Radiomics Study of Thyroid Ultrasound for Predicting BRAF Mutation in Papillary Thyroid Carcinoma: Preliminary Results

Ultrasound features as predictive markers of BRAFV600E mutation in thyroid cancer: a systematic review and meta-analysis

Background

Conflicting evidence exists on the predictive value of ultrasound characteristics for BRAFV600E gene expression in thyroid cancer. This study aimed to determine the predictive value of ultrasound features for BRAFV600E gene expression status in thyroid cancer.

Methods

A systematic review of studies published before December 31, 2023, was conducted in the PubMed, Web of Science, and Cochrane Library databases. Studies evaluating the ultrasonographic features for predicting BRAFV600E gene mutations in thyroid cancer were included. The relevant data were extracted, and the quality of eligible studies was independently assessed by two reviewers. Statistical analysis was performed using RevMan 5.4 and Stata 12.0 software.

Results

The meta-analysis included 13 studies involving a total of 2,250 thyroid cancer patients. Ultrasound features significantly associated with BRAFV600E gene expression status in thyroid cancer (P<0.05) comprised hypoechogenicity, absence of halo, irregular borders, and vertical orientation. Contrastingly, no significant differences were observed in solid composition, irregular shape, and microcalcifications (P>0.05). Among the seven ultrasound features, the ones with superior combined sensitivity for nodules were hypoechogenicity, solid composition, absence of halo, and irregular borders, with sensitivities of 0.93 [95% confidence interval (CI): 0.87-0.96], 0.93 (95% CI: 0.86-0.97), 0.83 (95% CI: 0.72-0.91), and 0.74 (95% CI: 0.64-0.83), respectively. Finally, the areas under the summary receiver operating characteristic (SROC) curve with the highest diagnostic performance were the absence of halo and hypoechogenicity, with area under the curve (AUC) of 0.84 (95% CI: 0.80-0.87) and 0.81 (95% CI: 0.77-0.84), respectively.

Conclusions

The expression status of the BRAFV600E gene in thyroid cancer correlates with nodules exhibiting hypoechogenicity, absence of halo, irregular borders, and taller-than-wide shape. Notably, the absence of a halo and hypoechogenicity were identified as the most predictive ultrasonic features. However, due to the limited sample size, there may be bias in the meta-analysis results, and more extensive research is necessary.

Combining radiomics with thyroid imaging reporting and data system to predict lateral cervical lymph node metastases in medullary thyroid cancer

BACKGROUND

Medullary Thyroid Carcinoma (MTC) is a rare type of thyroid cancer. Accurate prediction of lateral cervical lymph node metastases (LCLNM) in MTC patients can help guide surgical decisions and ensure that patients receive the most appropriate and effective surgery. To our knowledge, no studies have been published that use radiomics analysis to forecast LCLNM in MTC patients. The purpose of this study is to develop a radiomics combined with thyroid imaging reporting and data system (TI-RADS) model that can use preoperative thyroid ultrasound images to noninvasively predict the LCLNM status of MTC.

METHODS

We retrospectively included 218 MTC patients who were confirmed from postoperative pathology as LCLNM negative (n=111) and positive (n=107). Ultrasound features were selected using the Student's t-test, while radiomics features are first extracted from preoperative thyroid ultrasound images, and then a two-step feature selection approach was used to select features. These features are then used to establish three regularized logistic regression models, namely the TI-RADS model (TM), the radiomics model (RM), and the radiomics-TI-RADS model (RTM), in 5-fold cross-validation to determine the likelihood of the LCLNM. The Delong's test and decision curve analysis (DCA) were used to evaluate and compare the performance of the models.

RESULTS

The ultrasound features of margin and TI-RADS level, and a total of 12 selected radiomics features, were significantly different between the LCLNM negative and positive groups (p<0.05). The TM, RM, and RTM yielded an averaged AUC of 0.68±0.05, 0.78±0.06, and 0.82±0.05 in the 5-fold cross-validation dataset, respectively. RM and RTM are statistically better than TM (p<0.05 and p<0.001) according to Delong test. DCA demonstrates that RTM brings more benefit than TM and RM.

CONCLUSIONS

We have developed a joint radiomics-based model for noninvasive prediction of the LCLNM in MTC patients solely using preoperative thyroid ultrasound imaging. It has the potential to be used as a complementary tool to help guide treatment decisions for this rare form of thyroid cancer.

Ultrasound radiomics based XGBoost model to differential diagnosis thyroid nodules and unnecessary biopsy rate: Individual application of SHapley additive exPlanations

OBJECTIVES

Radiomics-based eXtreme gradient boosting (XGBoost) model was developed to differentiate benign thyroid nodules from malignant thyroid nodules and to prevent unnecessary thyroid biopsies, including positive and negative effects.

METHODS

The study evaluated a data set of ultrasound images of thyroid nodules in patients retrospectively, who initially received ultrasound-guided fine-needle aspiration biopsy (FNAB) for diagnostic purposes. According to ACR TI-RADS, a total of five ultrasound feature categories and the maximum size of the nodule were determined by four radiologists. A radiomics score was developed by the LASSO algorithm from the ultrasound-based radiomics features. An interpretative method based on Shapley additive explanation (SHAP) was developed. XGBoost was compared with ACR TI-RADS for its diagnostic performance and FNAB rate and was compared with six other machine learning models to evaluate the model performance.

RESULTS

Finally, 191 thyroid nodules were examined from 177 patients. The radiomics score were calculated using 8 features, which were selected among 789 candidate features generated from the ultrasound images. The model yielded an AUC of 93% in the training cohort and 92% in the test cohort. It outperformed traditional machine learning models in assessing the nature of thyroid nodules. Compared with ACR TI-RADS, the FNAB rate decreased from 34% to 30% in training and from 35% to 41% in test.

CONCLUSIONS

The radiomics-based XGBoost model proposed could distinguish benign and malignant thyroid nodules, thereby reduced significantly the number of unnecessary FNAB. It was effective in making preoperative decisions and managing selected patients using the SHAP visual interpretation tools.

A nomogram model combining ultrasound-based radiomics features and clinicopathological factors to identify germline BRCA1/2 mutation in invasive breast cancer patients

Objective

BRCA1/2 status is a key to personalized therapy for invasive breast cancer patients. This study aimed to explore the association between ultrasound radiomics features and germline BRCA1/2 mutation in patients with invasive breast cancer.

Materials and methods

In this retrospective study, 100 lesions in 92 BRCA1/2-mutated patients and 390 lesions in 357 non-BRCA1/2-mutated patients were included and randomly assigned as training and validation datasets in a ratio of 7:3. Gray-scale ultrasound images of the largest plane of the lesions were used for feature extraction. Maximum relevance minimum redundancy (mRMR) algorithm and multivariate logistic least absolute shrinkage and selection operator (LASSO) regression were used to select features. The multivariate logistic regression method was used to construct predictive models based on clinicopathological factors, radiomics features, or a combination of them.

Results

In the clinical model, age at first diagnosis, family history of BRCA1/2-related malignancies, HER2 status, and Ki-67 level were found to be independent predictors for BRCA1/2 mutation. In the radiomics model, 10 significant features were selected from the 1032 radiomics features extracted from US images. The AUCs of the radiomics model were not inferior to those of the clinical model in both training dataset [0.712 (95% CI, 0.647-0.776) vs 0.768 (95% CI, 0.704-0.835); p = 0.429] and validation dataset [0.705 (95% CI, 0.597-0.808) vs 0.723 (95% CI, 0.625-0.828); p = 0.820]. The AUCs of the nomogram model combining clinical and radiomics features were 0.804 (95% CI, 0.748-0.861) in the training dataset and 0.811 (95% CI, 0.724-0.894) in the validation dataset, which were proved significantly higher than those of the clinical model alone by DeLong's test (p = 0.041; p = 0.007). To be noted, the negative predictive values (NPVs) of the nomogram model reached a favorable 0.93 in both datasets.

Conclusion

This machine nomogram model combining ultrasound-based radiomics and clinical features exhibited a promising performance in identifying germline BRCA1/2 mutation in patients with invasive breast cancer and may help avoid unnecessary gene tests in clinical practice.

Application and prospects of AI-based radiomics in ultrasound diagnosis

Artificial intelligence (AI)-based radiomics has attracted considerable research attention in the field of medical imaging, including ultrasound diagnosis. Ultrasound imaging has unique advantages such as high temporal resolution, low cost, and no radiation exposure. This renders it a preferred imaging modality for several clinical scenarios. This review includes a detailed introduction to imaging modalities, including Brightness-mode ultrasound, color Doppler flow imaging, ultrasound elastography, contrast-enhanced ultrasound, and multi-modal fusion analysis. It provides an overview of the current status and prospects of AI-based radiomics in ultrasound diagnosis, highlighting the application of AI-based radiomics to static ultrasound images, dynamic ultrasound videos, and multi-modal ultrasound fusion analysis.

Contrast-enhanced CT-based Radiomics for the Differentiation of Anaplastic or Poorly Differentiated Thyroid Carcinoma from Differentiated Thyroid Carcinoma: A Pilot Study

Differential diagnosis of anaplastic thyroid carcinoma/poorly differentiated thyroid carcinoma (ATC/PDTC) from differentiated thyroid carcinoma (DTC) is crucial in patients with large thyroid malignancies. This study creates a predictive model using radiomics feature analysis to differentiate ATC/PDTC from DTC. We compared the clinicoradiological characteristics and radiomics features extracted from a volume of interest on contrast-enhanced computed tomography (CT) between the groups. Estimations of variable importance were performed via modeling using the random forest quantile classifier. The diagnostic performance of the model with radiomics features alone had the area under the receiver operating characteristic (AUROC) curve value of 0.883. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy were 81.7%, 93.3%, 97.7%, 64.5%, and 84.6%, respectively, for the differential diagnosis of ATC/PDTC and DTC. The model with both radiomics and clinicoradiological information showed the AUROC of 0.908, with sensitivity, specificity, PPV, NPV, and accuracy of 82.9%, 97.6%, 99.2%, 67.1%, and 86.5% respectively. Distant metastasis, moment, shape, age, and gray-level size zone matrix features were the most useful factors for differential diagnosis. Therefore, we concluded that a radiomics approach based on contrast-enhanced CT features can potentially differentiate ATC/PDTC from DTC in patients with large thyroid malignancies.

MRI-Based Texture Analysis for Preoperative Prediction of BRAF V600E Mutation in Papillary Thyroid Carcinoma

Purpose

BRAF V600E mutation can compensate for the low detection rate by fine-needle aspiration (FNA) and is related to aggressiveness and lymph node metastasis. This study aimed to investigate the relationship between texture analysis features based on magnetic resonance imaging (MRI) and mutations.

Methods

Retrospective analysis was performed on patients with postoperative pathology confirmed papillary thyroid carcinoma (PTC) from 2017 to 2021. One thousand one hundred and thirty-two texture features were extracted from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI) separately by outlining the tumor volume of interest (VOI). Univariate, minimum redundancy maximum relevance (mRMR), and multivariate analyses were used for feature selection to construct 3 models (T2WI, CE-T1WI, and combined model) to predict mutation. The reproducibility between observers was evaluated by intraclass correlation coefficient (ICC). Receiver operating characteristic (ROC) analysis was used to assess the performance of models. The diagnostic performance of the optimal cut-off value of models were calculated and validated by 10-fold cross-validation.

Results

A total of 80 PTCs (22 BRAF V600E wild-type and 58 BRAF V600E mutant) were included in our study. Good interobserver agreement was found on texture features we selected (all ICCs >0.75). The area under the ROC curves (AUCs) for the T2WI model, CE-T1WI model, and combined model were 0.83 (95% CI: 0.75-0.91), 0.83 (95% CI: 0.73-0.90), and 0.88 (95% CI: 0.81-0.94), respectively. The accuracy, sensitivity, specificity, PPV, and NPV were 0.776, 0.679, 0.905, 0.905, and 0.679 for the T2WI model at a cut-off value of 0.674; 0.755, 0.750, 0.762, 0.808, and 0.696 for the CE-T1WI model at a cut-off value of 0.573; 0.816, 0.893, 0.714, 0.806, and 0.833 for the combined model at a cut-off value of 0.420.

Conclusion

MRI-based texture analysis could be a potential method for predicting BRAF V600E mutation in PTC preoperatively.

The Diagnostic Performance of Ultrasonography in the Evaluation of Extrathyroidal Extension in Papillary Thyroid Carcinoma: A Systematic Review and Meta-Analysis

Extrathyroidal extension (ETE) in patients with papillary thyroid carcinoma (PTC) is an indication of disease progression and can influence treatment aggressiveness. This meta-analysis assesses the diagnostic accuracy of ultrasonography (US) in detecting ETE. A systematic review and meta-analysis were performed by searching PubMed, Embase, and Cochrane for studies published up to April 2022. The pooled sensitivity, specificity, and diagnostic odds ratio (DOR) were calculated. The areas under the curve (AUC) for summary receiver operating curves were compared. A total of 11 studies analyzed ETE in 3795 patients with PTC. The sensitivity of ETE detection was 76% (95%CI = 74-78%). The specificity of ETE detection was 51% (95%CI = 49-54%). The DOR of detecting ETE by US was 5.32 (95%CI = 2.54-11.14). The AUC of ETE detection was determined to be 0.6874 ± 0.0841. We report an up-to-date analysis elucidating the diagnostic accuracy of ETE detection by US. Our work suggests the diagnostic accuracy of US in detecting ETE is adequate. Considering the importance of ETE detection on preoperative assessment, ancillary studies such as adjunct imaging studies and genetic testing should be considered.

Prediction of BRAF V600E variant from cancer gene expression data

Background

BRAF inhibitors have been approved for the treatment of melanoma, non-small cell lung cancer, and colon cancer. Real-time polymerase chain reaction or next-generation sequencing were clinically used for BRAF variant detection to select who responds to BRAF inhibitors. The prediction of BRAF variants using gene expression data might be an alternative test when the direct variant sequencing test is not feasible. In this study, we built a prediction model to detect BRAF V600 variants with mRNA gene expression data in various cancer types.

Methods

We adopted a penalized logistic regression for the BRAF V600E variants prediction model. Ten times bootstrap resampling was done with a combined target variable and cancer type stratification. Data preprocessing included knnimputation for missing value imputation, YeoJohnson transformation for skewness correction, center, and scale for standardization, synthetic minority over-sampling technique for class imbalance. Hyperparameter optimization with a grid search was undertaken for model selection in terms of area under the precision-recall.

Results

The area under the curve of the receiver operating characteristic curve on the test set was 0.98 in thyroid carcinoma, 0.90 in colon adenocarcinoma, and 0.85 in cutaneous melanoma. The area under the precision-recall of the test set was 0.98 in thyroid carcinoma, 0.71 in colon adenocarcinoma, and 0.65 in cutaneous melanoma.

Conclusions

Our penalized logistic regression model can predict BRAF V600E variants with good performance in thyroid carcinoma, cutaneous melanoma, and colon adenocarcinoma.

Thyroid Disease Prediction Using Selective Features and Machine Learning Techniques

Simple Summary

The study presents a thyroid disease prediction approach which utilizes random forest-based features to obtain high accuracy. The approach can obtain a 0.99 accuracy to predict ten thyroid diseases.

Abstract

Thyroid disease prediction has emerged as an important task recently. Despite existing approaches for its diagnosis, often the target is binary classification, the used datasets are small-sized and results are not validated either. Predominantly, existing approaches focus on model optimization and the feature engineering part is less investigated. To overcome these limitations, this study presents an approach that investigates feature engineering for machine learning and deep learning models. Forward feature selection, backward feature elimination, bidirectional feature elimination, and machine learning-based feature selection using extra tree classifiers are adopted. The proposed approach can predict Hashimoto’s thyroiditis (primary hypothyroid), binding protein (increased binding protein), autoimmune thyroiditis (compensated hypothyroid), and non-thyroidal syndrome (NTIS) (concurrent non-thyroidal illness). Extensive experiments show that the extra tree classifier-based selected feature yields the best results with 0.99 accuracy and an F1 score when used with the random forest classifier. Results suggest that the machine learning models are a better choice for thyroid disease detection regarding the provided accuracy and the computational complexity. K-fold cross-validation and performance comparison with existing studies corroborate the superior performance of the proposed approach.

Artificial Intelligence for Thyroid Nodule Characterization: Where Are We Standing?

Simple Summary

In the present review, an up-to-date summary of the state of the art of artificial intelligence (AI) implementation for thyroid nodule characterization and cancer is provided. The opinion on the real effectiveness of AI systems remains controversial. Taking into consideration the largest and most scientifically valid studies, it is possible to state that AI provides results that are comparable or inferior to expert ultrasound specialists and radiologists. Promising data approve AI as a support tool and simultaneously highlight the need for a radiologist supervisory framework for AI provided results. Therefore, current solutions might be more suitable for educational purposes.

Abstract

Machine learning (ML) is an interdisciplinary sector in the subset of artificial intelligence (AI) that creates systems to set up logical connections using algorithms, and thus offers predictions for complex data analysis. In the present review, an up-to-date summary of the current state of the art regarding ML and AI implementation for thyroid nodule ultrasound characterization and cancer is provided, highlighting controversies over AI application as well as possible benefits of ML, such as, for example, training purposes. There is evidence that AI increases diagnostic accuracy and significantly limits inter-observer variability by using standardized mathematical algorithms. It could also be of aid in practice settings with limited sub-specialty expertise, offering a second opinion by means of radiomics and computer-assisted diagnosis. The introduction of AI represents a revolutionary event in thyroid nodule evaluation, but key issues for further implementation include integration with radiologist expertise, impact on workflow and efficiency, and performance monitoring.

Value of Whole-Thyroid CT-Based Radiomics in Predicting Benign and Malignant Thyroid Nodules

The objective of this research is to explore the value of whole-thyroid CT-based radiomics in predicting benign (noncancerous) and malignant thyroid nodules. The imaging and clinical data of 161 patients with thyroid nodules that were confirmed by pathology were retrospectively analyzed. The entire thyroid regions of interest (ROIs) were manually sketched for all 161 cases. After extracting CT radiomic features, the patients were divided into a training group (128 cases) and a test group (33 cases) according to the 4:1 ratio with stratified random sampling (fivefold cross validation). All the data were normalized by the maximum absolute value and screened using selection operator regression analysis and K best. The data generation model was trained by logistic regression. The effectiveness of the model in differentiating between benign and malignant thyroid nodules was validated by a receiver operating characteristic (ROC) curve. After data grouping, eigenvalue screening, and data training, the logistic regression model with the maximum absolute value normalized was constructed. For the training group, the area under the ROC curve (AUC) was 94.4% (95% confidence interval: 0.941–0.977); the sensitivity and specificity were 89.7% and 86.7%, respectively; and the diagnostic accuracy was 87.6%. For the test group, the AUC was 94.2% (95% confidence interval: 0.881–0.999); the sensitivity and specificity were 89.4% and 86.8%, respectively; and the diagnostic accuracy was 87.6%. The CT radiomic model of the entire thyroid gland is highly efficient in differentiating between benign and malignant thyroid nodules.

Ultrasound-based radiomics analysis for preoperative prediction of central and lateral cervical lymph node metastasis in papillary thyroid carcinoma: a multi-institutional study

Background

An accurate preoperative assessment of cervical lymph node metastasis (LNM) is important for choosing an optimal therapeutic strategy for papillary thyroid carcinoma (PTC) patients. This study aimed to develop and validate two ultrasound (US) nomograms for the individual prediction of central and lateral compartment LNM in patients with PTC.

Methods

A total of 720 PTC patients from 3 institutions were enrolled in this study. They were categorized into a primary cohort, an internal validation, and two external validation cohorts. Radiomics features were extracted from conventional US images. LASSO regression was used to select optimized features to construct the radiomics signature. Two nomograms integrating independent clinical variables and radiomics signature were established with multivariate logistic regression. The performance of the nomograms was assessed with regard to discrimination, calibration, and clinical usefulness.

Results

The radiomics scores were significantly higher in patients with central/lateral LNM. A radiomics nomogram indicated good discrimination for central compartment LNM, with an area under the curve (AUC) of 0.875 in the training set, the corresponding value in the validation sets were 0.856, 0.870 and 0.870, respectively. Another nomogram for predicting lateral LNM also demonstrated good performance with an AUC of 0.938 and 0.905 in the training and internal validation cohorts, respectively. The AUC for the two external validation cohorts were 0.881 and 0.903, respectively. The clinical utility of the nomograms was confirmed by the decision curve analysis.

Conclusion

The nomograms proposed here have favorable performance for preoperatively predicting cervical LNM, hold promise for optimizing the personalized treatment, and might greatly facilitate the decision-making in clinical practice.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00809-2.

A machine-learning algorithm for distinguishing malignant from benign indeterminate thyroid nodules using ultrasound radiomic features

Background: Ultrasound (US)-guided fine needle aspiration (FNA) cytology is the gold standard for the evaluation of thyroid nodules. However, up to 30% of FNA results are indeterminate, requiring further testing. In this study, we present a machine-learning analysis of indeterminate thyroid nodules on ultrasound with the aim to improve cancer diagnosis. Methods: Ultrasound images were collected from two institutions and labeled according to their FNA (F) and surgical pathology (S) diagnoses [malignant (M), benign (B), and indeterminate (I)]. Subgroup breakdown (FS) included: 90 BB, 83 IB, 70 MM, and 59 IM thyroid nodules. Margins of thyroid nodules were manually annotated, and computerized radiomic texture analysis was conducted within tumor contours. Initial investigation was conducted using five-fold cross-validation paradigm with a two-class Bayesian artificial neural networks classifier, including stepwise feature selection. Testing was conducted on an independent set and compared with a commercial molecular testing platform. Performance was evaluated using receiver operating characteristic analysis in the task of distinguishing between malignant and benign nodules. Results: About 1052 ultrasound images from 302 thyroid nodules were used for radiomic feature extraction and analysis. On the training/validation set comprising 263 nodules, five-fold cross-validation yielded area under curves (AUCs) of 0.75 [Standard Error (SE) = 0.04; P < 0.001 ] and 0.67 (SE = 0.05; P = 0.0012 ) for the classification tasks of MM versus BB, and IM versus IB, respectively. On an independent test set of 19 IM/IB cases, the algorithm for distinguishing indeterminate nodules yielded an AUC value of 0.88 (SE = 0.09; P < 0.001 ), which was higher than the AUC of a commercially available molecular testing platform (AUC = 0.81, SE = 0.11; P < 0.005 ). Conclusion: Machine learning of computer-extracted texture features on gray-scale ultrasound images showed promising results classifying indeterminate thyroid nodules according to their surgical pathology.

Iodine Maps from Dual-Energy CT to Predict Extrathyroidal Extension and Recurrence in Papillary Thyroid Cancer Based on a Radiomics Approach

BACKGROUND AND PURPOSE

Accurate prediction of extrathyroidal extension and subsequent recurrence is crucial in papillary thyroid cancer clinical management. Our aim was to conduct iodine map-based radiomics to predict extrathyroidal extension and to explore its prognostic value for recurrence-free survival in papillary thyroid cancer.

MATERIALS AND METHODS

A total of 452 patients with papillary thyroid cancer were retrospectively recruited between June 2017 and June 2020. Radiomics features were extracted from noncontrast images, dual-phase mixed images, and iodine maps, respectively. Random forest and least absolute shrinkage and selection operator (LASSO) were applied to build 6 radiomics scores (noncontrast radiomics score_random forest; noncontrast rad-score_LASSO; mixed rad-score_random forest; mixed rad-score_LASSO; iodine radiomics score_random forest; iodine radiomics score_LASSO) respectively. Logistic regression was used to construct 6 radiomics models incorporating 6 radiomics scores with clinical risk factors and to compare them with the clinical model. A radiomics model that achieved the highest performance was presented as a nomogram and assessed by discrimination, calibration, clinical usefulness, and prognosis evaluation.

RESULTS

Iodine radiomics scores performed significantly better than mixed radiomics scores. Both of them outperformed noncontrast radiomics scores. Iodine map-based radiomics models significantly surpassed the clinical model. A radiomics nomogram incorporating size, capsule contact, and iodine radiomics score_random forest was built with the highest performance (training set, area under the curve = 0.78; validation set, area under the curve  = 0.84). Stratified analysis confirmed the nomogram stability, especially in group negative for CT-reported extrathyroidal extension (area under the curve  = 0.69). Nomogram-predicted extrathyroidal extension risk was an independent predictor of recurrence-free survival. A high risk for extrathyroidal extension portended significantly lower recurrence-free survival than low risk (P < .001).

CONCLUSIONS

Iodine map-based radiomics might be a supporting tool for predicting extrathyroidal extension and subsequent recurrence risk in patients with papillary thyroid cancer, thus facilitating clinical decision-making.

Nomogram based on radiomics analysis of ultrasound images can improve preoperative BRAF mutation diagnosis for papillary thyroid microcarcinoma

BACKGROUND

The preoperative identification of BRAF mutation could assist to make appropriate treatment strategies for patients with papillary thyroid microcarcinoma (PTMC). This study aimed to establish an ultrasound (US) radiomics nomogram for the assessment of BRAF status.

METHODS

A total of 328 PTMC patients at the China-Japan Friendship Hospital between February 2019 and November 2021 were enrolled in this study. They were randomly divided into training (n = 232) and validation (n = 96) cohorts. Radiomics features were extracted from the US images. The least absolute shrinkage and selection operator (LASSO) regression was applied to select the BRAF status-related features and calculate the radiomics score (Rad-score). Univariate and multivariate logistic regression analyses were subsequently performed to identify the independent factors among Rad-score and conventional US features. The US radiomics nomogram was established and its predictive performance was evaluated via discrimination, calibration, and clinical usefulness in the training and validation sets.

RESULTS

Multivariate analysis indicated that the Rad-score, composition, and aspect ratio were independent predictive factors of BRAF status. The US radiomics nomogram which incorporated the three variables showed good calibration. The discrimination of the US radiomics nomogram showed better discriminative ability than the conventional US model both in the training set (AUC 0.685 vs. 0.592) and validation set (AUC 0.651 vs. 0.622). Decision curve analysis indicated the superior clinical applicability of the nomogram compared to the conventional US model.

CONCLUSIONS

The US radiomics nomogram displayed better performance than the conventional US model in predicting BRAF mutation in patients with PTMC.

Radiomic Model for Determining the Value of Elasticity and Grayscale Ultrasound Diagnoses for Predicting BRAFV600E Mutations in Papillary Thyroid Carcinoma

BRAF^V600E is the most common mutated gene in thyroid cancer and is most closely related to papillary thyroid carcinoma(PTC). We investigated the value of elasticity and grayscale ultrasonography for predicting BRAF^V600E mutations in PTC.

METHODS

138 patients with PTC who underwent preoperative ultrasound between January 2014 and 2021 were retrospectively examined. Patients were divided into BRAF^V600E mutation-free group (n=75) and BRAF^V600E mutation group (n=63). Patients were randomly divided into training (n=96) and test (n=42) groups. A total of 479 radiomic features were extracted from the grayscale and elasticity ultra-sonograms. Regression analysis was done to select the features that provided the most information. Then, 10-fold cross-validation was used to compare the performance of different classification algorithms. Logistic regression was used to predict BRAF^V600E mutations.

RESULTS

Eight radiomics features were extracted from the grayscale ultrasonogram, and five radiomics features were extracted from the elasticity ultrasonogram. Three models were developed using these radiomic features. The models were derived from elasticity ultrasound, grayscale ultrasound, and a combination of grayscale and elasticity ultrasound, with areas under the curve (AUC) 0.952 [95% confidence interval (CI), 0.914-0.990], AUC 0.792 [95% CI, 0.703-0.882], and AUC 0.985 [95% CI, 0.965-1.000] in the training dataset, AUC 0.931 [95% CI, 0.841-1.000], AUC 0. 725 [95% CI, 0.569-0.880], and AUC 0.938 [95% CI, 0.851-1.000] in the test dataset, respectively.

CONCLUSION

The radiomic model based on grayscale and elasticity ultrasound had a good predictive value for BRAF^V600E gene mutations in patients with PTC.

Ultrasound images-based deep learning radiomics nomogram for preoperative prediction of RET rearrangement in papillary thyroid carcinoma

PURPOSE

To create an ultrasound -based deep learning radiomics nomogram (DLRN) for preoperatively predicting the presence of RET rearrangement among patients with papillary thyroid carcinoma (PTC).

METHODS

We retrospectively enrolled 650 patients with PTC. Patients were divided into the RET/PTC rearrangement group (n = 103) and the non-RET/PTC rearrangement group (n = 547). Radiomics features were extracted based on hand-crafted features from the ultrasound images, and deep learning networks were used to extract deep transfer learning features. The least absolute shrinkage and selection operator regression was applied to select the features of nonzero coefficients from radiomics and deep transfer learning features; then, we established the deep learning radiomics signature. DLRN was constructed using a logistic regression algorithm by combining clinical and deep learning radiomics signatures. The prediction performance was evaluated using the receiver operating characteristic curve, calibration curve, and decision curve analysis.

RESULTS

Comparing the effectiveness of the models by linking the area under the receiver operating characteristic curve of each model, we found that the area under the curve of DLRN could reach 0.9545 (95% confidence interval: 0.9133-0.9558) in the test cohort and 0.9396 (95% confidence interval: 0.9185-0.9607) in the training cohort, indicating that the model has an excellent performance in predicting RET rearrangement in PTC. The decision curve analysis demonstrated that the combined model was clinically useful.

CONCLUSION

The novel ultrasonic-based DLRN has an important clinical value for predicting RET rearrangement in PTC. It can provide physicians with a preoperative non-invasive primary screening method for RET rearrangement diagnosis, thus facilitating targeted patients with purposeful molecular sequencing to avoid unnecessary medical investment and improve treatment outcomes.

Deep learning and pathomics analyses reveal cell nuclei as important features for mutation prediction of BRAF-mutated melanomas

Image-based analysis as a method for mutation detection can be advantageous in settings when tumor tissue is limited or unavailable for direct testing. Here, we utilize two distinct and complementary machine learning methods of analyzing whole slide images (WSI) for predicting mutated BRAF. In the first method, WSI of melanomas from 256 patients were used to train a deep convolutional neural network (CNN) in order to develop a fully automated model that first selects for tumor-rich areas (Area Under the Curve AUC=0.96) then predicts for mutated BRAF (AUC=0.71). Saliency mapping was performed and revealed that pixels corresponding to nuclei were the most relevant to network learning. In the second method, WSI were analyzed using a pathomics pipeline that first annotates nuclei and then quantifies nuclear features, demonstrating that mutated BRAF nuclei were significantly larger and rounder nuclei compared to BRAF WT nuclei. Lastly, we developed a model that combines clinical information, deep learning, and pathomics that improves the predictive performance for mutated BRAF to AUC=0.89. Not only does this provide additional insights on how BRAF mutations affect tumor structural characteristics, machine learning-based analysis of WSI has the potential to be integrated into higher order models for understanding tumor biology.

Artificial Intelligence in Thyroid Field-A Comprehensive Review

Simple Summary

The incidence of thyroid pathologies has been increasing worldwide. Historically, the detection of thyroid neoplasms relies on medical imaging analysis, depending mainly on the experience of clinicians. The advent of artificial intelligence (AI) techniques led to a remarkable progress in image-recognition tasks. AI represents a powerful tool that may facilitate understanding of thyroid pathologies, but actually, the diagnostic accuracy is uncertain. This article aims to provide an overview of the basic aspects, limitations and open issues of the AI methods applied to thyroid images. Medical experts should be familiar with the workflow of AI techniques in order to avoid misleading outcomes.

Abstract

Artificial intelligence (AI) uses mathematical algorithms to perform tasks that require human cognitive abilities. AI-based methodologies, e.g., machine learning and deep learning, as well as the recently developed research field of radiomics have noticeable potential to transform medical diagnostics. AI-based techniques applied to medical imaging allow to detect biological abnormalities, to diagnostic neoplasms or to predict the response to treatment. Nonetheless, the diagnostic accuracy of these methods is still a matter of debate. In this article, we first illustrate the key concepts and workflow characteristics of machine learning, deep learning and radiomics. We outline considerations regarding data input requirements, differences among these methodologies and their limitations. Subsequently, a concise overview is presented regarding the application of AI methods to the evaluation of thyroid images. We developed a critical discussion concerning limits and open challenges that should be addressed before the translation of AI techniques to the broad clinical use. Clarification of the pitfalls of AI-based techniques results crucial in order to ensure the optimal application for each patient.

Radiomics in Differentiated Thyroid Cancer and Nodules: Explorations, Application, and Limitations

Radiomics is an emerging technique that allows the quantitative extraction of high-throughput features from single or multiple medical images, which cannot be observed directly with the naked eye, and then applies to machine learning approaches to construct classification or prediction models. This method makes it possible to evaluate tumor status and to differentiate malignant from benign tumors or nodules in a more objective manner. To date, the classification and prediction value of radiomics in DTC patients have been inconsistent. Herein, we summarize the available literature on the classification and prediction performance of radiomics-based DTC in various imaging techniques. More specifically, we reviewed the recent literature to discuss the capacity of radiomics to predict lymph node (LN) metastasis, distant metastasis, tumor extrathyroidal extension, disease-free survival, and B-Raf proto-oncogene serine/threonine kinase (BRAF) mutation and differentiate malignant from benign nodules. This review discusses the application and limitations of the radiomics process, and explores its ability to improve clinical decision-making with the hope of emphasizing its utility for DTC patients.

Implications of US radiomics signature for predicting malignancy in thyroid nodules with indeterminate cytology

OBJECTIVES

The purpose of this study was to evaluate the role of the radiomics score using US images to predict malignancy in AUS/FLUS and FN/SFN nodules.

METHODS

One hundred fifty-five indeterminate thyroid nodules in 154 patients who received initial US-guided FNA for diagnostic purposes were included in this retrospective study. A representative US image of each tumor was acquired, and square ROIs covering the whole nodule were drawn using the Paint program of Windows 7. Texture features were extracted by in-house texture analysis algorithms implemented in MATLAB 2019b. The LASSO logistic regression model was used to choose the most useful predictive features, and ten-fold cross-validation was performed. Two prediction models were constructed using multivariable logistic regression analysis: one based on clinical variables, and the other based on clinical variables with the radiomics score. Predictability of the two models was assessed with the AUC of the ROC curves.

RESULTS

Clinical characteristics did not significantly differ between malignant and benign nodules, except for mean nodule size. Among 730 candidate texture features generated from a single US image, 15 features were selected. Radiomics signatures were constructed with a radiomics score, using selected features. In multivariable logistic regression analysis, higher radiomics score was associated with malignancy (OR = 10.923; p < 0.001). The AUC of the malignancy prediction model composed of clinical variables with the radiomics score was significantly higher than the model composed of clinical variables alone (0.839 vs 0.583).

CONCLUSIONS

Quantitative US radiomics features can help predict malignancy in thyroid nodules with indeterminate cytology.

Radiomics Based on Thyroid Ultrasound Can Predict Distant Metastasis of Follicular Thyroid Carcinoma

We aimed to evaluate whether radiomics analysis based on gray-scale ultrasound (US) can predict distant metastasis of follicular thyroid cancer (FTC). We retrospectively included 35 consecutive FTCs with distant metastases and 134 FTCs without distant metastasis. We extracted a total of 60 radiomics features derived from the first order, shape, gray-level cooccurrence matrix, and gray-level size zone matrix features using US imaging. A radiomics signature was generated using the least absolute shrinkage and selection operator and was used to train a support vector machine (SVM) classifier in five-fold cross-validation. The SVM classifier showed an area under the curve (AUC) of 0.90 on average on the test folds. Age, size, widely invasive histology, extrathyroidal extension, lymph node metastases on pathology, nodule-in-nodule appearance, marked hypoechogenicity, and rim calcification on the US were significantly more frequent among FTCs with distant metastasis compared to those without metastasis (p < 0.05). Radiomics signature and widely invasive histology were significantly associated with distant metastasis on multivariate analysis (p < 0.01 and p = 0.003). The classifier using the results of the multivariate analysis showed an AUC of 0.93. The radiomics signature from thyroid ultrasound is an independent biomarker for noninvasively predicting distant metastasis of FTC.