To address the high computational complexity of the Transformer in the segmentation of ultrasound thyroid nodules and the loss of image details or omission of key spatial information caused by traditional image sampling techniques when dealing with high-resolution, complex texture or uneven density two-dimensional ultrasound images, this paper proposes a thyroid nodule segmentation method that integrates the receiving weighted key-value (RWKV) architecture and spherical geometry feature (SGF) sampling technology. This method effectively captures the details of adjacent regions through two-dimensional offset prediction and pixel-level sampling position adjustment, achieving precise segmentation. Additionally, this study introduces a patch attention module (PAM) to optimize the decoder feature map using a regional cross-attention mechanism, enabling it to focus more precisely on the high-resolution features of the encoder. Experiments on the thyroid nodule segmentation dataset (TN3K) and the digital database for thyroid images (DDTI) show that the proposed method achieves dice similarity coefficients (DSC) of 87.24% and 80.79% respectively, outperforming existing models while maintaining a lower computational complexity. This approach may provide an efficient solution for the precise segmentation of thyroid nodules.
Thyroid Nodule/diagnostic imaging* ; Humans ; Ultrasonography/methods* ; Algorithms ; Image Processing, Computer-Assisted/methods* ; Thyroid Gland/diagnostic imaging*

Thyroid nodules are a common endocrine disorder, and their early detection and accurate diagnosis are crucial for the prevention of thyroid cancer. However, the highly heterogeneous morphology and boundaries of thyroid nodules pose significant challenges to their precise identification and classification. Traditional diagnostic approaches rely heavily on physicians' experience, which increases the risk of misdiagnosis and missed diagnoses. With the rapid advancement of computer-aided diagnosis (CAD) technologies, applying deep learning algorithms to the analysis of thyroid nodule ultrasound images has shown great potential. This paper reviews the latest research progress on deep learning-based CAD methods for thyroid nodules, with a focus on their applications in image preprocessing, segmentation and classification. The advantages and limitations of current techniques are analyzed, and potential future directions are discussed. This review aims to highlight the potential of deep learning in thyroid nodule diagnosis and to provide a foundation for selecting feasible pathways for future clinical applications.
Humans ; Thyroid Nodule/diagnostic imaging* ; Deep Learning ; Ultrasonography/methods* ; Diagnosis, Computer-Assisted/methods* ; Algorithms ; Thyroid Neoplasms/diagnostic imaging* ; Image Processing, Computer-Assisted/methods*

INTRODUCTION

Thyroid cancer is the most common endocrine related malignancy in the Philippines. Data showed Filipino patients are at higher risk to develop thyroid malignancy with an increasing incidence annually. Currently, the initial screening test utilized to evaluate thyroid nodules is ultrasonography with studies showing promising results in detecting and evaluating thyroid carcinoma employing the use of the Thyroid Imaging, Reporting and Data System (TIRADS). TIRADS is a standardized classification system to evaluate and characterize thyroid nodules. However, there are studies stating that TIRADS is of limited clinical value for risk stratification of indeterminate cytological results.

OBJECTIVES

The primary objective of this study is to determine the correlation of the results of TIRADS, Fine Needle Aspiration Cytology (FNAC), and histopathology of thyroid nodules among patients who underwent thyroidectomy at Makati Medical Center from January 2016 to March 2020.

METHODS

This is a retrospective, analytical, observational, cross-sectional study wherein medical records of patients who were diagnosed with thyroid nodules goiter who underwent thyroid ultrasound with TIRADS scoring, Fine needle Aspiration Biopsy (FNAB) and ultimately thyroidectomy were reviewed. The primary endpoint included diagnostic performance of TIRADS classification and the possible factors that may contribute to discordance to FNAB and Histopathology.

RESULTS

One hundred twenty-five patients who underwent thyroidectomy were reviewed. These patients underwent thyroidectomy on the basis of their fine needle aspiration biopsy results. With FNAB as a reference standard, TIRADS had good sensitivity of 100% and low specificity of 27.7% in detecting thyroid malignancy. Patients who had FNAB positive or suspicious for malignancy are 1.37 times more likely to yield a positive TIRADS compared to patients who are FNAB negative (LR+), and 94% less likely to yield a negative TIRADS result (LR-). When TIRADS is positive, the positive predictive value was 31.3% and when TIRADS is negative, the negative predictive value (NPV) was nearly 100%. Overall, the accuracy of TIRADS in thyroid malignancy is 45.6% with ROC area at 0.638, indicating fair discriminative power of TIRADS to differentiate between benign vs malignant thyroid nodules. With histopathology as a reference standard, TIRADS had good sensitivity of 96.3% and low specificity of 33.8%. Patients who are histopathology positive are 1.45 times more likely to yield a positive TIRADS compared to patients who are histopathology negative (LR+), and 89% less likely to yield a negative TIRADS result (LR-). When TIRADS is positive, the positive predictive value was 52.5% and when TIRADS is negative, the negative predictive value (NPV) was 92.3%. Overall, the accuracy of TIRADS in thyroid malignancy is 60.8% with ROC area at 0.65, indicating fair discriminative power to differentiate between benign versus malignant thyroid nodules.

CONCLUSION

TIRADS classification provides high sensitivity value in detecting thyroid malignancies but has fair discriminative power to differentiate between benign versus malignant thyroid nodules. Factors that are associated with discordant classification between TIRADS and FNAB were seen in those who underwent total thyroidectomy with lymph node dissection, and solid composition. There is insufficient evidence to determine whether any of the patient or nodule characteristics were associated with discordance between TIRADS and histopathology.

Human ; Thyroid Nodule

Objective To analyze the cellular and histopathological characteristics of underdiagnosed thyroid nodules of Chinese thyroid imaging reporting and data system(C-TIRADS) categories 3 and 4a,thus improving the understanding of these lesions. Methods The data of ultrasound and fine needle aspiration cytology were collected from 683 nodules diagnosed based on pathological evidence in 549 patients undergoing thyroid surgery.The cellular and histopathological characteristics of C-TIRADS 3 and 4a nodules were analyzed. Results Two hundred and sixty-eight nodules were classified as C-TIRADS category 3,including 236 benign nodules,12 low-risk ones,and 20 (7.46%) malignant ones.Two hundred and twenty-one nodules were classified as C-TIRADS category 4a,including 133 benign nodules,7 low-risk ones,and 81 (36.65%) malignant ones.The malignancy rates differed between C-TIRADS 3 and 4a nodules (χ²=58.93,P<0.001),and both were higher than the recommended malignancy rate in the guidelines for malignancy risk stratification of thyroid nodules (C-TIRADS) (both P<0.001).According to the pathological evidence,the underdiagnosed C-TIRADS 3/4a nodules were mainly papillary thyroid carcinoma,especially in patients with Hashimoto thyroiditis.There was not a consistent one-to-one match between each ultrasound result and each cytological classification of low-risk thyroid nodules.Conclusions When the malignant features in preoprative ultrasound imaging are atypical or absent,papillary thyroid carcinoma (especially with Hashimoto thyroiditis),follicular carcinoma,and medullary carcinoma are likely to be underdiagnosed as C-TIRADS 3 or 4a nodules.Therefore,efforts should be made to fully understand the cellular and pathological characteristics of these lesions.
Humans ; Thyroid Nodule/diagnostic imaging* ; Female ; Male ; Middle Aged ; Adult ; Ultrasonography ; Biopsy, Fine-Needle ; Aged ; Young Adult ; Thyroid Neoplasms/diagnostic imaging* ; Adolescent

Objective To explore the research progress and hotspots of intelligent ultrasound imaging in the diagnosis of thyroid nodules and clarify the research directions via the bibliometric method.Methods The relevant research articles on intelligent ultrasound imaging in the diagnosis of thyroid nodules were retrieved from the Web of Science Core Collection,covering the period from January 2004 to August 2024.Python was used to analyze the number of annual publications.VOSviewer was used to create the co-occurrence network of authors and the keyword density map.CiteSpace was used to demonstrate the dual-map overlays of the journals,as well as the bursts and clustering of co-citations and keywords.Results A total of 1 179 articles were included.The annual number of publications increased steadily.The involved journals demonstrated high quality,and the publications showed a trend of cross-research.Chinese researchers were the core research force in this field.Haugen et al.'s study on the guidelines for thyroid nodules had the most citations.The clustering of co-citations and keywords indicated studies in multiple fields.Thyroid nodules,cancer,and deep learning were the representative keywords in this field.Conclusions The continuous enrichment of research topics promotes the rapid development of intelligent ultrasound imaging for thyroid nodules.Intelligent diagnosis methods based on deep learning can provide diagnostic suggestions,while there are still challenges such as interpretation.One of the research directions is the deep combination of intelligent diagnosis algorithms and medical knowledge.
Thyroid Nodule/diagnostic imaging* ; Humans ; Ultrasonography ; Bibliometrics

OBJECTIVES

To discuss a case of papillary thyroid carcinoma with concomitant thyroid tuberculosisin terms of clinical presentation and treatment.

METHODS

Design:Case Report

Setting:Tertiary Government Training Hospital

Patient:One

RESULTS

A 19-year-old Filipina consulted with a four-year history of a left thyroid nodule. She was clinically euthyroid with unremarkable systemic examination. Fine needle aspiration cytology (FNAC) was suspicious for malignancy and she underwent total thyroidectomy. Histopathology revealed papillary thyroid carcinoma of the left lobe, microcarcinoma of the isthmus and incidental note of tuberculosis (TB) of the right lobe. Management included oral anti-TB medications and surveillance.

CONCLUSION

A 19-year-old Filipina consulted with a four-year history of a left thyroid nodule. She was clinically euthyroid with unremarkable systemic examination. Fine needle aspiration cytology (FNAC) was suspicious for malignancy and she underwent total thyroidectomy. Histopathology revealed papillary thyroid carcinoma of the left lobe, microcarcinoma of the isthmus and incidental note of tuberculosis (TB) of the right lobe. Management included oral anti-TB medications and surveillance.

Human ; Female ; Young Adult: 19-24 Yrs Old ; Carcinoma ; Thyroid Cancer, Papillary ; Thyroid Neoplasms ; Thyroid Gland ; Thyroidectomy ; Thyroid Nodule ; Government ; Needles ; Hospitals ; Research Report

OBJECTIVE

To determine the predictive value of ACR-TIRADS in detecting malignancy in thyroid nodules.

METHODS

This is a retrospective, multi-center, cross-sectional analysis of patients who underwent ultrasound and thyroidectomy at three Cordillera Consortium hospitals between January 2019 and December 2021. Ultrasound reports were reviewed and correlated with histopathology reports to determine features associated with malignancy.

RESULTS

A study of 117 patients with thyroid nodules found significant differences in ACR-TIRADS subcategories. The risk of malignancy for TIRADS categories 1, 2, 3, 4, and 5 were 10%, 9.5%, 21.9%, 43.9%, and 76.97%, respectively. ACR-TIRADS demonstrated a high sensitivity of 92.1% and negative predictive value (NPV) of 90.3% as a rule-out test, and a specificity of 96.2% with a positive predictive value (PPV) of 76.9% as a rule-in test using TIRADS 5 as malignant. Correct classification of malignant nodules increased by cut-off value with the highest at 73.5% at the ≥5 cut-off value. Discussion: Thyroid nodules were more common in females under 55 years old. Certain sonographic features of thyroid nodules, such as being solid or predominantly solid, hypoechoic, lobulated/irregular, and having punctate echogenic foci, were associated with malignancy. The risk of malignancy at Cordillera Consortium hospitals was notably higher in this study. The ACR-TIRADS test yielded results consistent with previous studies, with TR 1 and 2 indicating benign nodules and TIRAD 3-5 indicating malignant nodules.

CONCLUSION

Due to a higher risk of malignancy, it is recommended to be more aggressive in performing biopsies for thyroid nodules at Cordillera Consortium hospitals. ACR-TIRADS is a reliable screening tool and is recommended as a confirmatory test (TIRADS 5) for thyroid malignancy. Biopsies are still recommended for TIRADS 3, 4, and 5 nodules to avoid unnecessary procedures and confusion among surgeons.

Human ; Thyroid Nodule ; Thyroid Gland ; Thyroidectomy ; Radiology

BACKGROUND

Thyroid fine-needle aspiration biopsy (FNAB) is widely used for thyroid nodule characterization, with approximately 2.7% of samples classified as "inadequate." Non-diagnostic samples pose limitations, resulting in repeated procedures, and unnecessary diagnostic thyroidectomies. Conventional smear (CS) is commonly the method of choice for cytologic preparation of thyroid FNAB. The cell block technique is an alternative that concentrates cells providing additional material for better evaluation and ancillary testing. While conventional smears are commonly used, introducing routine complementary cell blocks could potentially lower costs associated with repeat procedures and improve patient management.

OBJECTIVE

The study aimed to investigate the diagnostic value of incorporating the cell block technique as adjunct to conventional smear technique in reducing nondiagnostic rates (Bethesda Category I) in thyroid-fine needle aspiration biopsies (FNAB) conducted in 2 private hospitals.

METHODOLOGY

This is a multi-center, retrospective cross-sectional study with 701 samples from 528 adult patients, who underwent thyroid FNAB between January 2020 - September 2022. The primary outcome of interest is the reduction in non-diagnostic rates with the combined use of conventional smears and cell block.

RESULTS

The non-diagnostic rates were significantly higher with cell block technique (28.10%) as compared to conventional smears (16.26%), p-value < .01. The results show that conventional smears have lower non-diagnostic rates. With smear cytology alone, 114 (16.3%) of all samples were nondiagnostic. With the addition of cell block technique, 15 of these samples were reclassified as benign (n = 13), Bethesda III (n = 1) or Bethesda IV (n = 1). The rest of the non-diagnostic samples (n = 99) remained Bethesda I. Overall, the equivalent decrease in non-diagnostic rate was 2.1%.

CONCLUSION

The combined use of cell block and conventional smears did not significantly decrease nondiagnostic rates in thyroid FNAB. In general, conventional smears demonstrated superior diagnostic efficacy across all Bethesda categories, establishing it as the preferred sampling preparation method for thyroid FNAB. Cell blocks should be considered a supplementary technique, particularly in cases where ancillary methods like immunohistochemistry or molecular testing are needed.

Biopsy, Fine-needle ; Thyroid Nodule ; Thyroid Gland ; Thyroid Diseases

Objective: Management of thyroid nodules relies on the Thyroid Imaging Recording and Data System (TIRADS) for sonographic findings and the Bethesda System for Reporting Thyroid Cytopathology (TBSRTC). The proponents aimed to determine the concordance between sonographic TIRADS findings and cytological diagnosis by TBSRTC in the evaluation of malignancy of patients with thyroid nodules. Methodology: Sonographic and cytology results collected from 2018 to 2022 were obtained to determine whether there is an agreement between TIRADS and TBSRTC findings. Results: Two hundred sixty-two (262) samples were obtained. Overall accuracy of predicting TIRADS category was highest for echogenic foci. Thyroid nodule distribution was highest for TIRADS 3 and 4 sonographically and TBSRTC II cytologically. There is low agreement between TBSRTC and TIRADS in the categorization of nodules as benign, implying that nodules may show sonographic features suspicious of malignancy despite being categorized as TBSRTC I or II by cytology. However, nodules categorized as TBSRTC III to VI show sonographic features suspicious for malignancy at the very least. Conclusion The correctness of TIRADS prediction is highest for echogenic foci although not significantly higher than other parameters. The overall predicting power of TIRADS for the absence of malignancy is high for TIRADS 1 and 2, whereas TIRADS 5 predicts a 31.11% risk of malignancy making it a strong indication for FNAC. However, prediction of malignancy in TIRADS 3 and 4 nodules must be in association with other factors since a significant percentage may turn out to be TBSRTC II.
Thyroid Nodule

Objective: This study aims to evaluate the diagnostic accuracy of the American College of Radiology Thyroid Imaging Reporting Data System (ACR TI-RADS) in identifying nodules that need to undergo fine-needle aspiration biopsy (FNAB) and identify specific thyroid ultrasound characteristics of nodules associated with thyroid malignancy in Filipinos in a single tertiary center. Methodology: One hundred seventy-six thyroid nodules from 130 patients who underwent FNAB from January 2018 to December 2018 were included. The sonographic features were described and scored using the ACR TI-RADS risk classification system, and the score was correlated to their final cytopathology results. Results: The calculated malignancy rates for TI-RADS 2 to TI-RADS 5 were 0%, 3.13%, 7.14%, and 38.23%, respectively, which were within the TI-RADS risk stratification thresholds. The ACR TI-RADS had a sensitivity of 89.5% and specificity of 54%, LR + of 1.95 and LR - of 0.194, NPV of 97.7%, PPV of 19.1%, and accuracy of 58%. Conclusion The ACR TI-RADS may provide an effective malignancy risk stratification for thyroid nodules and may help guide the decision for FNAB among Filipino patients. The classification system may decrease the number of unnecessary FNABs for nodules with low-risk scores.
Thyroid Nodule