus 6%, P < 0.0001).

CONCLUSIONS

Binary reporting of AUS subclasses based on nuclear atypia distinguishes cases with a higher risk of NIFTP/cancer. There is a low but non-negligible prevalence of NIFTP/cancer in cases without nuclear atypia.

A knowledge-interpretable multi-task learning framework for automated thyroid nodule diagnosis in ultrasound videos

Ultrasound has become the most widely used modality for thyroid nodule diagnosis, due to its portability, real-time feedback, lack of toxicity, and low cost. Recently, the computer-aided diagnosis (CAD) of thyroid nodules has attracted significant attention. However, most existing techniques can only be applied to either static images with prominent features (manually selected from scanning videos) or rely on 'black boxes' that cannot provide interpretable results. In this study, we develop a user-friendly framework for the automated diagnosis of thyroid nodules in ultrasound videos, by simulating the typical diagnostic workflow used by radiologists. This process consists of two orderly part-to-whole tasks. The first interprets the characteristics of each image using prior knowledge, to obtain corresponding frame-wise TI-RADS scores. Associated embedded representations not only provide diagnostic information for radiologists but also reduce computational costs. The second task models temporal contextual information in an embedding vector sequence and selectively enhances important information to distinguish benign and malignant thyroid nodules, thereby improving the efficiency and generalizability of the proposed framework. Experimental results demonstrated this approach outperformed other state-of-the-art video classification methods. In addition to assisting radiologists in understanding model predictions, these CAD results could further ease diagnostic workloads and improve patient care.

Thyroid Nodules: Emerging Trends in Detection and Visualization based on Citespace

BACKGROUND

Thyroid nodule (TN) is a highly prevalent clinical endocrine disease. Many countries have formed guidelines on the prevention and treatment of TN based on extensive research. However, there is a scarcity of TN-related literature based on bibliometrics.

OBJECTIVES

This study aimed to evaluate the scientific achievements and progress of TN research from a global perspective by investigating the literature for 20 years through bibliometrics.

METHODS

We searched the literature on TN in the core collection of the Web of Science database from 2002 to 2021 and used the Citespace software to analyze the co-authorship, co-citation, and co-occurrence of countries, institutions, authors, keywords, and co-cited literature.

RESULTS

We retrieved 12319 documents related to TN. The literature on TN has been growing since 2002. The United States has contributed the largest proportion of TN papers (20.64%), followed by China, Italy, and South Korea. The United States ranked first in terms of centrality (0.38). Haugen BR, Gharib H, and Cibas ES are the top three most cited authors. The papers published in Thyroid were cited most frequently (7952 times). The most prominent keywords were management, cancer, fine needle aspiration, diagnosis, malignant tumor, thyroid cancer, ultrasound, biopsy, benign, surgery, ablation, and cytology. All keywords could be divided into three categories: diagnosis stratification, treatment, and cancer. As far as potential hot spots are concerned, the keywords that have recently burst strongly and are still continuing are: "Association Guideline" (2018-2021), "Radiofrequency Ablation" (2017-2021), "Classification" (2019-2021), and "Data System" (2017-2021).

CONCLUSION

Based on the current trends, the number of publications on TN will continue to increase. The United States is the most active contributor to research in this field. Previous literature focused on stratification, cancer, surgery, and ablation, and there were different opinions on the stratification of diagnosis. There were relatively few studies on pathogenesis and treatment using medicine. More focus will be placed on association guidelines, radiofrequency ablation, classification, and data system, which may be the next popular topics in TN research.

A white paper

Medullary thyroid carcinoma (MTC) is an infrequent thyroid malignancy that is often diagnosed at advanced stage with consequent poor prognosis. Thus, the earlier the diagnosis of MTC, the better the prognosis. Unfortunately, the preoperative detection of MTC remains challenging in clinical practice. In fact, while ultrasound and fine-needle aspiration cytology have suboptimal performance in this context, measuring serum calcitonin (Ctn), fully recognized as the most reliable test to detect MTC, is not universally accepted as routine test in all patients with thyroid nodule(s). The authors of this paper reappraise critically the matter of Ctn measurement in view of the recent advancements in the literature to point out the essential information to be known, and then to prepare an easy-to-use guide for clinicians to appropriately consider the measurement of serum Ctn during clinical practice.

Cancer rates and characteristics of thyroid nodules with macrocalcification

AIMS

The aim of this study was to determine the malignant potential of thyroid nodules with macrocalcifications and to evaluate the role of other sonographic findings in the diagnosis of malignancy in thyroid nodules besides macrocalcifications.

METHODS

The findings of 8250 patients who applied to our outpatient clinic and underwent thyroid ultrasonography(US) between 2008 and 2021 were retrospectively reviewed. We included a total of 296 patients with 296 macrocalcified nodules (macrocalcification group) and an age- and sex matched group of 300 patients (control group) with the cytopathologic and/or histopathologic data of fine-needle aspiration biopsy (FNAB) of thyroid nodules without calcification. Demographic characteristics of these patients, US characteristics of the nodules, and thyroid function tests were recorded. Cytopathological data of FNAB were classified according to BETHESDA.

RESULTS

The malignancy rate was 14.2% (42/296) in the macrocalcification group and 5.3% (16/300) in the control group (p < 0.001). There was no significant relationship between interrupted peripheral calcification and malignancy. Hypoechoic or markedly hypoechoic appearance, irregular border, solid structure, presence of accompanying pathological lymphadenopathy on sonographic examination and upper and middle zone localization were other sonographic features that increased the risk of malignancy of a nodule. The presence of autoimmunity was not found to be associated with the risk of malignancy. TSH and calcitonin levels of malignant nodules were higher than benign nodules. There was no significant difference between gender and malignancy. In the univariate analysis, it was found that the presence of macrocalcification increased the risk of malignancy 2.935 times. (OR:2.935, p < 0.001.95% CI for OR 1.611-5.349) In addition, being younger, being in the high TIRADS category, and being in the upper and middle zones were factors that increased the risk of malignancy. Gender, TSH level, nodule volume and structure were not associated with malignancy. However, after multivariate analysis, factors that significantly increased the risk of malignancy were younger age, higher TIRADS category, and nodule localization.

CONCLUSION

In our study, the malignancy rate was higher in the macrocalcification group than in the control group. However, no correlation was found after multivariate analysis. In the multivariate analysis, younger age, higher TIRADS category, and nodules located in the upper and middle zone were other factors associated with malignancy. There was no association between peripheral interrupted calcification and malignancy risk.

Use of ultrasound elastography in differentiating benign from malignant thyroid nodules: a prospective study

Purpose

Elastography is a real-time non-invasive ultrasonography modality wherein the tissue stiffness is evaluated by calculating the degree of tissue distortion in response to an external force. This study was undertaken to assess the diagnostic value of elastography in differentiating benign from malignant thyroid nodules.

Methodology

In this prospective comparative study, a total of 52 thyroid nodules from 44 euthyroid patients undergoing fine needle aspiration cytology were assessed. Elastography was performed by a single experienced sonologist, wherein the nodules were graded as per elastography scoring (ES), and the strain ratio (SR) for each nodule was computed. Final histopathology findings of the patients undergoing surgery were compared to elastography findings, and measures of diagnostic accuracy to differentiate between benign and malignant nodules were determined for ES and SR.

Results

Thirty (68.2%) females and 14 (31.8%) males, with a mean age of 45.18 ± 11.23 years, were assessed. Fourteen (31.8%) patients underwent thyroidectomy, and histopathology was reported for 18 (34.6%) nodules. In all, nine (17.3%) nodules were malignant, and 43 (82.7%) nodules were considered benign. ES demonstrated a sensitivity of 88.9%, specificity of 88.3%, PPV of 61.5%, NPV of 97.4%, and accuracy of 88.5% to identify benign thyroid nodules. The mean SR for benign nodules was significantly lower as compared to malignant nodules (2.72 ± 0.62 vs. 4.52 ± 0.75, P < 0.0001). The optimal cut-point value for SR to differentiate benign and malignant thyroid nodules was determined to be 3.8, with the sensitivity, specificity, PPV, NPV, and accuracy being 88.9%, 95.4%, 80%, 94.6%, and 94.2%, respectively.

Conclusion

Ultrasound elastography (ES and SR) demonstrated good diagnostic efficacy to differentiate benign thyroid nodules from the malignant ones, and can be a good supplementary tool to gray-scale ultrasonography. It can also help in reducing the rates of unnecessary fine needle-aspiration biopsy.

SDA-Net: Self-distillation driven deformable attentive aggregation network for thyroid nodule identification in ultrasound images

Early detection and accurate identification of thyroid nodules are the major challenges in controlling and treating thyroid cancer that can be difficult even for expert physicians. Currently, many computer-aided diagnosis (CAD) systems have been developed to assist this clinical process. However, most of these systems are unable to well capture geometrically diverse thyroid nodule representations from ultrasound images with subtle and various characteristic differences, resulting in suboptimal diagnosis and lack of clinical interpretability, which may affect their credibility in the clinic. In this context, a novel end-to-end network equipped with a deformable attention network and a distillation-driven interaction aggregation module (DIAM) is developed for thyroid nodule identification. The deformable attention network learns to identify discriminative features of nodules under the guidance of the deformable attention module (DAM) and an online class activation mapping (CAM) mechanism and suggests the location of diagnostic features to provide interpretable predictions. DIAM is designed to take advantage of the complementarities of adjacent layers, thus enhancing the representation capabilities of aggregated features; driven by an efficient self-distillation mechanism, the identification process is complemented with more multi-scale semantic information to calibrate the diagnosis results. Experimental results on a large dataset with varying nodule appearances show that the proposed network can achieve competitive performance in nodule diagnosis and provide interpretability suitable for clinical needs.

Modification of size cutoff for biopsy based on the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) for thyroid nodules in patients younger than 19 years

OBJECTIVES

To modify the size cutoff for biopsy for thyroid nodules in patients < 19 years based on the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) and evaluate the performance of the new criteria in two referral centers.

METHODS

Patients < 19 years with cytopathologic or surgical pathology results were retrospectively identified from two centers from May 2005 to August 2022. Patients from one center were classified as the training cohort, and those from the other center were classified as the validation cohort. The diagnostic performance, unnecessary biopsy rates, and missed malignancy rates of the TI-RADS guideline, and the new criteria (≥ 35 mm for TR3 and no threshold for TR5) were compared.

RESULTS

A total of 236 nodules from 204 patients in the training cohort and 225 nodules from 190 patients in the validation cohort were analyzed. The area under the receiver operating characteristic curve of the new criteria in identifying thyroid malignant nodules was higher (0.809 vs. 0.681, p < 0.001; 0.819 vs. 0.683, p < 0.001), and the unnecessary biopsy rates (45.0% vs. 56.8%; 42.2% vs. 56.8%) and missed malignancy rates (5.7% vs. 18.6%; 9.2% vs. 21.5%) were lower than that of the TI-RADS guideline in the training cohort and validation cohort, respectively.

CONCLUSIONS

The new criteria (≥ 35 mm for TR3 and no threshold for TR5) for biopsy based on the TI-RADS may help improve the diagnostic performance and reduce unnecessary biopsy rates and missed malignancy rates for thyroid nodules in patients < 19 years.

CLINICAL RELEVANCE STATEMENT

The study developed and validated the new criteria (≥ 35 mm for TR3 and no threshold for TR5) to indicate FNA based on the ACR TI-RADS of thyroid nodules in patients younger than 19 years.

KEY POINTS

•The AUC of the new criteria (≥ 35 mm for TR3 and no threshold for TR5) in identifying thyroid malignant nodules was higher than that of the TI-RADS guideline (0.809 vs. 0.681) in patients < 19 years. •The unnecessary biopsy rates and missed malignancy rates of the new criteria (≥ 35 mm for TR3 and no threshold for TR5) in identifying thyroid malignant nodules were lower than that of the TI-RADS guideline in patients < 19 years (45.0% vs. 56.8% and 5.7% vs. 18.6%, respectively).

Drivers of Thyroid Ultrasound Use: A Retrospective Observational Study

OBJECTIVE

Excessive use of thyroid ultrasound (TUS) contributes to the overdiagnosis of thyroid nodules and thyroid cancer. In this study, we evaluated drivers of and clinical trajectories following TUS orders.

METHODS

We conducted a retrospective review of 500 adult patients who underwent an initial TUS between 2015 and 2017 at Mayo Clinic in Rochester, MN. A framework was employed to classify the indication for TUS, and it was characterized as inappropriate when ordered without a guideline-based indication. Medical records were reviewed for up to 12 months following the TUS, and clinical outcomes were evaluated.

RESULTS

The mean age mean age (SD) was 53.6 years (16.6), 63.8% female, and 86.6% white. TUS orders were triggered by incidental findings on unrelated imaging (31.6%), thyroid symptoms (20.4%), thyroid abnormalities on routine physical examination (17.2%), and thyroid dysfunction workup (11.8%). In females and males, the most common reason were incidental findings on imaging (female, 91/319, 28.5% and male, 67/181, 37.0%). In primary care practice, TUS orders were mostly triggered by symptoms (71/218, 32.5%), while thyroid dysfunction workup was the primary reason in endocrinology (28/100, 28.0%). We classified 11.2% (56/500) TUS orders as likely to have been ordered inappropriately based on current guidelines. Finally, 119 patients (119/500, 23.8%) had a thyroid biopsy with 11.8% had thyroid cancer (14/119. 11.8%).

CONCLUSIONS

Incidental findings on imaging, symptoms, and routine physical exam findings in asymptomatic patients were the most prevalent drivers of TUS. Furthermore, 1 in 10 TUS were likely inappropriately ordered based on current practice guidelines.

Learnability of Thyroid Nodule Assessment on Ultrasonography: Using a Big Data Set

OBJECTIVE

The aims of the work described here were to evaluate the learnability of thyroid nodule assessment on ultrasonography (US) using a big data set of US images and to evaluate the diagnostic utilities of artificial intelligence computer-aided diagnosis (AI-CAD) used by readers with varying experience to differentiate benign and malignant thyroid nodules.

METHODS

Six college freshmen independently studied the "learning set" composed of images of 13,560 thyroid nodules, and their diagnostic performance was evaluated after their daily learning sessions using the "test set" composed of images of 282 thyroid nodules. The diagnostic performance of two residents and an experienced radiologist was evaluated using the same "test set." After an initial diagnosis, all readers once again evaluated the "test set" with the assistance of AI-CAD.

RESULTS

Diagnostic performance of almost all students increased after the learning program. Although the mean areas under the receiver operating characteristic curves (AUROCs) of residents and the experienced radiologist were significantly higher than those of students, the AUROCs of five of the six students did not differ significantly compared with that of the one resident. With the assistance of AI-CAD, sensitivity significantly increased in three students, specificity in one student, accuracy in four students and AUROC in four students. Diagnostic performance of the two residents and the experienced radiologist was better with the assistance of AI-CAD.

CONCLUSION

A self-learning method using a big data set of US images has potential as an ancillary tool alongside traditional training methods. With the assistance of AI-CAD, the diagnostic performance of readers with varying experience in thyroid imaging could be further improved.

Deep learning approaches for differentiating thyroid nodules with calcification: a two-center study

BACKGROUND

Calcification is a common phenomenon in both benign and malignant thyroid nodules. However, the clinical significance of calcification remains unclear. Therefore, we explored a more objective method for distinguishing between benign and malignant thyroid calcified nodules.

METHODS

This retrospective study, conducted at two centers, involved a total of 631 thyroid nodules, all of which were pathologically confirmed. Ultrasound image sets were employed for analysis. The primary evaluation index was the area under the receiver-operator characteristic curve (AUROC). We compared the diagnostic performance of deep learning (DL) methods with that of radiologists and determined whether DL could enhance the diagnostic capabilities of radiologists.

RESULTS

The Xception classification model exhibited the highest performance, achieving an AUROC of up to 0.970, followed by the DenseNet169 model, which attained an AUROC of up to 0.959. Notably, both DL models outperformed radiologists (P < 0.05). The success of the Xception model can be attributed to its incorporation of deep separable convolution, which effectively reduces the model's parameter count. This feature enables the model to capture features more effectively during the feature extraction process, resulting in superior performance, particularly when dealing with limited data.

CONCLUSIONS

This study conclusively demonstrated that DL outperformed radiologists in differentiating between benign and malignant calcified thyroid nodules. Additionally, the diagnostic capabilities of radiologists could be enhanced with the aid of DL.

Safety and efficacy of microwave ablation for symptomatic benign thyroid nodules in children

OBJECTIVE

To evaluate the efficacy and safety of microwave ablation (MWA) for the treatment of symptomatic benign thyroid nodules in children.

METHODS

A retrospective study of MWA for the treatment of 34 symptomatic benign thyroid nodules in 25 children was conducted. Volume reduction ratio (VRR), technique efficacy, symptom score, cosmetic score, and thyroid function were used to evaluate the efficacy of the technique. The associated complications and side effects were recorded.

RESULTS

The participants were followed for at least 6 months (median 12 months, range 6-48 months). After MWA treatment, the volumes of the targeted nodules decreased gradually (median volume 5.86 mL before MWA and 0.34 mL at the final follow-up assessment), the VRR achieved was up to 85.03% at the final follow-up assessment, and the technical efficacy at this time was 91.2%. The subjective and objective nodule-related symptoms were also ameliorated. The circulating hormone concentrations reflecting thyroid function remained within their normal ranges in all the participants after one month of follow-up. The procedure had no major complications.

CONCLUSIONS

MWA seems to be an effective and safe technique for the treatment of symptomatic benign thyroid nodules in pediatric patients.

CLINICAL RELEVANCE STATEMENT

Microwave ablation is a safe and effective method to treat symptomatic benign thyroid nodules in pediatric patients. This treatment may be selected if the patient or parents are not suitable or refuse to undergo surgery.

KEY POINTS

• Microwave ablation is effective in reducing the volume of benign thyroid nodules and ameliorating nodule-related symptoms in pediatric patients. • Microwave ablation is a safe method in children, with low complications. • Microwave ablation does not affect the circulating thyroid hormone concentrations of children.

Markedly hypoechoic: a new definition improves the diagnostic performance of thyroid ultrasound

OBJECTIVES

To determine the contribution of a modified definition of markedly hypoechoic in the differential diagnosis of thyroid nodules.

METHODS

A total of 1031 thyroid nodules were included in this retrospective multicenter study. All of the nodules were examined with US before surgery. The US features of the nodules were evaluated, in particular, the classical markedly hypoechoic and modified markedly hypoechoic (decreased or similar echogenicity relative to the adjacent strap muscles). The sensitivity, specificity, and AUC of classical/modified markedly hypoechoic and the corresponding ACR-TIRADS, EU-TIRADS, and C-TIRADS categories were calculated and compared. The inter- and intraobserver variability in the evaluation of the main US features of the nodules was assessed.

RESULTS

There were 264 malignant nodules and 767 benign nodules. Compared with classical markedly hypoechoic as a diagnostic criterion for malignancy, using modified markedly hypoechoic as the criterion resulted in a significant increase in sensitivity (28.03% vs. 63.26%) and AUC (0.598 vs. 0.741), despite a significant decrease in specificity (91.53% vs. 84.88%) (p < 0.001 for all). Compared to the AUC of the C-TIRADS with the classical markedly hypoechoic, the AUC of the C-TIRADS with the modified markedly hypoechoic increased from 0.878 to 0.888 (p = 0.01); however, the AUCs of the ACR-TIRADS and EU-TIRADS did not change significantly (p > 0.05 for both). There was substantial interobserver agreement (κ = 0.624) and perfect intraobserver agreement (κ = 0.828) for the modified markedly hypoechoic.

CONCLUSION

The modified definition of markedly hypoechoic resulted in a significantly improved diagnostic efficacy in determining malignant thyroid nodules and may improve the diagnostic performance of the C-TIRADS.

CLINICAL RELEVANCE STATEMENT

Our study found that, compared with the original definition, modified markedly hypoechoic significantly improved the diagnostic performance in differentiating malignant from benign thyroid nodules and the predictive efficacy of the risk stratification systems.

KEY POINTS

• Compared with the classical markedly hypoechoic as a diagnostic criterion for malignancy, the modified markedly hypoechoic resulted in a significant increase in sensitivity and AUC. • The C-TIRADS with the modified markedly hypoechoic achieved higher AUC and specificity than that with the classical markedly hypoechoic (p = 0.01 and  < 0.001, respectively).

Ultrasound screening for thyroid nodules and cancer in individuals with family history of thyroid cancer: a micro-costing approach

PURPOSE

Screening programs that target healthy populations are an important tool for identifying unrecognized, asymptomatic disease. However, ultrasound screening for thyroid cancer has no obvious advantage in terms of cost-effectiveness in asymptomatic adults. There is far less consensus (and data) on the indications for screening in high-risk individuals. The aim of the study was to estimate the costs of ultrasound screening for individuals with first-degree family history of thyroid cancer.

METHODS

We conducted a prospective cross-sectional study from January 1, 2009 through December 31, 2018 in the Thyroid Cancer Outpatient Clinic of a large teaching hospital in Rome, Italy. We estimated the costs of an ultrasound screening protocol using the micro-costing bottom-up method.

RESULTS

For individuals without thyroid nodules, the screening examination had an estimated cost of €66.21 per screenee. For those found to have unsuspicious nodules, the estimated cost rose to €119.52 per screenee, owing to the addition of thyroid function tests. The estimated cost of screening for a subject with newly diagnosed nodules that were submitted to cytology was €259.89. The total cost of screening for the entire population of 1176 individuals was € 118,133.85. The total expenditure to confirm a single thyroid cancer diagnosis was €10,598.71.

CONCLUSION

A sonographic screening implies a significant direct expenditure and is likely to detect a very large number of individuals with benign nodules (more than 45 asymptomatic individuals are diagnosed with a thyroid nodule for each newly detected cancer case), whose long-term follow-up will further increase healthcare costs.

The performance of deep learning on thyroid nodule imaging predicts thyroid cancer: A systematic review and meta-analysis of epidemiological studies with independent external test sets

BACKGROUND AND AIMS

It is still controversial whether deep learning (DL) systems add accuracy to thyroid nodule imaging classification based on the recent available evidence. We conducted this study to analyze the current evidence of DL in thyroid nodule imaging diagnosis in both internal and external test sets.

METHODS

Until the end of December 2022, PubMed, IEEE, Embase, Web of Science, and the Cochrane Library were searched. We included primary epidemiological studies using externally validated DL techniques in image-based thyroid nodule appraisal. This systematic review was registered on PROSPERO (CRD42022362892).

RESULTS

We evaluated evidence from 17 primary epidemiological studies using externally validated DL techniques in image-based thyroid nodule appraisal. Fourteen studies were deemed eligible for meta-analysis. The pooled sensitivity, specificity, and area under the curve (AUC) of these DL algorithms were 0.89 (95% confidence interval 0.87-0.90), 0.84 (0.82-0.86), and 0.93 (0.91-0.95), respectively. For the internal validation set, the pooled sensitivity, specificity, and AUC were 0.91 (0.89-0.93), 0.88 (0.85-0.91), and 0.96 (0.93-0.97), respectively. In the external validation set, the pooled sensitivity, specificity, and AUC were 0.87 (0.85-0.89), 0.81 (0.77-0.83), and 0.91 (0.88-0.93), respectively. Notably, in subgroup analyses, DL algorithms still demonstrated exceptional diagnostic validity.

CONCLUSIONS

Current evidence suggests DL-based imaging shows diagnostic performances comparable to clinicians for differentiating thyroid nodules in both the internal and external test sets.

Use of molecular testing results to analyze the overuse of atypia of undetermined significance in thyroid cytology

INTRODUCTION

The suggested atypia of undetermined significance (AUS) rate for thyroid fine-needle aspiration biopsies is 10% or less. Prompted by a high institutional AUS rate, we examined using molecular testing results (MTR) as a potential quality metric tool to reduce the AUS rate. We correlated MTR with AUS cytologic findings, surgical pathology follow-up, and individual pathologist AUS rates.

MATERIALS AND METHODS

Demographic data, cytologic diagnoses, MTR, and surgical pathology diagnoses were retrospectively obtained. MTR were classified as either positive or negative. AUS rates and MTR proportions were compared among pathologists. The cytomorphologic features of 143 AUS cases were assessed and correlated with MTR.

RESULTS

Between 2017 and 2022, 710 of 3247 thyroid fine-needle aspirations were classified as AUS, with a yearly average rate of 22% (range = 19%-26%). AUS cases included: 331 (47%) with architectural atypia; 204 (29%) with oncocytic (Hürthle cell) atypia; 99 (14%) with combined architectural and cytologic atypia; and 76 (10%) with isolated cytologic atypia. Most AUS cases with molecular testing had negative MTR (360/492, 73%). AUS with cytologic atypia had higher positive MTR risk (logarithm of odds ratio = 1.27, 95% credible interval [0.5-2.04], P = 0.001). The average positive MTR rate by pathologist was 21.5% (range 0%-35%); higher positive MTR rates had better correlation with subsequent neoplastic/malignant histologic diagnoses. The MTR sensitivity for malignant disease was 89% and the negative predictive value was 91%.

CONCLUSIONS

MTR analysis reveals the importance of cytologic atypia as a determinant of malignancy risk in AUS cases. Periodic analysis of MTR data alongside individual pathologist AUS rates can help refine diagnostic criteria and potentially reduce AUS overuse.

Comparison of six machine learning methods for differentiating benign and malignant thyroid nodules using ultrasonographic characteristics

BACKGROUND

Several machine learning (ML) classifiers for thyroid nodule diagnosis have been compared in terms of their accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and area under the receiver operating curve (AUC). A total of 525 patients with thyroid nodules (malignant, n = 228; benign, n = 297) underwent conventional ultrasonography, strain elastography, and contrast-enhanced ultrasound. Six algorithms were compared: support vector machine (SVM), linear discriminant analysis (LDA), random forest (RF), logistic regression (LG), GlmNet, and K-nearest neighbors (K-NN). The diagnostic performances of the 13 suspicious sonographic features for discriminating benign and malignant thyroid nodules were assessed using different ML algorithms. To compare these algorithms, a 10-fold cross-validation paired t-test was applied to the algorithm performance differences.

RESULTS

The logistic regression algorithm had better diagnostic performance than the other ML algorithms. However, it was only slightly higher than those of GlmNet, LDA, and RF. The accuracy, sensitivity, specificity, NPV, PPV, and AUC obtained by running logistic regression were 86.48%, 83.33%, 88.89%, 87.42%, 85.20%, and 92.84%, respectively.

CONCLUSIONS

The experimental results indicate that GlmNet, SVM, LDA, LG, K-NN, and RF exhibit slight differences in classification performance.

TS-DSANN: Texture and shape focused dual-stream attention neural network for benign-malignant diagnosis of thyroid nodules in ultrasound images

Recently, accurate diagnosis of thyroid nodules has played a critical role in precision medicine and healthcare system management. Due to complicated changes in ultrasound features of texture, and similar visual appearance of benign-malignant nodules, the identification of cancerous thyroid lesions from a given ultrasound image still faces challenges for even experienced radiologists. Learning-based computer-aided diagnosis (CAD) systems have accordingly attracted more and more attention recently. However, little research is committed to developing a deep learning-based CAD system that has greater conformity with radiologists' diagnostic decision-making. In this study, we devise a texture and shape focused dual-stream attention neural network, dubbed TS-DSANN. Specifically, in the texture focused stream, we utilize the ImageNet pre-trained ResNet34 to guide the network to recognize texture-related nodule attributes. Meanwhile, in the shape focused stream, in addition to using ResNet34 backbone, jointly learning from scratch with the contour obtained by contour detection module to enhance the extraction of shape features. Afterward, we employ a concatenation operation to aggregate the abovementioned two stream networks for capturing richer and more representative features. Finally, we further utilize an online class activation mapping mechanism to assist the dual-stream network in generating a localization heatmap to obtain more visualization attention to the nodule from the whole image, and supervise classifier's attention in decision-making. Experimental results conducted on the two-center thyroid nodule ultrasound datasets verify that our proposed method has improved the classification performance, superior to the state-of-the-art methods.

The auxiliary diagnosis of thyroid echogenic foci based on a deep learning segmentation model: A two-center study

OBJECTIVE

The aim of this study is to develop AI-assisted software incorporating a deep learning (DL) model based on static ultrasound images. The software aims to aid physicians in distinguishing between malignant and benign thyroid nodules with echogenic foci and to investigate how the AI-assisted DL model can enhance radiologists' diagnostic performance.

METHODS

For this retrospective study, a total of 2724 ultrasound (US) scans were collected from two independent institutions, encompassing 1038 echogenic foci nodules. All echogenic foci were confirmed by pathology. Three DL segmentation models (DeepLabV3+, U-Net, and PSPNet) were developed, with each model using two different backbones to extract features from the nodular regions with echogenic foci. Evaluation indexes such as Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA), and Dice coefficients were employed to assess the performance of the segmentation model. The model demonstrating the best performance was selected to develop the AI-assisted diagnostic software, enabling radiologists to benefit from AI-assisted diagnosis. The diagnostic performance of radiologists with varying levels of seniority and beginner radiologists in assessing high-echo nodules was then compared, both with and without the use of auxiliary strategies. The area under the receiver operating characteristic curve (AUROC) was used as the primary evaluation index, both with and without the use of auxiliary strategies.

RESULTS

In the analysis of Institution 2, the DeepLabV3+ (backbone is MobileNetV2 exhibited optimal segmentation performance, with MIoU = 0.891, MPA = 0.945, and Dice = 0.919. The combined AUROC (0.693 [95% CI 0.595-0.791]) of radiology beginners using AI-assisted strategies was significantly higher than those without such strategies (0.551 [0.445-0.657]). Additionally, the combined AUROC of junior physicians employing adjuvant strategies improved from 0.674 [0.574-0.774] to 0.757 [0.666-0.848]. Similarly, the combined AUROC of senior physicians increased slightly, rising from 0.745 [0.652-0.838] to 0.813 [0.730-0.896]. With the implementation of AI-assisted strategies, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of both senior physicians and beginners in the radiology department underwent varying degrees of improvement.

CONCLUSIONS

This study demonstrates that the DL-based auxiliary diagnosis model using US static images can improve the performance of radiologists and radiology students in identifying thyroid echogenic foci.