Elastography and Doppler May Bring a New Perspective to TIRADS, Altering Conventional Ultrasonography Dominance

Comparison of Explainable Artificial Intelligence Model and Radiologist Review Performances to Detect Breast Cancer in 752 Patients

OBJECTIVES

Breast cancer is a type of cancer caused by the uncontrolled growth of cells in the breast tissue. In a few cases, erroneous diagnosis of breast cancer by specialists and unnecessary biopsies can lead to various negative consequences. In some cases, radiologic examinations or clinical findings may raise the suspicion of breast cancer, but subsequent detailed evaluations may not confirm cancer. In addition to causing unnecessary anxiety and stress to patients, such diagnosis can also lead to unnecessary biopsy procedures, which are painful, expensive, and prone to misdiagnosis. Therefore, there is a need for the development of more accurate and reliable methods for breast cancer diagnosis.

METHODS

In this study, we proposed an artificial intelligence (AI)-based method for automatically classifying breast solid mass lesions as benign vs malignant. In this study, a new breast cancer dataset (Breast-XD) was created with 791 solid mass lesions belonging to 752 different patients aged 18 to 85 years, which were examined by experienced radiologists between 2017 and 2022.

RESULTS

Six classifiers, support vector machine (SVM), K-nearest neighbor (K-NN), random forest (RF), decision tree (DT), logistic regression (LR), and XGBoost, were trained on the training samples of the Breast-XD dataset. Then, each classifier made predictions on 159 test data that it had not seen before. The highest classification result was obtained using the explainable XGBoost model (X2GAI) with an accuracy of 94.34%. An explainable structure is also implemented to build the reliability of the developed model.

CONCLUSIONS

The results obtained by radiologists and the X2GAI model were compared according to the diagnosis obtained from the biopsy. It was observed that our developed model performed well in cases where experienced radiologists gave false positive results.

Ultrasound-Based Nomogram for Predicting the Aggressiveness of Papillary Thyroid Carcinoma in Adolescents and Young Adults

RATIONALE AND OBJECTIVES

Assessing the aggressiveness of papillary thyroid carcinoma (PTC) preoperatively might play an important role in guiding therapeutic strategy. This study aimed to develop and validate a nomogram that integrated ultrasound (US) features with clinical characteristics to preoperatively predict aggressiveness in adolescents and young adults with PTC.

MATERIALS AND METHODS

In this retrospective study, a total of 2373 patients were enrolled and randomly divided into two groups with 1000 bootstrap sampling. The multivariable logistic regression (LR) analysis or least absolute shrinkage and selection operator LASSO regression was applied to select predictive US and clinical characteristics in the training cohort. By incorporating most powerful predictors, two predictive models presented as nomograms were developed, and their performance was assessed with respect to discrimination, calibration, and clinical usefulness.

RESULTS

The LR_model that incorporated gender, tumor size, multifocality, US-reported cervical lymph nodes (CLN) status, and calcification demonstrated good discrimination and calibration with an area under curve (AUC), sensitivity and specificity of 0.802 (0.781-0.821), 65.58% (62.61%-68.55%), and 82.31% (79.33%-85.46%), respectively, in the training cohort; and 0.768 (0.736-0.797), 60.04% (55.62%-64.46%), and 83.62% (78.84%-87.71%), respectively, in the validation cohort. Gender, tumor size, orientation, calcification, and US-reported CLN status were combined to build LASSO_model. Compared with LR_model, the LASSO_model yielded a comparable diagnostic performance in both cohorts, the AUC, sensitivity, and specificity were 0.800 (0.780-0.820), 65.29% (62.26%-68.21%), and 81.93% (78.77%-84.91%), respectively, in the training cohort; and 0.763 (0.731-0.792), 59.43% (55.12%-63.93%), and 84.98% (80.89%-89.08%), respectively, in the validation cohort. The decision curve analysis indicated that using the two nomograms to predict the aggressiveness of PTC provided a greater benefit than either the treat-all or treat-none strategy.

CONCLUSION

Through these two easy-to-use nomograms, the possibility of the aggressiveness of PTC in adolescents and young adults can be objectively quantified preoperatively. The two nomograms may serve as a useful clinical tool to provide valuable information for clinical decision-making.

Utility of Six Ultrasound-Based Risk Stratification Systems in the Diagnosis of AUS/FLUS Thyroid Nodules

RATIONALE AND OBJECTIVES

To estimate the diagnostic performance of the currently used ultrasound (US)-based risk stratification systems (RSSs) (American Thyroid Association, American Association of Clinical Endocrinologists, American College of Endocrinology, and Association Medici Endocrinology Medical Guidelines for Clinical Practice for the Diagnosis and Management of Thyroid Nodules, European Thyroid Association Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules in Adults [EU-TIRADS], American College of Radiology Thyroid Imaging Reporting and Data System [ACR-TIRADS], Chinese Guidelines for Ultrasound Malignancy Risk Stratification of Thyroid Nodules [C-TIRADS], and Thyroid Imaging Reporting and Data System Developed by Kwak et al [Kwak-TIRADS]) for atypia of undetermined significance or follicular lesion of undetermined significance (AUS/FLUS) thyroid nodules.

MATERIALS AND METHODS

This retrospective study included 514 consecutive AUS/FLUS nodules in 481 patients with final diagnosis. The US characteristics were reviewed and classified using the categories defined by each RSS. The diagnostic performance was evaluated and compared using a generalized estimating equation method.

RESULTS

Of the 514 AUS/FLUS nodules, 148 (28.8%) were malignant and 366 (71.2%) were benign. The calculated malignancy rate increased from the low-risk to high-risk categories for all RSSs (all P < .001). Interobserver correlation for both US features and RSSs showed substantial to almost perfect agreement. The diagnostic efficacy of Kwak-TIRADS (AUC=0.808) and C-TIRADS (AUC=0.804) were similar (P = .721) and higher than those of other RSSs (all P < .05). The EU-TIRADS and Kwak-TIRADS exhibited similar sensitivity (86.5% vs 85.1%, P = .739) and were only higher than that of the C-TIRADS (all P < .05). The specificity of C-TIRADS and ACR-TIRADS were similar (78.1% vs 72.1%, P = .06) and were higher than those of other RSSs (all P < .05).

CONCLUSION

Currently used RSSs can provide risk stratification for AUS/FLUS nodules. Kwak-TIRADS and C-TIRADS have the highest diagnostic efficacy in identifying malignant AUS/FLUS nodules. A detailed knowledge of the benefits and shortcomings of the various RSSs is essential.

Diagnostic efficiency among Eu-/C-/ACR-TIRADS and S-Detect for thyroid nodules: a systematic review and network meta-analysis

Background

The performance in evaluating thyroid nodules on ultrasound varies across different risk stratification systems, leading to inconsistency and uncertainty regarding diagnostic sensitivity, specificity, and accuracy.

Objective

Comparing diagnostic performance of detecting thyroid cancer among distinct ultrasound risk stratification systems proposed in the last five years.

Evidence acquisition

Systematic search was conducted on PubMed, EMBASE, and Web of Science databases to find relevant research up to December 8, 2022, whose study contents contained elucidation of diagnostic performance of any one of the above ultrasound risk stratification systems (European Thyroid Imaging Reporting and Data System[Eu-TIRADS]; American College of Radiology TIRADS [ACR TIRADS]; Chinese version of TIRADS [C-TIRADS]; Computer-aided diagnosis system based on deep learning [S-Detect]). Based on golden diagnostic standard in histopathology and cytology, single meta-analysis was performed to obtain the optimal cut-off value for each system, and then network meta-analysis was conducted on the best risk stratification category in each system.

Evidence synthesis

This network meta-analysis included 88 studies with a total of 59,304 nodules. The most accurate risk category thresholds were TR5 for Eu-TIRADS, TR5 for ACR TIRADS, TR4b and above for C-TIRADS, and possible malignancy for S-Detect. At the best thresholds, sensitivity of these systems ranged from 68% to 82% and specificity ranged from 71% to 81%. It identified the highest sensitivity for C-TIRADS TR4b and the highest specificity for ACR TIRADS TR5. However, sensitivity for ACR TIRADS TR5 was the lowest. The diagnostic odds ratio (DOR) and area under curve (AUC) were ranked first in C-TIRADS.

Conclusion

Among four ultrasound risk stratification options, this systemic review preliminarily proved that C-TIRADS possessed favorable diagnostic performance for thyroid nodules.

Systematic review registration

https://www.crd.york.ac.uk/prospero, CRD42022382818.

US-Elastography With Different Techniques for Thyroid Nodule Characterization: Systematic Review and Meta-analysis

Background

Thyroid nodules are frequent in adult population and thyroid cancer incidence has increased dramatically over the past three decades. The aim of this systematic review and meta-analysis was to evaluate the US-Elastosonography (USE) diagnostic performance in assessing the thyroid nodules malignancy risk.

Methods

PubMed and Embase databases were searched from January 2011 to July 2021. We extracted data from selected studies and calculated the overall diagnostic accuracy of qualitative USE, semi-quantitative USE and quantitative USE. Summary receiver operating characteristic (ROC) curve was elaborated to show the results. All statistical tests were performed using Metadisc and Medcal software package.

Results

Finally 72 studies with 13,505 patients and 14,015 thyroid nodules (33% malignant) undergoing elastography were included. The pooled sensitivity, specificity and AUC were 84%, 81%, and 0.89 respectively for qualitative USE; 83%, 80%, and 0.93 for semi-quantitative USE and 78%, 81% and 0.87, for quantitative USE. The qualitative and semiquantitative USE present very similar diagnostic accuracy values and both better than the quantitative USE.

Conclusions

USE is a useful imaging tool for thyroid nodule characterization. In accordance with recent guidelines and meta-analyses, the USE could be used daily in thyroid nodule malignancy risk stratification.

Systematic Review Registration

PROSPERO: CRD42021279257.

Impact of the Hypoechogenicity Criteria on Thyroid Nodule Malignancy Risk Stratification Performance by Different TIRADS Systems

Simple Summary

This study is aimed at raising the question of the use of several TIRADS systems that stratify the risk of thyroid nodule malignancy. Approximately 5–20% of thyroid nodules are malignant, but most nodules are benign, and they are scored by FNA biopsy. One of the goals is to reduce the number of unnecessary FNA and the associated with-it possible complications for the patient and financial cost. Most TIRADS systems are based on the fact that one suspicious feature of a thyroid nodule classifies it as malignant, but there is a modified Kwak et al. system that is based on the count of malignant features. Therefore, this study is intended to estimate the specificity, sensitivity, and accuracy of the systems and, in the future, think about reducing the number of FNA biopsies. The result of this study can be important for all doctors who face thyroid changes, such as radiologists, ultrasonography specialists, and endocrinologists, those who must decide about the need for an FNA.

Abstract

Background: Various Thyroid Imaging and Reporting data systems (TIRADS) are used worldwide for risk stratification of thyroid nodules. Their sensitivity is high, while the specificity is suboptimal. The aim of the study was to compare several TIRADS systems and evaluate the effect of hypoechogenicity as a sign of risk of malignancy on the overall assessment of diagnostic accuracy. Methods: The prospective study includes 274 patients with 289 thyroid nodules to whom US and risk of malignancy were assessed according to four TIRADS systems—European (EU-TIRADS), Korean (K-TIRADS), TIRADS by American College of Radiology (ACR TIRADS), and modified Kwak et al. TIRADS (L-TIRADS) systems, in which mild hypoechogenicity is not included in malignancy risk suggestive signs. For all thyroid nodules, a fine needle aspiration (FNA) biopsy was performed and evaluated according to the Bethesda system. For all systems, diagnostic accuracy was calculated. Results: Assessing the echogenicity of the thyroid nodules: from 81 of isoechogenic nodules, 2 were malignant (2.1%), from 151 mild hypoechogenic, 18 (12%) were malignant, and from 48 marked hypoechogenic nodules, 16 (33%) were malignant. In 80 thyroid nodules, mild hypoechogenicity was the only sign of malignancy and none appeared malignant. Assessing various TIRADS systems on the same cohort, sensitivity, specificity, PPV, NPV, and accuracy, firstly for EU-TIRADS, they were 97.2%; 39.9%; 18.7%; 99.0%, and 73.3%, respectively; for K-TIRADS they were 97.2%; 46.6%; 20.6%; 99.2%, and 53.9%; for ACR-TIRADS they were 97.2%; 41.1%, 19.0%; 99.0%, and 48.0%, respectively; finally, for L-TIRADS they were 80.6%; 72.7%; 29.6%; 96.3%, and 73.3%. Conclusions: This comparative research has highlighted that applying different TIRADS systems can alter the number of necessary biopsies by re-categorization of the thyroid nodules. The main pattern that affected differences was inconsistent hypoechogenicity interpretation, giving the accuracy superiority to the systems that raise the malignancy risk with marked hypoechogenicity, at the same time with minor compensation for sensitivity.