Diagnostic performance evaluation of different TI-RADS using ultrasound computer-aided diagnosis of thyroid nodules: An experience with adjusted settings

Improving the diagnostic strategy for thyroid nodules: a combination of artificial intelligence-based computer-aided diagnosis system and shear wave elastography

PURPOSE

Thyroid nodules are highly prevalent in the general population, posing a clinical challenge in accurately distinguishing between benign and malignant cases. This study aimed to investigate the diagnostic performance of different strategies, utilizing a combination of a computer-aided diagnosis system (AmCAD) and shear wave elastography (SWE) imaging, to effectively differentiate benign and malignant thyroid nodules in ultrasonography.

METHODS

A total of 126 thyroid nodules with pathological confirmation were prospectively included in this study. The AmCAD was utilized to analyze the ultrasound imaging characteristics of the nodules, while the SWE was employed to measure their stiffness in both transverse and longitudinal thyroid scans. Twelve diagnostic patterns were formed by combining AmCAD diagnosis and SWE values, including isolation, series, parallel, and integration. The diagnostic performance was assessed using the receiver operating characteristic curve and area under the curve (AUC). Sensitivity, specificity, accuracy, missed malignancy rate, and unnecessary biopsy rate were also determined.

RESULTS

Various diagnostic schemes have shown specific advantages in terms of diagnostic performance. Overall, integrating AmCAD with SWE imaging in the transverse scan yielded the most favorable diagnostic performance, achieving an AUC of 72.2% (95% confidence interval (CI): 63.0-81.5%), outperforming other diagnostic schemes. Furthermore, in the subgroup analysis of nodules measuring <2 cm or 2-4 cm, the integrated scheme consistently exhibited promising diagnostic performance, with AUCs of 74.2% (95% CI: 61.9-86.4%) and 77.4% (95% CI: 59.4-95.3%) respectively, surpassing other diagnostic schemes. The integrated scheme also effectively addressed thyroid nodule management by reducing the missed malignancy rate to 9.5% and unnecessary biopsy rate to 22.2%.

CONCLUSION

The integration of AmCAD and SWE imaging in the transverse thyroid scan significantly enhances the diagnostic performance for distinguishing benign and malignant thyroid nodules. This strategy offers clinicians the advantage of obtaining more accurate clinical diagnoses and making well-informed decisions regarding patient management.

[Standardized acquisition and documentation of cine loops on conventional thyroid ultrasound]

Ultrasound is the basic imaging method for the assessment of the thyroid gland. Due to the high prevalence of structural disease, the examination procedure is used very frequently in Germany, in many cases in the context of follow-up. The assessment of thyroid pathologies and their dynamics is subjected to relevant inter- and intraobserver variability. Findings that were not identified during live ultrasound cannot be assessed retrospectively. Applying an SOP for the acquisition and documentation of standardized video sequences of ultrasound images (so-called cine loops), allows for a secondary retrospective evaluation of the thyroid gland, taking into account previously acquired images analogous to other cross-sectional imaging methods such as CT or MRI. The cine loops can be acquired by non-physician personnel, stored to the local PACS and used for educational and research purposes.

Monitoring Thyrotropin in Veterans With Thyroid Nodules

Background

After the initial thyroid nodule diagnosis, a patient's thyrotropin is often monitored. However, the American Thyroid Association guidelines do not offer recommendations for follow-up thyrotropin testing for patients with thyroid nodules who have no history of conditions or known medications that affect thyroid hormone levels.

Methods

At the Veterans Affairs Dayton Healthcare System in Ohio, we conducted a retrospective chart review from January 2010 to December 2016 of 100 patients diagnosed with ≥ 1 thyroid nodule on imaging studies who had normal blood thyrotropin at the time of nodule diagnosis. The thyrotropin value was studied at and after diagnosis. A 95% CI was determined for the true population rate of patients with an abnormal thyrotropin at their most recent testing. χ2 tests for categorical variables and independent sample t tests for continuous variables were used to compare the abnormal and normal most recent thyrotropin groups.

Results

One hundred patients (male [83%], White race [82%]) with normal thyrotropin at nodule diagnosis had thyrotropin monitoring for a mean (SD) of 5.7 (2.5) years. Six of 100 patients (6%; 95% CI, 2.5%-12.7%) developed abnormal thyrotropin levels in a mean (SD) of 6.9 (3.1) years. When comparing the 6 patients with abnormal thyrotropin vs the 94 with normal thyrotropin, there were no significant differences in sex (P = .99), race (P = .55), age at diagnosis (P = .12), initial thyrotropin level (P = .24), most recent thyrotropin level (P = .98), or time from diagnosis to most recent thyrotropin level (P = .23).

Conclusions

This study found no significant change in thyrotropin levels over time in patients with thyroid nodules and no history of medical conditions or medications known to affect thyrotropin levels. Monitoring thyrotropin over time may not be required in these patients. More studies are needed to provide additional data on thyrotropin monitoring for thyroid nodules so that clinicians can make evidence-based decisions.

Comparison of the diagnostic accuracy of K-TIRADS and EU-TIRADS guidelines for detection of thyroid malignancy on ultrasound

INTRODUCTION

This retrospective study compared the diagnostic accuracy of histopathologically proven thyroid nodules between the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) and the European Thyroid Imaging Reporting and Data System (EU-TIRADS) guidelines for the management of thyroid nodules characterized by ultrasonography.

MATERIAL AND METHODS

For thyroid nodules resected from 2018 to 2021 at our institution, static ultrasound images of each nodule were reviews and stratify into both systems. Agreement between above two classifications was compared based on histopathological results.

RESULTS

A total 403 thyroid nodules from 213 patients were evaluated. Each nodule was characterized by ultrasonography and stratified into K-TIRADS and EU-TIRADS classifications. The diagnostic accuracy was as follows: K-TIRADS sensitivity 85.3% (95% CI, 78.7-91.9) specificity 76.8% (95% CI, 72.1-81.7), positive predictive value 57.8% (95% CI, 50.1-65.4) negative predictive value 93.4% (95% CI, 90.3-96.5); EU-TIRADS sensitivity 86.2% (95% CI, 79.7-92.7), specificity 75.5% (95% CI, 70.6-80.4), positive predictive value 56.6% (95% CI, 49.1-64.2), negative predictive value 93.7% (95% CI, 90.6-96.8). Excellent agreement in risk stratifications between both systems was found (kappa 0.86).

CONCLUSIONS

Ultrasound thyroid nodules categorized by either by K-TIRADS or EU-TIRADS are useful to predicting malignancy and perform risk stratification with similar results.

IMPLICATIONS FOR PRACTICE

This study confirmed that both K-TIRADS and EU-TIRADS have high diagnostic accuracy and both guidelines may be used as an effective tool for management planning of patients with thyroid nodules in daily clinical practice.

Classification regularized dimensionality reduction improves ultrasound thyroid nodule diagnostic accuracy and inter-observer consistency

PROBLEM

Convolutional Neural Networks (CNNs) for medical image analysis usually only output a probability value, providing no further information about the original image or inter-relationships between different images. Dimensionality Reduction Techniques (DRTs) are used for visualization of high dimensional medical image data, but they are not intended for discriminative classification analysis.

AIM

We develop an interactive phenotype distribution field visualization system for medical images to accurately reflect the pathological characteristics of lesions and their similarity to assist radiologists in diagnosis and medical research.

METHODS

We propose a novel method, Classification Regularized Uniform Manifold Approximation and Projection (UMAP) referred as CReUMAP, combining the advantages of CNN and DRT, to project the extracted feature vector fused with the malignant probability predicted by a CNN to a two-dimensional space, and then apply a spatial segmentation classifier trained on 2614 ultrasound images for prediction of thyroid nodule malignancy and guidance to radiologists.

RESULTS

The CReUMAP embedding correlates well with the TI-RADS categories of thyroid nodules. The parametric version that embeds external test dataset of 303 images in presence of the training data with known pathological diagnosis improves the benign and malignant nodule diagnostic accuracy (p-value = 0.016) and confidence (p-value = 1.902 × 10^-6) of eight radiologists of different experience levels significantly as well as their inter-observer agreements (kappa≥0.75). CReUMAP achieve 90.8% accuracy, 92.1% sensitivity and 88.6% specificity in test set.

CONCLUSION

CReUMAP embedding is well correlated with the pathological diagnosis of thyroid nodules, and helps radiologists achieve more accurate, confident and consistent diagnosis. It allows a medical center to generate its locally adapted embedding using an already-trained classification model in an updateable manner on an ever-growing local database as long as the extracted feature vectors and predicted diagnostic probabilities of the correspondent classification model can be outputted.

Combined Shear Wave Elastography and EU TIRADS in Differentiating Malignant and Benign Thyroid Nodules

Although multimodal ultrasound approaches have been suggested to potentially improve the diagnosis of thyroid cancer; the diagnostic utility of the combination of SWE and malignancy-risk stratification systems remains vague due to the lack of standardized criteria. The purpose of the study was to assess the diagnostic value of the combination of grey scale ultrasound assessment using EU TIRADS and shear wave elastography. 121 patients (126 nodules−81 benign; 45 malignant) underwent grey scale ultrasound and SWE imaging of nodules between 0.5 cm and 5 cm prior to biopsy and/or surgery. Nodules were analyzed based on size stratifications: <1 cm (n = 43); 1−2 cm (n = 52) and >2 cm (n = 31) and equivocal cytology status (n = 52), and diagnostic performance assessments were conducted. The combination of EU TIRADS with SWE using the SD parameter; maintained a high sensitivity and significantly improved the specificity of sole EU TIRADS for nodules 1−2 cm (SEN: 72.2% vs. 88.9%, p > 0.05; SPEC: 76.5% vs. 55.9%, p < 0.01) and >2 cm (SEN: 71.4% vs. 85.7%, p > 0.05; SPEC: 95.8% vs. 62.5%, p < 0.01). For cytologically-equivocal nodules; the combination with the SWE minimum parameter resulted in a significant reduction in sensitivity with increased specificity (SEN: 60% vs. 80%; SPEC: 83.4% vs. 37.8%; all p < 0.05). SWE in combination with EU TIRADS is diagnostically efficient in discriminating nodules > 1 cm but is not ideal for discriminating cytologically-equivocal nodules.

Concordance between TIRADS and Cytology in Thyroid Nodule

Introduction

Palpable thyroid nodules are stated in 4 to 7% of individuals. This study was designed to evaluate the relation of Thyroid Imaging Reporting and Data System (TIRADS) and fine-needle aspiration (FNA) based cytology reports in patients with thyroid nodules.

Materials and Methods

In this retrospective cross-sectional study, individuals with thyroid nodules who were selected for ultrasonographic-guided FNA enrolled in this study. Demographic data, radiologic assessment, and cytology report were gathered based on hospital medical records. TIRADS grading of the nodules was assessed for each nodule. Cytology was performed on all samples. Sensitivity and specificity were calculated by comparing cytology with ACR-TIRADS and also cytology with TIRADS 4-5 cut-off point as a radiologic malignant lesion.

Results

172 patients were studied, 151 of whom were female and 21 were male. The mean age of the patients was 49.46 years. Most of the patients had TIRADS 4 (53.5%) followed by 3 (31.4%), and 5 (11.6%). 151 patients (87.8%) had a benign lesion in cytology. Of them, 118 had colloid nodules. There was a statistically significant relation between TIRADS and cytology (p-value<0.001). Sensitivity, specificity, AUC, and positive and negative predictive value for ACR-TIRADS classification were 76.19%, 47.54%, 0.619, 20.00%, and 92.06%, respectively. These values for cut-off "4-5" classification was 86.36%, 38.00%, 0.622, 16.96%, and 95.00%.

Conclusions

According to the significant concordance between TIRADS and cytology, as shown in the results of our study, it seems that TIRADS could be used to decrease the amount of unnecessary FNA in individuals with thyroid nodules.

Differential diagnosis and feature visualization for thyroid nodules using computer-aided ultrasonic diagnosis system: initial clinical assessment

BACKGROUND

To assess the diagnostic efficacy of the computer-aided ultrasonic diagnosis system (CAD system) in differentiating benign and malignant thyroid nodules.

METHODS

The images of 296 thyroid nodules were included in validation sets. The diagnostic efficacy of the CAD system was compared with that of junior physicians and senior physicians, as well as that of the combination diagnosis of the CAD system with junior physicians. The diagnostic efficacy of the CAD system for different sizes of thyroid nodules was compared.

RESULTS

The diagnostic sensitivity and accuracy of the CAD system were higher than those of junior physicians (83.4% vs. 72.2%, 73.0% vs. 69.6%), but the diagnostic specificity of the CAD system was lower than that of junior physicians (62.1% vs. 66.9%). The diagnostic accuracy of the CAD system was lower than that of senior physicians (73.0% vs. 83.8%). However, the combination diagnosis of the CAD system with junior physicians had higher accuracy (81.8%) and AUC (0.842) than those of either the CAD system or junior physicians alone, and comparable diagnostic performance with those of senior physicians. The Kappa was 0.635 in the combination diagnosis of the CAD system with junior physicians, showing good consistency with the pathological results. The accuracy (76.4%) of the CAD system was the highest for nodules of 1-2 cm.

CONCLUSION

The CAD system can effectively assist physicians to identify malignant and benign thyroid nodules, reduce the overdiagnosis and overtreatment of thyroid nodules, avoid unnecessary invasive fine needle aspiration, and improve the diagnostic accuracy of junior physicians.

The Use of Internet of Things and Cloud Computing Technology in the Performance Appraisal Management of Innovation Capability of University Scientific Research Team

This study aims to speed up the progress of scientific research projects in colleges and universities, continuously improve the innovation ability of scientific research teams in colleges and universities, and optimize the current management methods of performance appraisal of college innovation ability. Firstly, the needs of the innovation performance evaluation system are analyzed, and the corresponding innovation performance evaluation index system of scientific research team is constructed. Secondly, the Internet of Things (IoT) combines the Field Programmable Gate Array (FPGA) to build an innovation capability performance appraisal management terminal. Thirdly, the lightweight deep network has been built into the innovation ability performance assessment management network of university scientific research teams, which relates to the innovation performance assessment index system of scientific research teams. Finally, the system performance is tested. The results show that the proposed method has different degrees of compression for MobileNet, which can significantly reduce the network computation and retain the original recognition ability. Models whose Floating-Point Operations (FLOPs) are reduced by 70% to 90% have 3.6 to 14.3 times fewer parameters. Under different pruning rates, the proposed model has higher model compression rate and recognition accuracy than other models. The results also show that the output of the results is closely related to the interests of the research team. The academic influence score of Team 1 is 0.17, which is the highest among the six groups in this experimental study, indicating that Team 1 has the most significant academic influence. These results provide certain data support and method reference for evaluating the innovation ability of scientific research teams in colleges and universities and contribute to the comprehensive development of efficient scientific research teams.

Artificial Intelligence (AI) Tools for Thyroid Nodules on Ultrasound, From the AJR Special Series on AI Applications

Artificial intelligence (AI) methods for evaluating thyroid nodules on ultrasound have been widely described in the literature, with reported performance of AI tools matching or in some instances surpassing radiologists. As these data have accumulated, products for classification and risk stratification of thyroid nodules on ultrasound have become commercially available. This article reviews FDA-approved products currently on the market, with a focus on product features, reported performance, and considerations for implementation. The products perform risk stratification primarily using the Thyroid Imaging Reporting and Data System (TI-RADS), though may provide additional prediction tools independent of TI-RADS. Key issues in implementation include integration with radiologist interpretation, impact on workflow and efficiency, and performance monitoring. AI applications beyond nodule classification, including report construction and incidental findings follow-up, are also described. Anticipated future directions of research and development in AI tools for thyroid nodules are highlighted.

Multi-channel convolutional neural network architectures for thyroid cancer detection

Early detection of malignant thyroid nodules leading to patient-specific treatments can reduce morbidity and mortality rates. Currently, thyroid specialists use medical images to diagnose then follow the treatment protocols, which have limitations due to unreliable human false-positive diagnostic rates. With the emergence of deep learning, advances in computer-aided diagnosis techniques have yielded promising earlier detection and prediction accuracy; however, clinicians' adoption is far lacking. The present study adopts Xception neural network as the base structure and designs a practical framework, which comprises three adaptable multi-channel architectures that were positively evaluated using real-world data sets. The proposed architectures outperform existing statistical and machine learning techniques and reached a diagnostic accuracy rate of 0.989 with ultrasound images and 0.975 with computed tomography scans through the single input dual-channel architecture. Moreover, the patient-specific design was implemented for thyroid cancer detection and has obtained an accuracy of 0.95 for double inputs dual-channel architecture and 0.94 for four-channel architecture. Our evaluation suggests that ultrasound images and computed tomography (CT) scans yield comparable diagnostic results through computer-aided diagnosis applications. With ultrasound images obtained slightly higher results, CT, on the other hand, can achieve the patient-specific diagnostic design. Besides, with the proposed framework, clinicians can select the best fitting architecture when making decisions regarding a thyroid cancer diagnosis. The proposed framework also incorporates interpretable results as evidence, which potentially improves clinicians' trust and hence their adoption of the computer-aided diagnosis techniques proposed with increased efficiency and accuracy.