Thyroid Imaging Reporting And Data System Research Articles

Explainable Automated TI-RADS Evaluation of Thyroid Nodules.

A thyroid nodule, a common abnormal growth within the thyroid gland, is often identified through ultrasound imaging of the neck. These growths may be solid- or fluid-filled, and their treatment is influenced by factors such as size and location. The Thyroid Imaging Reporting and Data System (TI-RADS) is a classification method that categorizes thyroid nodules into risk levels based on features such as size, echogenicity, margin, shape, and calcification. It guides clinicians in deciding whether a biopsy or other further evaluation is needed. Machine learning (ML) can complement TI-RADS classification, thereby improving the detection of malignant tumors. When combined with expert rules (TI-RADS) and explanations, ML models may uncover elements that TI-RADS misses, especially when TI-RADS training data are scarce. In this paper, we present an automated system for classifying thyroid nodules according to TI-RADS and assessing malignancy effectively. We use ResNet-101 and DenseNet-201 models to classify thyroid nodules according to TI-RADS and malignancy. By analyzing the models' last layer using the Grad-CAM algorithm, we demonstrate that these models can identify risk areas and detect nodule features relevant to the TI-RADS score. By integrating Grad-CAM results with feature probability calculations, we provide a precise heat map, visualizing specific features within the nodule and potentially assisting doctors in their assessments. Our experiments show that the utilization of ResNet-101 and DenseNet-201 models, in conjunction with Grad-CAM visualization analysis, improves TI-RADS classification accuracy by up to 10%. This enhancement, achieved through iterative analysis and re-training, underscores the potential of machine learning in advancing thyroid nodule diagnosis, offering a promising direction for further exploration and clinical application.

Comparative evaluation of thyroid imaging reporting and data system and cytopathological correlation in thyroid nodules

Background: With the increasing availability of ultrasound (USG) and concern for malignancy, there has been significant increase in the detection of thyroid lesions. However, there is no uniformity in the reporting pattern among radiologists, and hence, such USG reports are mostly inconclusive to exclude thyroid malignancy. Therefore, most of the patients have to undergo fine needle aspiration cytology or fine needle non-aspiration cytology (FNNAC), which is avoidable. The sonographic assessment of thyroid nodule can provide alternative method to this invasive modality of diagnosis. Therefore, the need was felt for establishing uniformity in USG reporting of thyroid nodules and risk stratification for malignancy with aim of reducing unnecessary FNNAC. Thyroid imaging reporting and data system (TIRADS) classification brings uniformity in reporting and reduces ambiguity in management of the patients. Aims and Objectives: The objective of the study was to perform comparative evaluation of TIRADS and cytopathological evaluation of thyroid nodules FNNAC in Indian scenario. Materials and Methods: Multicentric prospective study was conducted in the department of radio diagnosis and department of surgery at defence service hospitals of Jaipur and Chandimandir during the study period of July 01, 2017–October 31, 2022. Results: Out of the 208 nodules, 28 (13.5%) turned out to be malignant. The percentage of malignant thyroid nodules was higher in nodules with TIRADS scores 4 and 5. The percentage of malignant thyroid nodules was 1% and 2%, respectively, for TIRADS 2 and 3 categories. The most common finding of USG evaluation was diffuse thyroiditis. There was a significant correlation between the USG findings and FNNAC findings in TIRADS scoring system. Conclusion: Our study shows high degree of correlation between TIRADS classification and cytopathological evaluation of thyroid nodules. Hence, TIRADS can be used an effective tool for avoiding unnecessary FNNAC procedures.

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 19years.

To modify the size cutoff for biopsy for thyroid nodules in patients < 19years 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. Patients < 19years 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 (≥ 35mm for TR3 and no threshold for TR5) were compared. 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. The new criteria (≥ 35mm 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 < 19years. The study developed and validated the new criteria (≥ 35mm for TR3 and no threshold for TR5) to indicate FNA based on the ACR TI-RADS of thyroid nodules in patients younger than 19years. •The AUC of the new criteria (≥ 35mm 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 < 19years. •The unnecessary biopsy rates and missed malignancy rates of the new criteria (≥ 35mm for TR3 and no threshold for TR5) in identifying thyroid malignant nodules were lower than that of the TI-RADS guideline in patients < 19years (45.0% vs. 56.8% and 5.7% vs. 18.6%, respectively).

Value of TI-RADS and elastography strain ratio in predicting malignant thyroid nodules: experience from a single center in Egypt

IntroductionThyroid nodules are highly prevalent in the general population; therefore, it is crucial to discriminate benign from malignant nodules. A practical thyroid imaging reporting and data system (TI-RADS) for thyroid nodules and ultrasound elastography are valuable tools not only for characterization of nodules but also for the selection of tumors for fine-needle aspiration cytology (FNAC).ObjectiveThis study aimed to evaluate the diagnostic accuracy of US evaluation in the prediction of malignant thyroid nodules and evaluate the role of the elastography score, strain ratio (SR), and the TI-RADS scoring system as non-invasive tools in differentiation between malignant and benign thyroid nodules.Material and methodsA total of 1269 patients were evaluated between February 2017 and April 2020 by a single expert thyroid ultrasound operator. The final diagnosis was achieved from cytological and/or histological evaluation and follow-up for at least 1 year.ResultsThere were 1088 females and 181 males with a mean age of 44 ± 10 SD. The final diagnosis was 1197 benign nodules and 72 malignant nodules. Most malignant nodules were scored elastography score 4 (83.3%) and TI-RADS category 5 (86.11%). We found that nodules with antero-posterior to transverse (A-P/T) diameter > 1, have 21 times more risk to be malignant than those with A-P/T diameter < 1, patients with solitary thyroid nodules have 4.5 times to develop malignancy compared to those with multinodular goiter (MNG), nodules with absent halo have 4 times more risk of malignancy. Furthermore, microcalcifications in thyroid nodules increase the risk of malignancy 9 times compared to those without calcifications. SR was found to be an excellent discriminator to differentiate between benign and malignant nodules with P < 0.001. Also, we found that for every unit increase in SR, the risk of malignancy increased by 20%. We reported that the accuracy of ultrasonography in the detection of malignant thyroid nodules had a sensitivity of 89%, specificity of 98%, 70% PPV, and 99.3% NPV, with an overall accuracy of 97.2%.ConclusionThe application of ultrasonographic non-invasive criteria for thyroid nodules in clinical practice might significantly reduce the number of unnecessary FNAC. Elastography, SR, and TI-RADS classification could be good predictors for malignant thyroid nodules.

Assessment of thyroid nodule malignancy risk in medical radiation workers using ACR TI-RADS

BackgroundLow-dose radiation exposure brings medical radiation professionals at risk for thyroid parenchymal disease and nodules. ObjectiveTo classify thyroid nodules in medical radiation workers according to their risk, and to look into parenchymal disease and thyroid dysfunction. Design, setting and participantsRetrospective observational study in a tertiary health facility with 148 healthcare workers working in radiation-containing areas. Main outcome and measuresParticipants were divided into groups based on their sociodemographic characteristics, the department they worked in, and the number of years they had been in the profession. The levels of TSH, parenchymal heterogeneity, and thyroid nodule presence were compared between the groups. American College of Radiology (ACR) Thyroid Imaging – Reporting and Data System (TI-RADS) classification was used to evaluate thyroid nodules. ResultsThe presence of nodules was significantly more prevalent in patients over the age of 33 (p = 0.02). The majority of individuals (98%) had nodules that below the American College of Radiology (ACR) Thyroid Imaging – Reporting and Data System (TI-RADS) category 4. Age and professional experience both elevated TSH results (p = 0.015, p = 0.033). With age, parenchymal heterogeneity became more prominent (p = 0.04). For the parameters, there were no appreciable differences between the occupation and department. The results applied to both genders equally. ConclusionWith increasing long-term low-dose exposure, medical radiation workers are at risk for nodules and parenchymal disease. However, the majority of the nodules in our study were sonographically in the low risk group, therefore routine follow-up is advised.

Diagnostic efficacy of a combination of the Chinese thyroid imaging reporting and data system and shear wave elastography in detecting category 4a and 4b thyroid nodules.

Differential diagnosis of benign and malignant thyroid imaging reporting and data system (TIRADS) category 4a and 4b nodules can be difficult using conventional ultrasonography (US). The objective of this study was to evaluate the diagnostic efficacy of a combination of the Chinese-TIRADS (C-TIRADS) and shear wave elastography (SWE) in detecting malignant nodules among category 4a and 4b thyroid nodules. Among 409 thyroid nodules in 332 patients that we included in this study, 106 thyroid nodules were diagnosed as category 4a and 4b using C-TIRADS. We used SWE to measure the maximum Young's modulus (Emax) values of category 4a and 4b thyroid nodules. We calculated the diagnostic efficacy of only the C-TIRADS, only SWE, and a combination of C-TIRADS with SWE, and compared these, while taking the pathology results as the gold standard. The area under the ROC curve (AUC), sensitivity, and accuracy values of the combination of C-TIRADS and SWE (0.870, 83.3%, and 84.0%, respectively) were all higher when compared with the values of only the C-TIRADS (0.785, 68.5%, and 78.3%, respectively) or only SWE (0.775, 68.5%, and 77.4%, respectively) in the diagnosis of category 4a and 4b thyroid nodules. In this study, we found that the combination of C-TIRADS and SWE significantly improved the diagnostic efficacy in detecting malignant nodules among category 4a and 4b thyroid nodules, and this could provide a reference for further use of this combination by clinicians for diagnosis and treatment.

Analysis of Thyroid Imaging Reporting and Data System Criteria and Its Correlation With the Pathological Results.

Introduction Thyroid nodules are frequently encounteredand may be discovered roughly in around 4-8% of individuals by clinical palpation. Aim The present study aims to analyze the Thyroid Imaging Reporting and Data Systems (TIRADS) classification and assess the validity of each criterion in predicting malignancy. Methods A prospective observational study was conducted at Sri Ramachandra Institute of Higher Education and Research from June 2020 to October 2021. Fifty patients who presented to the outpatient clinic with thyroid swelling got an ultrasound (USG) neck performed followed by either fine-needle aspiration cytology (FNAC) or thyroidectomy. They were included in the study and informed consent was obtained from all patients. Results Among50 patients considered for the study, 36 were females. The mean age for malignant patients is 46 years with a standard deviation (SD) of 15, and for benign lesions is 47 years with an SD of 1. Most of the patients were TIRADS 4, which has a 56.2% risk of malignancy. The pathological results show a significant difference in ACR (American College of Radiology) TIRADS and echogenic foci between FNAC. The present study's solid composition showed a sensitivity of 25% and specificity of 75%, with an odds ratio of 0.90 in picking up malignant nodules. The shape of a nodule taller than wider, a malignant feature, showed a specificity of 92.3%. Punctate echogenic foci showed a sensitivity of 50% and specificity of 76.9% with a statistical significance of p-value 0.048. Conclusion TIRADS scoring avoids unessential invasive techniques for lower TIRADS scores. Certain criteria are more specific in recognizing malignant nodules. Proportional priority shall be given to certain criteria over others, and not all criteria should be considered.

Revised Thyroid Imaging Reporting and Data System (TIRADS): imitating the American College of Radiology TIRADS, a single-center retrospective study.

The incidence of thyroid lumps is more and more high in population, and most biopsies of thyroid nodules are benign. To develop a practical risk stratification system based on five ultrasound features to stratify the malignancy risk of thyroid neoplasms. This retrospective investigation enrolled 999 consecutive patients with 1,236 thyroid nodules who underwent ultrasound screening. Fine-needle aspiration and/or surgery was performed, and pathology results were obtained at the Seventh Affiliated Hospital of Sun Yat-sen University in Shenzhen, China, which is a tertiary referral center, from May 2018 to February 2022. Each thyroid nodule's score was calculated based on five ultrasound features: composition, echogenicity, shape, margin, and echogenic foci. Additionally, each nodule's malignancy rate was calculated. The chi-square test was used to test whether the malignancy rate was different among the three subcategories (scores of 4-6, 7-8, and 9 or more) of thyroid nodules. We proposed the revised Thyroid Imaging Reporting and Data System (R-TIRADS), and its sensitivity and specificity were compared to the two existing systems [the American College of Radiology TIRADS (ACR TIRADS) and the Korean Society of Thyroid Radiology TIRADS (K-TIRADS)]. The final dataset consisted of 425 nodules from 370 patients. The malignancy rates of three subcategories [malignancy rate: 28.8% (scores from 4-6), 64.7% (scores from 7-8), and 84.2% (scores of 9 or more)] were significantly different (P<0.01). The unnecessary biopsy rates of the three systems (ACR TIRADS, R-TIRADS, and K-TIRADS) were 28.7%, 25.2%, and 14.8%, respectively. The R-TIRADS presented better diagnostic performance than the ACR TIRADS or K-TIRADS [area under the curve: 0.79 (95% CI: 0.74-0.83) vs. 0.69 (95% CI: 0.64-0.75), P=0.046; 0.79 (95% CI: 0.74-0.83) vs. 0.66 (95% CI: 0.60-0.71), P=0.041, respectively]. The R-TIRADS had the highest sensitivity [0.746 (95% CI: 0.689-0.803)], followed by the K-TIRADS [0.399 (95% CI: 0.335-0.463), P=0.000] and ACR TIRADS [0.377 (95% CI: 0.314-0.441), P=0.000]. The R-TIRADS enables radiologists to diagnose thyroid nodules efficiently, and the number of unnecessary fine-needle aspirations can be considerably reduced.

Comparison of the diagnostic performance and clinical role of different ultrasound-based thyroid malignancy risk stratification systems for medullary thyroid carcinoma.

This study sought to investigate the applicability of different ultrasound (US) thyroid risk stratification systems in diagnosing medullary thyroid carcinoma (MTC) and determining the need for biopsy. In total, 34 MTC nodules, 54 papillary thyroid carcinoma (PTC) nodules, and 62 benign thyroid nodules were examined in this study. All the diagnoses were histopathologically confirmed postoperatively. All the thyroid nodule sonographic features were recorded and categorized by 2 independent reviewers according to the Thyroid Imaging Reporting and Data System (TIRADS) of the American College of Radiology (ACR), the American Thyroid Association (ATA) guidelines, the European Thyroid Association (EU) TIRADS, the Kwak-TIRADS, and the Chinese TIRADS (C-TIRADS). The sonographic differences and risk stratifications of the MTCs, PTCs, and benign thyroid nodules were analyzed. The diagnostic performance and recommended biopsy rates for each classification system were evaluated. The risk stratifications of MTCs were all higher than the benign thyroid nodules (P<0.01) and lower than PTCs (P<0.01) with each classification system. Hypoechogenicity and malignant marginal features were independent risk factors for identifying malignant thyroid nodules, and the area under the receiver operating characteristic curve (AUC) for identifying MTCs was lower than that for identifying PTCs (0.873 vs. 0.954, respectively). The AUCs, sensitivity, specificity, positive predictive values, negative predictive values, and accuracy values of the 5 systems for MTC were all lower than those for PTC. The best cut-off values for diagnosing MTC were TIRADS (TR) 4 in the ACR-TIRADS, intermediate suspicion in the ATA guidelines, TR 4 in EU-TIRADS, and TR 4b in both the Kwak-TIRADS and the C-TIRADS. The Kwak-TIRADS had the highest recommended biopsy rate for MTCs (97.1%), followed by the ATA guidelines, the EU-TIRADS (88.2%), the C-TIRADS (85.3%), and the ACR-TIRADS (79.4%). The US-based thyroid malignancy risk stratification systems analyzed in this study were able to satisfactorily identify MTC and recommend biopsy, but the diagnostic performance of these systems for MTC was not as good as that for PTC.

Multimodality US versus Thyroid Imaging Reporting and Data System Criteria in Recommending Fine-Needle Aspiration of Thyroid Nodules.

Background Current guidelines recommend the use of conventional US for risk stratification and management of thyroid nodules. However, fine-needle aspiration (FNA) is often recommended in benign nodules. Purpose To compare the diagnostic performance of multimodality US (including conventional US, strain elastography, and contrast-enhanced US [CEUS]) with the American College of Radiology Thyroid Imaging Reporting and Data System (TI-RADS) in the recommendation of FNA for thyroid nodules to reduce unnecessary biopsies. Materials and Methods In this prospective study, 445 consecutive participants with thyroid nodules from nine tertiary referral hospitals were recruited between October 2020 and May 2021. With univariable and multivariable logistic regression, the prediction models incorporating sonographic features, evaluated with interobserver agreement, were constructed and internally validated with bootstrap resampling technique. In addition, discrimination, calibration, and decision curve analysis were performed. Results A total of 434 thyroid nodules confirmed at pathologic analysis (259 malignant thyroid nodules) in 434 participants (mean age, 45 years ± 12 [SD]; 307 female participants) were included. Four multivariable models incorporated participant age, nodule features at US (proportion of cystic components, echogenicity, margin, shape, punctate echogenic foci), elastography features (stiffness), and CEUS features (blood volume). In recommending FNA in thyroid nodules, the highest area under the receiver operating characteristic curve (AUC) was 0.85 (95% CI: 0.81, 0.89) for the multimodality US model, and the lowest AUC was 0.63 (95% CI: 0.59, 0.68) for TI-RADS (P < .001). At the 50% risk threshold, 31% (95% CI: 26, 38) of FNA procedures could be avoided with multimodality US compared with 15% (95% CI: 12, 19) with TI-RADS (P < .001). Conclusion Multimodality US had better performance in recommending FNA to avoid unnecessary biopsies than the TI-RADS. Clinical trial registration no. NCT04574258 © RSNA, 2023 Supplemental material is available for this article.

Diagnostic value of a dynamic artificial intelligence ultrasonic intelligent auxiliary diagnosis system for benign and malignant thyroid nodules in patients with Hashimoto thyroiditis.

A dynamic artificial intelligence (AI) ultrasonic intelligent assistant diagnosis system (dynamic AI) is a joint application of AI technology and medical imaging, which can conduct real-time synchronous dynamic analysis of nodules from multiple sectional views with different angles. This study explored the diagnostic value of dynamic AI for benign and malignant thyroid nodules in patients with Hashimoto thyroiditis (HT) and its significance in guiding surgical treatment strategies. Data of 487 patients (154 with and 333 without HT) with 829 thyroid nodules who underwent surgery were collected. Differentiation of benign and malignant nodules was performed using dynamic AI, and diagnostic effects (specificity, sensitivity, negative predictive value, positive predictive value, accuracy, misdiagnosis rate and missed diagnosis rate) was assessed. Differences in diagnostic efficacy were compared among AI, preoperative ultrasound based on the American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS), and fine needle aspiration cytology (FNAC) diagnoses. The accuracy, specificity and sensitivity of dynamic AI reached 88.06%, 80.19%, and 90.68%, respectively; besides, there was consistency with postoperative pathological consequences (κ=0.690; P<0.001). The diagnostic efficacy of dynamic AI was equivalent between patients with and without HT, and there were no significant differences in sensitivity, specificity, accuracy, positive predictive value, negative predictive value, missed diagnosis rate, and misdiagnosis rate. In patients with HT, dynamic AI had significantly higher specificity and a lower misdiagnosis rate than did preoperative ultrasound based on the ACR TI-RADS (P<0.05). Compared with FNAC diagnosis, dynamic AI had a significantly higher sensitivity and a lower missed diagnosis rate (P<0.05). Dynamic AI possessed an elevated diagnostic worth of malignant and benign thyroid nodules in patients with HT, which can provide a new method and valuable information for the diagnosis and development of management strategy of patients.

Thyroid malignancy in children: where does it locate?

As far as we know, in English literature, a limited number of studies has examined the relationship between the location of the nodule and malignancy risk. The studies were performed with adults and their results were mainly inconsistent. We aim to evaluate the potential association between the location of the thyroid nodules and risk for malignancy in the pediatric population. Patients younger than 18 years old with a pathological diagnosis were included. Nodules were divided into 5 categories according to the Thyroid Imaging Reporting and Data System (TI-RADS) algorithm. The location of the nodules was recorded: Right lobe, left lobe, isthmus, upper pole, lower pole, and middle. Thyroid glands were divided into 3 equal longitudinal areas to define upper, lower, and middle portions. Ninety-seven nodules of 103 children were included. The mean age of the population was 14.9 ± 2.51 years (7-18 years). Eighty-one participants were female (83.5%) and 16 male (16.5%). Fifty nodules were benign (51.5%) and 47 nodules were malignant (48.5%). We did not detect a significant correlation between the risk of malignancy and location of the nodule as right or left lobes or isthmus (P = 0.38). Rate of malignant nodules were significantly higher in middle lobe (23%, P = 0.002). Being located at middle part of thyroid gland increases the possibility of malignancy 11.3 times (OR = 11.3, P = 0.006). Nodule location can be used as a predictor for thyroid malignancy in pediatric patients, similar to adults. Middle lobe location increases the risk of malignancy. Using nodule location along with TI-RADS categorization can increase the efficacy of malignancy prediction.

Diagnostic performance of the thyroid imaging reporting and data system improved by color-coded acoustic radiation force pulse imaging.

To explore the value of color-coded virtual touch tissue imaging (CCV) using acoustic radiation force pulse technology (ARFI) in diagnosing malignant thyroid nodules. Images including 189 thyroid nodules were collected as training samples and a binary logistic regression analysis was used to calculate regression coefficients for Thyroid Imaging Reporting and Data System (TI-RADS) and CCV. An integrated prediction model (TI-RADS+CCV) was then developed based on the regression coefficients. Another testing dataset involving 40 thyroid nodules was used to validate and compare the diagnostic performance of TI-RADS, CCV, and the integrated predictive models using the receiver operating characteristic (ROC) curves. Both TI-RADS and CCV are independent predictors. The diagnostic performance advantage of CCV is insignificant compared to TI-RADS (P = 0.61). However, the diagnostic performance of the integrated prediction model is significantly higher than that of TI-RADS or CCV (all P < 0.05). Applying to the validation image dateset, the integrated predictive model yields an area under the curve (AUC) of 0.880. Developing a new predictive model that integrates the regression coefficients calculated from TI-RADS and CCV enables to achieve the superior performance of thyroid nodule diagnosis to that of using TI-RADS or CCV alone.

AIUM Practice Parameter for the Performance and Interpretation of Diagnostic Ultrasound of the Thyroid and Extracranial Head and Neck.

AIUM Practice Parameter for the Performance and Interpretation of Diagnostic Ultrasound of the Thyroid and Extracranial Head and Neck.

Fine-Needle Aspiration Biopsy Evaluation-Oriented Thyroid Carcinoma Auxiliary Diagnosis.

Thyroid carcinoma is one of the most common diseases with an increasing incidence worldwide in recent years. In clinical diagnosis, medical practitioners normally take a preliminary thyroid nodule grading so that highly suspected thyroid nodules can be taken into the fine-needle aspiration (FNA) biopsy to evaluate the malignancy. However, subjective misinterpretations might lead to ambiguous risk stratification of thyroid nodules and unnecessary FNA biopsy. We propose a thyroid carcinoma auxiliary diagnosis method for fine-needle aspiration biopsy evaluation. Through integration of several deep learning models into a multibranch network for thyroid nodule risk stratification in the Thyroid Imaging Reporting and Data System (TIRADS) with pathological features and cascading of a discriminator, our proposed method provides an intelligent auxiliary diagnosis to assist medical practitioners in determining the necessity for further FNA. Experimental results revealed that not only was the rate at which nodules are falsely diagnosed as malignant nodules effectively reduced, which avoids the unnecessary high cost and pain of aspiration biopsy, but also previously missing detected cases were identified with high possibility. By comparing the physicians' diagnosis alone with machine-assisted diagnosis, physicians' diagnostic performance improved with the aid of our proposed method, illustrating that our model can be very helpful in clinical practice. Our proposed method might help medical practitioners avoid subjective interpretations and inter-observer variability. For patients, reliable diagnosis is provided and unnecessary painful diagnostics can be avoided. In other superficial organs such as metastatic lymph nodes and salivary gland tumors, the proposed method might also provide a reliable auxiliary diagnosis for risk stratification.

Differential regional importance mapping for thyroid nodule malignancy prediction with potential to improve needle aspiration biopsy sampling reliability.

Existing guidelines for ultrasound-guided fine-needle aspiration biopsy lack specifications on sampling sites, but the number of biopsies improves diagnostic reliability. We propose the use of class activation maps (CAMs) and our modified malignancy-specific heat maps that locate important deep representations of thyroid nodules for class predictions. We applied adversarial noise perturbations to the segmented concentric "hot" nodular regions of equal sizes to differentiate regional importance for the malignancy diagnostic performances of an accurate ultrasound-based artificial intelligence computer-aided diagnosis (AI-CADx) system using 2,602 retrospectively collected thyroid nodules with known histopathological diagnosis. The AI system demonstrated high diagnostic performance with an area under the curve (AUC) value of 0.9302 and good nodule identification capability with a median dice coefficient >0.9 when compared to radiologists' segmentations. Experiments confirmed that the CAM-based heat maps reflect the differentiable importance of different nodular regions for an AI-CADx system to make its predictions. No less importantly, the hot regions in malignancy heat maps of ultrasound images in comparison with the inactivated regions of the same 100 malignant nodules randomly selected from the dataset had higher summed frequency-weighted feature scores of 6.04 versus 4.96 rated by radiologists with more than 15 years of ultrasound examination experience according to widely used ultrasound-based risk stratification American College of Radiology (ACR) Thyroid Imaging Reporting and Data System (TI-RADS) in terms of nodule composition, echogenicity, and echogenic foci, excluding shape and margin attributes, which could only be evaluated on the whole rather than on the sub-nodular component levels. In addition, we show examples demonstrating good spatial correspondence of highlighted regions of malignancy heat map to malignant tumor cell-rich regions in hematoxylin and eosin-stained histopathological images. Our proposed CAM-based ultrasonographic malignancy heat map provides quantitative visualization of malignancy heterogeneity within a tumor, and it is of clinical interest to investigate in the future its usefulness to improve fine-needle aspiration biopsy (FNAB) sampling reliability by targeting potentially more suspicious sub-nodular regions.

Colour‐based segmentation using FCM and K‐means clustering for 3D thyroid gland state image classification using deep convolutional neural network structure

AbstractThyroid cancer is a rare disease that often goes undetected until it reaches advanced stages. This study presents a novel approach for identifying Thyroid Imaging Reporting and Data System (TI‐RADS) stages of thyroid nodules using a deep convolutional neural network (Deep‐CNN) model. Our method incorporates pre‐processing, segmentation and feature extraction using colour based fuzzy‐c‐means and K‐means clustering, followed by deep learning classification. We demonstrate the efficacy of our proposed approach by achieving a success rate of 87% for classifying TI‐RADS1, TI‐RADS2, TI‐RADS3, TI‐RADS4 and TI‐RADS5 stages, outperforming other state‐of‐the‐art models. Our study fills an important gap in the literature, as previous studies have mainly focused on the margins of thyroid nodules rather than their calcium flecks. Our results offer promise for improving the accuracy and efficiency of thyroid cancer detection and management.

Diagnostic value of ACR TI-RADS combined with three-dimensional shear wave elastography in ACR TI-RADS 4 and 5 thyroid nodules.

Three-dimensional shear wave elastography (3D-SWE) is a promising method in distinguishing benign and malignant thyroid nodules. By combining with conventional method, it may further improve the diagnostic value. The study aimed to assess the diagnostic value of American College of Radiology (ACR) thyroid imaging reporting and data system (TI-RADS) combined with 3D-SWE in ACR TI-RADS 4 and 5 thyroid nodules. All nodules were examined by conventional ultrasonography, ACR TI-RADS classification, and 3D-SWE examination. Conventional ultrasonography was used to observe the location, size, shape, margin, echogenicity, taller-than-wide sign, microcalcification, and blood flow of thyroid nodules, and then ACR TI-RADS classification was performed. The Young's modulus values (3D-C-Emax, 3D-C-Emean, and elastography standard deviation [3D-C-Esd]) were measured on the reconstructed coronal plane images. According to the receiver operating characteristic (ROC) curve, the best diagnostic efficiency among 3D-C-Emax, 3D-C-Emean, and 3D-C-Esd was selected and the cut-off threshold was calculated. According to the surgical pathology, they were divided into benign group and malignant group. And appropriate statistical methods such as t -test and Mann-Whitney U test were used to compare the difference between the two groups. On this basis, 3D-SWE combined with conventional ACR TI-RADS was reclassified as combined ACR TI-RADS to determine benign or malignant thyroid nodules. Of the 112 thyroid nodules, 62 were malignant and 50 were benign. The optimal cut-off value of three-dimensional maximum Young's modulus in coronal plane (3D-C-Emax) was 51.5 kPa and the area under the curve (AUC) was 0.798. The AUC, sensitivity, specificity, and accuracy of conventional ACR TI-RADS were 0.828, 83.9%, 66.0%, and 75.9%, respectively. The AUC, sensitivity, specificity, and accuracy of combined ACR TI-RADS were 0.845, 90.3%, 66.0%, and 79.5%, respectively. The difference between the two AUC values was statistically significant. Combined ACR TI-RADS has higher diagnostic efficiency than conventional ACR TI-RADS. The sensitivity and accuracy of combined ACR TI-RADS showed significant improvements. It can be used as an effective method in the diagnosis of thyroid nodules.

Diagnostic and therapeutic performances of three score-based Thyroid Imaging Reporting and Data Systems after application of equal size thresholds.

The aim of this study was to explore the diagnostic and therapeutic performances of the artificial intelligence (AI), American College of Radiology (ACR), and Kwak Thyroid Imaging Reporting and Data Systems (TIRADSs) using the size thresholds for fine needle aspiration (FNA) and follow-up defined in the ACR TIRADS. This retrospective study included 3,833 consecutive thyroid nodules identified in 2,590 patients from January 2010 to August 2017. Ultrasound (US) features were reviewed using the 2017 white paper of the ACR TIRADS. US categories were assigned according to the ACR/AI and Kwak TIRADS. We applied the thresholds for FNA and follow-up defined in the ACR TIRADS to the Kwak TIRADS. The diagnostic and therapeutic performances were calculated and compared using the McNemar or DeLong methods. The AI TIRADS had higher specificity, accuracy, and area under the curve (AUC) than did the ACR and Kwak TIRADS (specificity: 64.6% vs. 57.4% and 52.69%; accuracy: 78.5% vs. 75.4% and 73.0%; AUC: 88.2% vs. 86.6% and 86.0%; all P values <0.05). Meanwhile, the AI TIRADS had a lower FNA rate (FNAR), unnecessary FNA rate (UFR), and follow-up rate (FUR) than did the ACR and Kwak TIRADS using the size thresholds of the ACR TIRADS (specificity: 30.9% vs. 34.4% and 36.9%; accuracy: 41.1% vs. 47.8% and 48.7%; AUC: 34.2% vs. 37.7% and 41.0%; all P values <0.05). In addition, the Kwak TIRADS incorporating the size thresholds of the ACR TIRADS was almost similar to the ACR TIRADS in diagnostic and therapeutical performance. The ACR TIRADS can be simplified, which potentially enhances its diagnostic and therapeutic performance. The method of score-based TIRADS (counting in the Kwak TIRADS and weighting in the ACR and AI TIRADS) might not determine the diagnostic and therapeutic performances of the TIRADS. Thus, we propose choosing a straightforward and practical TIRADS in daily practice.

A Comprehensive Study on the Diagnosis and Management of Noninvasive Follicular Thyroid Neoplasm with Papillary-Like Nuclear Features.

Background: Since the noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTPs) was introduced in 2016, most retrospective studies have included cases diagnosed as encapsulated follicular variant of papillary thyroid carcinoma. We investigate a cohort diagnosed with NIFTP at resection. Methods: Retrospective institutional cohort of NIFTP from 2016 to 2022, including clinical, cytological, and molecular data for 319 cases (6.6% of thyroid surgeries, 183 cases as NIFTP-only). Results: The patient cohort had unifocal or multifocal thyroid nodules. Female:male ratio was 2.7:1, mean age was 52 years and median NIFTP size was 2.1 cm. NIFTP was associated with multiple nodules in 23% patients (n = 73) and 12% of NIFTP were multifocal (n = 39). Fine needle aspiration (FNA) of NIFTP (n = 255) were designated as nondiagnostic = 5%, benign = 13%, atypia of undetermined significance/follicular lesion of undetermined significance (AUS/FLUS) = 49%, follicular neoplasm/suspicious for follicular neoplasm (FN/SFN) = 17%, suspicious for malignancy = 12%, or malignant = 4%. Molecular alterations were identified in 93% (n = 114), RAS or RAS-like. Thyroid Imaging Reporting and Data System (TI-RADS) score 4 was recorded in 50% of NIFTP, followed by scores 3 and 5 (26% and 20%, respectively). We also investigated the factors associated with extent of surgery. In our NIFTP-only group (n = 183), 66% were identified after hemithyroidectomy (HT) and 34% after total thyroidectomy (TT). On univariate analysis, TT patients demonstrated higher Bethesda category by FNA, more often had aberrant preoperative thyroid function, and/or underwent an FNA of additional nodule(s). With multivariable regression, Bethesda V NIFTP, in the presence of other nodules being evaluated by FNA and aberrant preoperative thyroid function, independently predicts TT. Bethesda II NIFTP correlated significantly with HT. Fifty-two patients (28%) with NIFTP-only had at least one postoperative surveillance ultrasound. In the NIFTP-only cohort, no HT patients had completion thyroidectomy or received postoperative radioactive iodine. No recurrence or metastases were recorded with median follow-up of 35 months (6-76 months; n = 120). Conclusions: Given this large cohort of NIFTP, including a large subset of isolated NIFTP-only, some with >6 years of follow-up and no tumor recurrences, consensus practical guidelines are needed for adequate postoperative management. Given the American Thyroid Association (ATA) provides guidelines for management of low-risk malignancies, guidance regarding that for borderline/biologically uncertain tumors, including NIFTP, is a reasonable next step.