Using ultrasound features and radiomics analysis to predict lymph node metastasis in patients with thyroid cancer

A risk stratification model based on ultrasound radiologic features for cervical metastatic lymph nodes in papillary thyroid cancer

BACKGROUND

Accurate preoperative evaluation for metastatic lesions is significant for PTC patients. However, the stratification systems revealed inconsistencies in the ultrasound (US) features of cervical metastatic lymph nodes (LNs). This study aimed to investigate and develop a risk stratification model based on US radiologic features for cervical metastatic lesions in PTC patients.

METHODS

This study retrospectively enrolled 1806 LNs from 1665 PTC patients who underwent US-guided fine-needle aspiration biopsy for cervical LNs from January 2010 to December 2022. Univariable and multivariable logistic regression analyses determined and developed the independent risk US features and a risk stratification model for cervical metastatic LNs. The performance of the risk stratification model was assessed and validated by the Korean Society of Thyroid Radiology and the European Thyroid Association.

RESULTS

Among the 1806 LNs, 1411 LNs were pathologically diagnosed with malignant. Multivariate analysis indicated that the absence of fatty hilum, cystic components, round shape (SD/LD ≥ 0.5), abundant vascularity, hyperechogenicity (including hyper and hypo-echogenicity, and hyper-echogenicity), and calcifications (include microcalcification, and macrocalcification) were independent risk US features associated with malignant LNs. A risk stratification model for cervical metastatic LNs was developed based on these suspicious US features and showed well-predicted performance (C-index 0.840; 95% CI: 0.840-0.923).

CONCLUSION

Our study proposed a new risk stratification system based on US radiologic features to predict cervical metastatic lymph nodes in PTC patients. We identified several risk factors for lymph node (LN) metastasis from PTC including the absence of fatty hilum, cystic components, round shape (SD/LD ≥ 0.5), abnormal vascularity, hyper-echogenicity, hyper- and hypo-echogenicity, microcalcification, and macrocalcification. These features could serve as valuable indicators for surgeons to accurately assess the status of cervical LNs.

The value of MRI radiomics in distinguishing different types of spinal infections

BACKGROUND

In clinical practice, the three most prevalent forms of infectious spondylitis are tuberculous spondylitis (TS), brucellosis spondylitis (BS), and pyogenic spondylitis (PS). It is possible to successfully lessen neurological and spinal damage by detecting them early. In the medical field, radiomics has been applied extensively. It is crucial to find out if MRI imaging can be used to diagnose spinal infections early.

PURPOSE

To explore the diagnostic value of establishing models based on MRI radiomics for different spinal infections.

METHODS

This retrospective study collected clinical and magnetic resonance imaging information on a total of 136 patients diagnosed with spondylitis in April 2019 and August 2023, who were classified into specific spinal infections (TS or BS) and non-specific spinal infections (PS) based on treatment. 3D Slicer software was used to outline the region of interest (ROI) and extracted ROI features. All patients were randomly divided into a training set and a test set (7:3), and after standardized, the t-test and LASSO were sequentially performed in the training set to extract the optimal radiomic features. These features were used to calculate the Radscore and construct the features classifier model and evaluated by test set. Univariate and multivariate logistic regression of Radscore and clinical features to identify predictors contributing to the diagnosis were used to plot nomograms, the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA) to assess the nomogram. The same approach described above was used to diagnose both subgroups of BS and TS in SSI.

RESULTS

321 radiological features were extracted from the three different sequences. The remaining 7 optimal radiomics features were used to calculate the Radscore and establish three feature classifier models, with RF having the best performance (AUC=1 and 0.86). And after univariate and multivariate logistic regression, the final nomogram constructed by Radscore and had good discriminatory performance in the training set and the test set (AUC =0.924 and 0.868), and the calibration curve and DCA showed good clinical efficacy. In the subgroup, the AUC of the training and test sets was 0.929and0.863.

CONCLUSION

The diagnostic model based on MR radiomics can gradually differentiate tuberculous spondylitis, brucellosis spondylitis, and pyogenic spondylitis.

Multiparameter and Ultrasound Radiomics Nomogram to Predict the Aggressiveness of Papillary Thyroid Carcinomas: A Multicenter, Retrospective Study

RATIONALE AND OBJECTIVES

To construct a multiparameter radiomics nomogram based on ultrasound (US) to predict the aggressiveness of thyroid papillary carcinoma (PTC).

MATERIALS AND METHODS

In total, 471 consecutive patients from three institutions were included in this study. Among them, patients from institution 1 were used for training (n = 294) and internal validation (n = 92), while 85 patients from institution 2 and institution 3 were used for external validation. Radiomics features were extracted from the conventional US. The least absolute shrinkage was employed to select the most relevant features for the aggressiveness of PTC, along with the maximum relevance minimum redundancy algorithm and selection operator. These features were then used to construct the radiomics signature (RS). Subsequently, relevant multiparameter ultrasound (MPUS) features from shear-wave elastic (SWE) and strain elastography (SE) will be extracted using multivariable logistic regression. The final radionics nomogram was conducted using the RS, clinical information, and conventional US and MPUS features. The receiver operating characteristic (ROC), calibration, and decision curves were used to evaluate the performance of the nomogram.

RESULTS

Multivariable logistic regression analysis indicated that age, nodule size, capsule abutment, SWV tumor, and RS were independent predictors of the aggressiveness of PTC. The radiomics nomogram, utilizing these characteristics, displayed impressive performance with an AUC of 0.920 [95% CI, 0.889-0.950], 0.901 [95% CI, 0.839-0.963], and 0.896 [95% CI, 0.823-0.969] in the training, internal, and external validation cohort. It outperformed the clinical US, MPUS, and RS models (p < 0.05). The decision curve analysis indicated that the nomogram offered valuable clinical utility.

CONCLUSION

The nomogram incorporated MPUS and radiomics have good diagnostic performance in predicting the aggressiveness of PTC which may help in the selection of the surgical modality.

Mechanism of the microRNA-373-3p/LATS2 Axis in the Prognosis and Metastasis of Thyroid Cancer Patients

This study focused on the role of the microRNA (miR)-373-3p/LATS2 axis in the prognosis and metastasis of thyroid cancer patients. miR-373-3p and LATS2 expression were assessed in thyroid cancer tissues and cells. The relationship between miR-373-3p and clinicopathological characteristics of patients with thyroid cancer and the impact of miR-373-3p and LATS2 expression levels on the survival and prognosis of thyroid cancer patients were analyzed. The targeting relationship between miR-373-3p and LATS2 was predicted and verified, and their impact on the malignant cell phenotype was assessed. Compared with adjacent normal tissues and normal human thyroid cells, miR-373-3p was highly expressed, while LATS2 was expressed at low levels in thyroid cancer tissues and cells (both p < 0.001). miR-373-3p expression was independent of age (p = 0.201) and gender (p = 0.516), and it was correlated with lymph node metastasis and TNM stage of thyroid cancer (both p < 0.001). Moreover, high miR-373-3p expression was associated with poor patient prognosis (p = 0.034). Interference with miR-373-3p or overexpression of LATS2 repressed KMH-2 cell malignant phenotypes (all p < 0.05). miR-373-3p targeted and suppressed LATS2 expression. Interference with miR-373-3p blocked its inhibition on LATS2, thereby repressing thyroid cancer progression and metastasis.

The application of a clinical-multimodal ultrasound radiomics model for predicting cervical lymph node metastasis of thyroid papillary carcinoma

Background

PTC (papillary thyroid cancer) is a lymphotropic malignancy associated with cervical lymph node metastasis (CLNM, including central and lateral LNM), which compromises the effect of treatment and prognosis of patients. Accurate preoperative identification will provide valuable reference information for the formulation of diagnostic and treatment strategies. The aim of this study was to develop and validate a clinical-multimodal ultrasound radiomics model for predicting CLNM of PTC.

Methods

One hundred sixty-four patients with PTC who underwent treatment at our hospital between March 2016 and December 2021 were included in this study. The patients were grouped into a training cohort (n=115) and a validation cohort (n=49). Radiomic features were extracted from the conventional ultrasound (US), contrast-enhanced ultrasound (CEUS) and strain elastography-ultrasound (SE-US) images of patients with PTC. Multivariate logistic regression analysis was used to identify the independent risk factors. FAE software was used for radiomic feature extraction and the construction of different prediction models. The diagnostic performance of each model was evaluated and compared in terms of the area under the curve (AUC), sensitivity, specificity, accuracy, negative predictive value (NPV) and positive predictive value (PPV). RStudio software was used to develop the decision curve and assess the clinical value of the prediction model.

Results

The clinical-multimodal ultrasound radiomics model developed in this study can successfully detect CLNM in PTC patients. A total of 3720 radiomic features (930 features per modality) were extracted from the ROIs of the multimodal images, and 15 representative features were ultimately screened. The combined model showed the best prediction performance in both the training and validation cohorts, with AUCs of 0.957 (95% CI: 0.918-0.987) and 0.932 (95% CI: 0.822-0.984), respectively. Decision curve analysis revealed that the combined model was superior to the other models.

Conclusion

The clinical-multimodal ultrasound radiomics model constructed with multimodal ultrasound radiomic features and clinical risk factors has favorable potential and high diagnostic value for predicting CLNM in PTC patients.

Quantitative ultrasound radiomics analysis to evaluate lymph nodes in patients with cancer: a systematic review

This systematic review aims to evaluate the role of ultrasound (US) radiomics in assessing lymphadenopathy in patients with cancer and the ability of radiomics to predict metastatic lymph node involvement. A systematic literature search was performed in the PubMed (MEDLINE), Cochrane Central Register of Controlled Trials (CENTRAL), and EMBASE (Ovid) databases up to June 13, 2023. 42 articles were included in which the lymph node mass was assessed with a US exam, and the analysis was performed using radiomics methods. From the survey of the selected articles, experimental evidence suggests that radiomics features extracted from US images can be a useful tool for predicting and characterizing lymphadenopathy in patients with breast, head and neck, and cervical cancer. This noninvasive and effective method allows the extraction of important information beyond mere morphological characteristics, extracting features that may be related to lymph node involvement. Future studies are needed to investigate the role of US-radiomics in other types of cancers, such as melanoma.

Prediction of TNFRSF9 expression and molecular pathological features in thyroid cancer using machine learning to construct Pathomics models

BACKGROUND

The TNFRSF9 molecule is pivotal in thyroid carcinoma (THCA) development. This study utilizes Pathomics techniques to predict TNFRSF9 expression in THCA tissue and explore its molecular mechanisms.

METHODS

Transcriptome data, pathology images, and clinical information from the cancer genome atlas (TCGA) were analyzed. Image segmentation and feature extraction were performed using the OTSU's algorithm and pyradiomics package. The dataset was split for training and validation. Features were selected using maximum relevance minimum redundancy recursive feature elimination (mRMR_RFE) and modeling conducted with the gradient boosting machine (GBM) algorithm. Model evaluation included receiver operating characteristic curve (ROC) analysis. The Pathomics model output a probabilistic pathomics score (PS) for gene expression prediction, with its prognostic value assessed in TNFRSF9 expression groups. Subsequent analysis involved gene set variation analysis (GSVA), immune gene expression, cell abundance, immunotherapy susceptibility, and gene mutation analysis.

RESULTS

High TNFRSF9 expression correlated with worsened progression-free interval (PFI) and acted as an independent risk factor [hazard ratio (HR) = 2.178, 95% confidence interval (CI) 1.045-4.538, P = 0.038]. Nine pathohistological features were identified. The GBM Pathomics model demonstrated good prediction efficacy [area under the curve (AUC) 0.819 and 0.769] and clinical benefits. High PS was a PFI risk factor (HR = 2.156, 95% CI 1.047-4.440, P = 0.037). Patients with high PS potentially exhibited enriched pathways, increased TIGIT gene expression, Tregs infiltration (P < 0.0001), and higher rates of gene mutations (BRAF, TTN, TG).

CONCLUSIONS

The GBM Pathomics model constructed based on the pathohistological features of H&E-stained sections well predicted the expression level of TNFRSF9 molecules in THCA.

Radiomics and deep learning for large volume lymph node metastasis in papillary thyroid carcinoma

Background

Thyroid cancer is prone to early lymph node metastasis (LNM), and patients with large volume LNM (LVLNM) tend to have a poorer prognosis. The aim of this study was to predict LVLNM in before surgery based on radiomics and deep learning (DL).

Methods

A multicenter retrospective study was performed, including 854 papillary thyroid carcinoma (PTC) patients from three centers. Radiomics features were extracted. Logistic regression (LR), support vector machine (SVM), K-nearest neighbors (KNN), multi-layer perceptron (MLP), random forest (RF), ExtraTrees, extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) algorithms were used to construct radiomics models. AlexNet, DenseNet121, inception_v3, ResNet50, and transformer algorithms were used to construct DL models. The receiver operating characteristic (ROC) curve was employed to select the better-performing model. A combined model was then created by merging radiomics features and DL features. The least absolute shrinkage and selection operator (LASSO) method was utilized to identify metabolites and radiomics features with non-zero coefficients. The performance of the models was evaluated using area under the curve (AUC), accuracy (ACC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), and F1-score.

Results

A total of 1,357 radiomics features were extracted. Among the radiomics models, the ExtraTrees model demonstrated the optimal diagnostic capabilities with an AUC of 0.787 [95% confidence interval (CI): 0.715-0.858], and DenseNet121 DL model demonstrated the optimal diagnostic capabilities with an AUC of 0.766 (95% CI: 0.683-0.848). Furthermore, the combined model, named the Thy-DL-Radiomics model, exhibited an AUC of 0.839 (95% CI: 0.758-0.920) in the internal validation set and 0.789 (95% CI: 0.718-0.859) in the external validation set.

Conclusions

A radiomics-DL features integrated model can predict LVLNM in PTC patients and provide guidance for personalized treatment.

Enhanced stiffness in peri-cancerous tissue: a marker of poor prognosis in papillary thyroid carcinoma with lymph node metastasis

BACKGROUND

The prognostic significance of lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) remains controversial. Notably, there is evidence suggesting an association between tissue stiffness and the aggressiveness of the disease. We therefore aimed to explore the effect of tissue stiffness on LNM-related invasiveness in PTC patients.

METHOD

A total of 2492 PTC patients from 3 hospitals were divided into an LNM group and a non-LNM group based on their pathological results. The effects of interior lesion stiffness (E) and peri-cancerous tissue stiffness (Eshell) on the LNM-related recurrence rate and mortality in each patient with PTC subgroup were analyzed. The activation of cancer-associated fibroblasts (CAFs) and extracellular matrix component type 1 collagen (COL-I) in the lesion were compared and analyzed across different subgroups. The underlying biological basis of differences in each subgroup was identified using RNA sequencing (RNA-seq) data.

RESULTS

The Eshell value and Eshell/E in the LNM group were significantly higher than those in the non-LNM group of patients with PTC (Eshell: 72.72 ± 5.63 vs 66.05 ± 4.46; Eshell/E: 1.20 ± 1.72 vs 1.09 ± 1.10, P < .001). When Eshell/E > 1.412 and LNM were both present, the recurrence rate and mortality were significantly increased compared to those of group of patients with LNM (91.67% and 7.29%, respectively). The CAF activation and COL-I content in the Eshell/E+ group were significantly higher than those in the Eshell/E- group (all P < .001), and the RNA-seq results revealed significant extracellular matrix (ECM) remodeling in the LNM-Eshell/E+ group.

CONCLUSIONS

Stiff peri-cancerous tissue induced CAF activation, COL-I deposition, and ECM remodeling, resulting in a poor prognosis for PTC patients with LNM.

Machine learning model for non-alcoholic steatohepatitis diagnosis based on ultrasound radiomics

BACKGROUND

Non-Alcoholic Steatohepatitis (NASH) is a crucial stage in the progression of Non-Alcoholic Fatty Liver Disease(NAFLD). The purpose of this study is to explore the clinical value of ultrasound features and radiological analysis in predicting the diagnosis of Non-Alcoholic Steatohepatitis.

METHOD

An SD rat model of hepatic steatosis was established through a high-fat diet and subcutaneous injection of CCl4. Liver ultrasound images and elastography were acquired, along with serum data and histopathological results of rat livers.The Pyradiomics software was used to extract radiomic features from 2D ultrasound images of rat livers. The rats were then randomly divided into a training set and a validation set, and feature selection was performed through dimensionality reduction. Various machine learning (ML) algorithms were employed to build clinical diagnostic models, radiomic models, and combined diagnostic models. The efficiency of each diagnostic model for diagnosing NASH was evaluated using Receiver Operating Characteristic (ROC) curves, Clinical Decision Curve Analysis (DCA), and calibration curves.

RESULTS

In the machine learning radiomic model for predicting the diagnosis of NASH, the Area Under the Curve (AUC) of ROC curve for the clinical radiomic model in the training set and validation set were 0.989 and 0.885, respectively. The Decision Curve Analysis revealed that the clinical radiomic model had the highest net benefit within the probability threshold range of > 65%. The calibration curve in the validation set demonstrated that the clinical combined radiomic model is the optimal method for diagnosing Non-Alcoholic Steatohepatitis.

CONCLUSION

The combined diagnostic model constructed using machine learning algorithms based on ultrasound image radiomics has a high clinical predictive performance in diagnosing Non-Alcoholic Steatohepatitis.

Application value of volumetric CT value in quantifying the activity of a pulmonary tuberculoma

OBJECTIVE

The purpose of this study was to explore the auxiliary diagnostic value of volumetric CT value in quantifying the activity of a pulmonary tuberculoma.

METHODS

Chest CT image data of 112 patients with pulmonary tuberculomas who were diagnosed clinically between October 16, 2013 and March 21, 2023 were selected. With the shortest diameter axis>5 mm on the mediastinal window serving as the inclusion criterion, 108 active tuberculomas and 64 non-active tuberculomas were selected. The focused image was manually segmented using ITK-SNAP software, the volumetric CT value of the focus was calculated, and the ROC curve was analyzed. Using the final clinical diagnosis as the reference standard, the auxiliary diagnostic efficacy and consistency of the conventional CT film reading method and volumetric CT value in determining the activity of a pulmonary tuberculoma were compared.

RESULTS

The volumetric CT value of 108 active pulmonary tuberculoma lesions (33.39 [28.17,36.23] HU) was significantly less than 64 inactive pulmonary tuberculoma lesions (78.91 [57.81,120.31] HU); the difference was statistically significant (Z = -10.888. P < 0.001). ROC curve analysis showed that at a maximum Yoden index value of 0.963, the optimal volumetric CT threshold value was 45.32 HU, the sensitivity and specificity of the volumetric CT value in determining the activity of a pulmonary tuberculoma were 97.2% and 100.0%, respectively, and the maximum area under the ROC curve was 0.998. Taking the final clinical diagnosis as the reference standard, the sensitivity, specificity, consistency, and kappa value of the conventional CT film reading method for determining the activity of a pulmonary tuberculoma were 72.2% (78/108), 70.3% (45/64), 71.5% (123/172), and 0.413, respectively, while the corresponding volumetric CT values were 97.2% (105/108), 100.0% (64/64), 98.3% (168/172), and 0.951, respectively.

CONCLUSION

Accurately quantifying the volumetric CT value of a pulmonary tuberculoma focus determines the activity of a pulmonary tuberculoma, which has very important auxiliary diagnostic value.

Artificial Intelligence-Driven Radiomics in Head and Neck Cancer: Current Status and Future Prospects

BACKGROUND

Radiomics is a rapidly growing field used to leverage medical radiological images by extracting quantitative features. These are supposed to characterize a patient's phenotype, and when combined with artificial intelligence techniques, to improve the accuracy of diagnostic models and clinical outcome prediction.

OBJECTIVES

This review aims at examining the application areas of artificial intelligence-based radiomics (AI-based radiomics) for the management of head and neck cancer (HNC). It further explores the workflow of AI-based radiomics for personalized and precision oncology in HNC. Finally, it examines the current challenges of AI-based radiomics in daily clinical oncology and offers possible solutions to these challenges.

METHODS

Comprehensive electronic databases (PubMed, Medline via Ovid, Scopus, Web of Science, CINAHL, and Cochrane Library) were searched following the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines. The quality of included studies and their risk of biases were evaluated using the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD)and Prediction Model Risk of Bias Assessment Tool (PROBAST).

RESULTS

Out of the 659 search hits retrieved, 45 fulfilled the inclusion criteria. Our review revealed that the application of AI-based radiomics model as an ancillary tool for improved decision-making in HNC management includes radiomics-based cancer diagnosis and radiomics-based cancer prognosis. The radiomics-based cancer diagnosis includes tumor staging, tumor grading, and classification of malignant and benign tumors. Similarly, radiomics-based cancer prognosis includes prediction for treatment response, recurrence, metastasis, and survival. In addition, the challenges in the implementation of these models for clinical evaluations include data imbalance, feature engineering (extraction and selection), model generalizability, multi-modal fusion, and model interpretability.

CONCLUSION

Considering the highly subjective and interobserver variability that is peculiar to the interpretation of medical images by expert clinicians, AI-based radiomics seeks to offer potentially useful quantitative information, which is not visible to the human eye or unintentionally often remain ignored during clinical imaging practice. By enabling the extraction of this type of information, AI-based radiomics has the potential to revolutionize HNC oncology, providing a platform for more personalized, higher quality, and cost-effective care for HNC patients.

Prediction of lymph node metastasis in patients with papillary thyroid cancer based on radiomics analysis and intraoperative frozen section analysis: A retrospective study

INTRODUCTION

To evaluate the diagnostic efficiency among the clinical model, the radiomics model and the nomogram that combined radiomics features, frozen section (FS) analysis and clinical characteristics for the prediction of lymph node (LN) metastasis in patients with papillary thyroid cancer (PTC).

METHODS

A total of 208 patients were randomly divided into two groups randomly with a proportion of 7:3 for the training groups (n = 146) and the validation groups (n = 62). The Least Absolute Shrinkage and Selection Operator (LASSO) regression was used for the selection of radiomics features extracted from ultrasound (US) images. Univariate and multivariate logistic analyses were used to select predictors associated with the status of LN. The clinical model, radiomics model and nomogram were subsequently established by logistic regression machine learning. The area under the curve (AUC), sensitivity and specificity were used to evaluate the diagnostic performance of the different models. The Delong test was used to compare the AUC of the three models.

RESULTS

Multivariate analysis indicated that age, size group, Adler grade, ACR score and the psammoma body group were independent predictors of lymph node metastasis (LNM). The results showed that in both the training and validation groups, the nomogram showed better performance than the clinical model, albeit not statistically significant (p > .05), and significantly outperformed the radiomics model (p < .05). However, the nomogram exhibits a slight improvement in sensitivity that could reduce the incidence of false negatives.

CONCLUSION

We propose that the nomogram holds substantial promise as an effective tool for predicting LNM in patients with PTC.

Single-cell and bulk RNA sequencing reveal heterogeneity and diagnostic markers in papillary thyroid carcinoma lymph-node metastasis

PURPOSE

Papillary thyroid carcinoma (PTC) is characterized by lymph-node metastasis (LNM), which affects recurrence and prognosis. This study analyzed PTC LNM by single-cell RNA sequencing (scRNA-seq) data and bulk RNA sequencing (RNA-seq) to find diagnostic markers and therapeutic targets.

METHODS

ScRNA-seq data were clustered and malignant cells were identified. Differentially expressed genes (DEGs) were identified in malignant cells of scRNA-seq and bulk RNA-seq, respectively. PTC LNM diagnostic model was constructed based on intersecting DEGs using glmnet package. Next, PTC samples from 66 patients were used to validate the two most significant genes in the diagnostic model, S100A2 and type 2 deiodinase (DIO2) by quantitative reverse transcription-polymerase chain reaction (RT-qPCR) and immunohistochemical (IHC). Further, the inhibitory effect of DIO2 on PTC cells was verified by cell biology behavior, western blot, cell cycle analysis, 5-ethynyl-2'-deoxyuridine (EdU) assay, and xenograft tumors.

RESULTS

Heterogeneity of PTC LNM was demonstrated by Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) analysis. A total of 19 differential genes were used to construct the diagnostic model. S100A2 and DIO2 differ significantly at the RNA (p < 0.01) and protein level in LNM patient tissues (p < 0.001). And differed in PTC tissues with different pathologic typing (p < 0.001). Further, EdU (p < 0.001) and cell biology behavior revealed that PTC cells overexpressed DIO2 had reduced proliferative capacity. Cell cycle proteins were reduced and cells are more likely to be stuck in G2/M phase (p < 0.001).

CONCLUSIONS

This study explored the heterogeneity of PTC LNM using scRNA-seq. By combining with bulk RNA-seq data, diagnostic markers were explored and the model was established. Clinical diagnostic efficacy of S100A2 and DIO2 was validated and the treatment potential of DIO2 was discovered.

Application of ultrasound elastography and radiomic for predicting central cervical lymph node metastasis in papillary thyroid microcarcinoma

Objective

This study aims to combine ultrasound (US) elastography (USE) and radiomic to predict central cervical lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC).

Methods

A total of 204 patients with 204 thyroid nodules who were confirmed with PTMC and treated in our hospital were enrolled and randomly assigned to the training set (n = 142) and the validation set (n = 62). US features, USE (gender, shape, echogenic foci, thyroid imaging reporting and data system (TIRADS) category, and elasticity score), and radiomic signature were employed to build three models. A nomogram was plotted for the combined model, and decision curve analysis was applied for clinical use.

Results

The combined model (USE and radiomic) showed optimal diagnostic performance in both training (AUC = 0.868) and validation sets (AUC = 0.857), outperforming other models.

Conclusion

The combined model based on USE and radiomic showed a superior performance in the prediction of CLNM of patients with PTMC, covering the shortage of low specificity of conventional US in detecting CLNM.

Cervical lymph node metastasis prediction from papillary thyroid carcinoma US videos: a prospective multicenter study

BACKGROUND

Prediction of lymph node metastasis (LNM) is critical for individualized management of papillary thyroid carcinoma (PTC) patients to avoid unnecessary overtreatment as well as undesired under-treatment. Artificial intelligence (AI) trained by thyroid ultrasound (US) may improve prediction performance.

METHODS

From September 2017 to December 2018, patients with suspicious PTC from the first medical center of the Chinese PLA general hospital were retrospectively enrolled to pre-train the multi-scale, multi-frame, and dual-direction deep learning (MMD-DL) model. From January 2019 to July 2021, PTC patients from four different centers were prospectively enrolled to fine-tune and independently validate MMD-DL. Its diagnostic performance and auxiliary effect on radiologists were analyzed in terms of receiver operating characteristic (ROC) curves, areas under the ROC curve (AUC), accuracy, sensitivity, and specificity.

RESULTS

In total, 488 PTC patients were enrolled in the pre-training cohort, and 218 PTC patients were included for model fine-tuning (n = 109), internal test (n = 39), and external validation (n = 70). Diagnostic performances of MMD-DL achieved AUCs of 0.85 (95% CI: 0.73, 0.97) and 0.81 (95% CI: 0.73, 0.89) in the test and validation cohorts, respectively, and US radiologists significantly improved their average diagnostic accuracy (57% vs. 60%, P = 0.001) and sensitivity (62% vs. 65%, P < 0.001) by using the AI model for assistance.

CONCLUSIONS

The AI model using US videos can provide accurate and reproducible prediction of cervical lymph node metastasis in papillary thyroid carcinoma patients preoperatively, and it can be used as an effective assisting tool to improve diagnostic performance of US radiologists.

TRIAL REGISTRATION

We registered on the Chinese Clinical Trial Registry website with the number ChiCTR1900025592.

Combined clinical variable and radiomics of post-treatment total body scan for prediction of successful I-131 ablation in low-risk papillary thyroid carcinoma patients

To explore the feasibility of combined radiomics of post-treatment I-131 total body scan (TBS) and clinical parameter to predict successful ablation in low-risk papillary thyroid carcinoma (PTC) patients. Data of low-risk PTC patients who underwent total/near total thyroidectomy and I-131 ablation 30 mCi between April 2015 and July 2021 were retrospectively reviewed. The clinical factors studied included age, sex, and pre-ablative serum thyroglobulin (Tg). Radiomic features were extracted via PyRadiomics, and radiomic feature selection was performed. The predictive performance for successful ablation of the clinical parameter, radiomic, and combined models (radiomics combined with clinical parameter) was calculated using the area under the receiver operating characteristic curve (AUC). One hundred and thirty patients were included. Successful ablation was achieved in 77 patients (59.2%). The mean pre-ablative Tg in the unsuccessful group (15.50 ± 18.04 ng/ml) was statistically significantly higher than those in the successful ablation group (7.12 ± 7.15 ng/ml). The clinical parameter, radiomic, and combined models produced AUCs of 0.66, 0.77, and 0.87 in the training sets, and 0.65, 0.69, and 0.78 in the validation sets, respectively. The combined model produced a significantly higher AUC than that of the clinical parameter (p < 0.05). Radiomic analysis of the post-treatment TBS combined with pre-ablative serum Tg showed a significant improvement in the predictive performance of successful ablation in low-risk PTC patients compared to the use of clinical parameter alone.Thai Clinical Trials Registry TCTR identification number is TCTR20230816004 ( https://www.thaiclinicaltrials.org/show/TCTR20230816004 ).

Detection of thyroglobulin for diagnosis of metastatic lateral cervical lymph nodes in papillary thyroid carcinoma: accuracy and application in clinical practice

Background

Accurate assessment of lateral cervical lymph node metastasis (LLNM) involvement is important for treating papillary thyroid carcinoma (PTC). Thyroglobulin is associated with LLNM, but there may be differences in the diagnostic value of serum thyroglobulin (sTg) and fine needle aspiration washout fluid thyroglobulin (FNA-Tg). Herein, we investigated the optimal cutoff value (OCV) of sTg and FNA-Tg and their diagnostic performance.

Methods

We enrolled 116 PTC patients who underwent radical resection of thyroid carcinoma with lateral cervical lymph node dissection at the Affiliated Hospital of Zunyi Medical University from June 2018 to July 2022. We used the receiver operating characteristic (ROC) curve analysis to determine the OCV for sTg and FNA-Tg to diagnose LLNM in PTC patients. We also evaluated the performance of FNA-Tg, sTg, fine needle aspiration cytology (FNAC), and their combinations for diagnosis. Pathological results were the gold standard.

Results

We performed 125 lymph node dissections, 106 had metastasis, and 19 did not. The OCV for sTg was 17.31 ng/mL [area under the curve (AUC) =0.760, sensitivity =78.30%, specificity =73.68%, and accuracy =77.60%]. Meanwhile, the OCV for FNA-Tg was 4.565 ng/mL (AUC =0.948, sensitivity =89.62%, specificity =100%, and accuracy =91.20%). The combination of FNAC and FNA-Tg presented the greatest diagnostic performance for LLNM detection in PTC patients. Moreover, serum antithyroglobulin antibody (TgAb) was not correlated with sTg or FNA-Tg levels.

Conclusions

The cutoff value for the diagnosis of LLNM in PTC are sTg >17.31 ng/mL or FNA-Tg >4.565 ng/mL. The combination method of FNA-Tg and FNAC is the most optimal choice for the diagnosis of LLNM and is highly recommended for further clinical application.

Prediction of cervical lymph node metastasis in differentiated thyroid cancer based on radiomics models

OBJECTIVE

The accurate clinical diagnosis of cervical lymph node metastasis plays an important role in the treatment of differentiated thyroid cancer (DTC). This study aimed to explore and summarize a more objective approach to detect cervical malignant lymph node metastasis of DTC via radiomics models.

METHODS

PubMed, Web of Science, MEDLINE, EMBASE, and Cochrane databases were searched for all eligible studies. Articles using radiomics models based on ultrasound, computed tomography, or magnetic resonance imaging to assess cervical lymph node metastasis preoperatively were included. Characteristics and diagnostic accuracy measures were extracted. Bias and applicability judgments were evaluated by the revised QUADAS-2 tool. The estimates were pooled using a random-effects model. Additionally, the leave-one-out method was conducted to assess the heterogeneity.

RESULTS

Twenty-nine radiomics studies with 6160 validation set patients were included in the qualitative analysis, and 11 studies with 3863 validation set patients were included in the meta-analysis. Four of them had an external independent validation set. The studies were heterogeneous, and a significant risk of bias was found in 29 studies. Meta-analysis showed that the pooled sensitivity and specificity for preoperative prediction of lymph node metastasis via US-based radiomics were 0.81 (95% CI, 0.73-0.86) and 0.87 (95% CI, 0.83-0.91), respectively.

CONCLUSIONS

Although radiomics-based models for cervical lymphatic metastasis in DTC have been demonstrated to have moderate diagnostic capabilities, broader data, standardized radiomics features, robust feature selection, and model exploitation are still needed in the future.

ADVANCES IN KNOWLEDGE

The radiomics models showed great potential in detecting malignant lymph nodes in thyroid cancer.

Multi-modal ultrasound multistage classification of PTC cervical lymph node metastasis via DualSwinThyroid

Objective

This study aims to predict cervical lymph node metastasis in papillary thyroid carcinoma (PTC) patients with high accuracy. To achieve this, we introduce a novel deep learning model, DualSwinThyroid, leveraging multi-modal ultrasound imaging data for prediction.

Materials and methods

We assembled a substantial dataset consisting of 3652 multi-modal ultrasound images from 299 PTC patients in this retrospective study. The newly developed DualSwinThyroid model integrates various ultrasound modalities and clinical data. Following its creation, we rigorously assessed the model's performance against a separate testing set, comparing it with established machine learning models and previous deep learning approaches.

Results

Demonstrating remarkable precision, DualSwinThyroid achieved an AUC of 0.924 and an 96.3% accuracy on the test set. The model efficiently processed multi-modal data, pinpointing features indicative of lymph node metastasis in thyroid nodule ultrasound images. It offers a three-tier classification that aligns each level with a specific surgical strategy for PTC treatment.

Conclusion

DualSwinThyroid, a deep learning model designed with multi-modal ultrasound radiomics, effectively estimates the degree of cervical lymph node metastasis in PTC patients. In addition, it also provides early, precise identification and facilitation of interventions for high-risk groups, thereby enhancing the strategic selection of surgical approaches in managing PTC patients.

Lymph node imaging for thyroid cancer

Cervical lymph nodes (LNs) in the central (level VI) and lateral (levels II-V) compartments of the neck are the most common sites of locoregional metastases associated with thyroid cancer. Prophylactic nodal dissections are uncommon in modern thyroid surgery and are not routinely performed due to concern for increased morbidity and do not offer improved survival. Therefore, a selective approach for LN dissections is increasingly important. Preoperatively, this is most frequently assessed with cervical ultrasound (US). Contrast-enhanced computed tomography (CT) of the neck can also be used for preoperative assessment. Both US and CT imaging can be used to characterise LNs in levels II-VI and their risk of malignancy based on size, morphology, and growth. US-guided fine-needle aspiration of equivocal LN with thyroglobulin (Tg) washout can also determine if a LN harbours malignancy. For postoperative surveillance after total thyroidectomy, both US and CT continue to play an important role at 6-12 months intervals. These patients may also benefit from additional biochemical data such as Tg levels in addition to LN and thyroid bed imaging. Thyroid uptake scans may also play a role in LN surveillance postoperatively for well-differentiated thyroid carcinoma in certain clinical contexts. Less commonly, positron emitted tomography may play a role, but is typically reserved for patients with aggressive or radioactive iodine refractory disease.

Reproducibility and location-stability of radiomic features derived from cone-beam computed tomography: a phantom study

OBJECTIVES

This study aims to determine the reproducibility and location-stability of cone-beam computed tomography (CBCT) radiomic features.

METHODS

Centrifugal tubes with six concentrations of K2HPO4 solutions (50, 100, 200, 400, 600, and 800 mg ml-1) were imaged within a customized phantom. For each concentration, images were captured twice as test and retest sets. Totally, 69 radiomic features were extracted by LIFEx. The reproducibility was assessed between the test and retest sets. We used the concordance correlation coefficient (CCC) to screen qualified features and then compared the differences in the numbers of them under 24 series (four locations groups * six concentrations). The location-stability was assessed using the Kruskal-Wallis test under different concentration sets; likewise, the numbers of qualified features under six test sets were analyzed.

RESULTS

There were 20 and 23 qualified features in the reproducibility and location-stability experiments, respectively. In the reproducibility experiment, the performance of the peripheral groups and high-concentration sets was significantly better than the center groups and low-concentration sets. The effect of concentration on the location-stability of features was not monotonic, and the number of qualified features in the low-concentration sets was greater than that in the high-concentration sets. No features were qualified in both experiments.

CONCLUSIONS

The density and location of the target object can affect the number of reproducible radiomic features, and its density can also affect the number of location-stable radiomic features. The problem of feature reliability should be treated cautiously in radiomic research on CBCT.

Artificial intelligence-based prediction of cervical lymph node metastasis in papillary thyroid cancer with CT

OBJECTIVES

To develop an artificial intelligence (AI) system for predicting cervical lymph node metastasis (CLNM) preoperatively in patients with papillary thyroid cancer (PTC) based on CT images.

METHODS

This multicenter retrospective study included the preoperative CT of PTC patients who were divided into the development, internal, and external test sets. The region of interest of the primary tumor was outlined manually on the CT images by a radiologist who has eight years of experience. With the use of the CT images and lesions masks, the deep learning (DL) signature was developed by the DenseNet combined with convolutional block attention module. One-way analysis of variance and least absolute shrinkage and selection operator were used to select features, and a support vector machine was used to construct the radiomics signature. Random forest was used to combine the DL, radiomics, and clinical signature to perform the final prediction. The receiver operating characteristic curve, sensitivity, specificity, and accuracy were used by two radiologists (R1 and R2) to evaluate and compare the AI system.

RESULTS

For the internal and external test set, the AI system achieved excellent performance with AUCs of 0.84 and 0.81, higher than the DL (p = .03, .82), radiomics (p < .001, .04), and clinical model (p < .001, .006). With the aid of the AI system, the specificities of radiologists were improved by 9% and 15% for R1 and 13% and 9% for R2, respectively.

CONCLUSIONS

The AI system can help predict CLNM in patients with PTC, and the radiologists' performance improved with AI assistance.

CLINICAL RELEVANCE STATEMENT

This study developed an AI system for preoperative prediction of CLNM in PTC patients based on CT images, and the radiologists' performance improved with AI assistance, which could improve the effectiveness of individual clinical decision-making.

KEY POINTS

• This multicenter retrospective study showed that the preoperative CT image-based AI system has the potential for predicting the CLNM of PTC. • The AI system was superior to the radiomics and clinical model in predicting the CLNM of PTC. • The radiologists' diagnostic performance improved when they received the AI system assistance.

Enhancing head and neck tumor management with artificial intelligence: Integration and perspectives

Head and neck tumors (HNTs) constitute a multifaceted ensemble of pathologies that primarily involve regions such as the oral cavity, pharynx, and nasal cavity. The intricate anatomical structure of these regions poses considerable challenges to efficacious treatment strategies. Despite the availability of myriad treatment modalities, the overall therapeutic efficacy for HNTs continues to remain subdued. In recent years, the deployment of artificial intelligence (AI) in healthcare practices has garnered noteworthy attention. AI modalities, inclusive of machine learning (ML), neural networks (NNs), and deep learning (DL), when amalgamated into the holistic management of HNTs, promise to augment the precision, safety, and efficacy of treatment regimens. The integration of AI within HNT management is intricately intertwined with domains such as medical imaging, bioinformatics, and medical robotics. This article intends to scrutinize the cutting-edge advancements and prospective applications of AI in the realm of HNTs, elucidating AI's indispensable role in prevention, diagnosis, treatment, prognostication, research, and inter-sectoral integration. The overarching objective is to stimulate scholarly discourse and invigorate insights among medical practitioners and researchers to propel further exploration, thereby facilitating superior therapeutic alternatives for patients.

Lymph node metastasis in cancer progression: molecular mechanisms, clinical significance and therapeutic interventions

Lymph nodes (LNs) are important hubs for metastatic cell arrest and growth, immune modulation, and secondary dissemination to distant sites through a series of mechanisms, and it has been proved that lymph node metastasis (LNM) is an essential prognostic indicator in many different types of cancer. Therefore, it is important for oncologists to understand the mechanisms of tumor cells to metastasize to LNs, as well as how LNM affects the prognosis and therapy of patients with cancer in order to provide patients with accurate disease assessment and effective treatment strategies. In recent years, with the updates in both basic and clinical studies on LNM and the application of advanced medical technologies, much progress has been made in the understanding of the mechanisms of LNM and the strategies for diagnosis and treatment of LNM. In this review, current knowledge of the anatomical and physiological characteristics of LNs, as well as the molecular mechanisms of LNM, are described. The clinical significance of LNM in different anatomical sites is summarized, including the roles of LNM playing in staging, prognostic prediction, and treatment selection for patients with various types of cancers. And the novel exploration and academic disputes of strategies for recognition, diagnosis, and therapeutic interventions of metastatic LNs are also discussed.

Predicting central lymph node metastasis in patients with papillary thyroid carcinoma based on ultrasound radiomic and morphological features analysis

OBJECTIVES

To build a combined model based on the ultrasound radiomic and morphological features, and evaluate its diagnostic performance for preoperative prediction of central lymph node metastasis (CLNM) in patients with papillary thyroid carcinoma (PTC).

METHOD

A total of 295 eligible patients, who underwent preoperative ultrasound scan and were pathologically diagnosed with unifocal PTC were included at our hospital from October 2019 to July 2022. According to ultrasound scanners, patients were divided into the training set (115 with CLNM; 97 without CLNM) and validation set (45 with CLNM; 38 without CLNM). Ultrasound radiomic, morphological, and combined models were constructed using multivariate logistic regression. The diagnostic performance was assessed by the area under the curve (AUC) of the receiver operating characteristic curve, accuracy, sensitivity, and specificity.

RESULTS

A combined model was built based on the morphology, boundary, length diameter, and radiomic score. The AUC was 0.960 (95% CI, 0.924-0.982) and 0.966 (95% CI, 0.901-0.993) in the training and validation set, respectively. Calibration curves showed good consistency between prediction and observation, and DCA demonstrated the clinical benefit of the combined model.

CONCLUSION

Based on ultrasound radiomic and morphological features, the combined model showed a good performance in predicting CLNM of patients with PTC preoperatively.

Development and validation of a dynamic nomogram based on conventional ultrasound and contrast-enhanced ultrasound for stratifying the risk of central lymph node metastasis in papillary thyroid carcinoma preoperatively

Purpose

The aim of this study was to develop and validate a dynamic nomogram by combining conventional ultrasound (US) and contrast-enhanced US (CEUS) to preoperatively evaluate the probability of central lymph node metastases (CLNMs) for patients with papillary thyroid carcinoma (PTC).

Methods

A total of 216 patients with PTC confirmed pathologically were included in this retrospective and prospective study, and they were divided into the training and validation cohorts, respectively. Each cohort was divided into the CLNM (+) and CLNM (-) groups. The least absolute shrinkage and selection operator (LASSO) regression method was applied to select the most useful predictive features for CLNM in the training cohort, and these features were incorporated into a multivariate logistic regression analysis to develop the nomogram. The nomogram's discrimination, calibration, and clinical usefulness were assessed in the training and validation cohorts.

Results

In the training and validation cohorts, the dynamic nomogram (https://clnmpredictionmodel.shinyapps.io/PTCCLNM/) had an area under the receiver operator characteristic curve (AUC) of 0.844 (95% CI, 0.755-0.905) and 0.827 (95% CI, 0.747-0.906), respectively. The Hosmer-Lemeshow test and calibration curve showed that the nomogram had good calibration (p = 0.385, p = 0.285). Decision curve analysis (DCA) showed that the nomogram has more predictive value of CLNM than US or CEUS features alone in a wide range of high-risk threshold. A Nomo-score of 0.428 as the cutoff value had a good performance to stratify high-risk and low-risk groups.

Conclusion

A dynamic nomogram combining US and CEUS features can be applied to risk stratification of CLNM in patients with PTC in clinical practice.

Artificial intelligence-driven radiomics study in cancer: the role of feature engineering and modeling

Modern medicine is reliant on various medical imaging technologies for non-invasively observing patients' anatomy. However, the interpretation of medical images can be highly subjective and dependent on the expertise of clinicians. Moreover, some potentially useful quantitative information in medical images, especially that which is not visible to the naked eye, is often ignored during clinical practice. In contrast, radiomics performs high-throughput feature extraction from medical images, which enables quantitative analysis of medical images and prediction of various clinical endpoints. Studies have reported that radiomics exhibits promising performance in diagnosis and predicting treatment responses and prognosis, demonstrating its potential to be a non-invasive auxiliary tool for personalized medicine. However, radiomics remains in a developmental phase as numerous technical challenges have yet to be solved, especially in feature engineering and statistical modeling. In this review, we introduce the current utility of radiomics by summarizing research on its application in the diagnosis, prognosis, and prediction of treatment responses in patients with cancer. We focus on machine learning approaches, for feature extraction and selection during feature engineering and for imbalanced datasets and multi-modality fusion during statistical modeling. Furthermore, we introduce the stability, reproducibility, and interpretability of features, and the generalizability and interpretability of models. Finally, we offer possible solutions to current challenges in radiomics research.

PTC-MAS: A Deep Learning-Based Preoperative Automatic Assessment of Lymph Node Metastasis in Primary Thyroid Cancer

BACKGROUND

Identifying cervical lymph node metastasis (LNM) in primary thyroid cancer preoperatively using ultrasound is challenging. Therefore, a non-invasive method is needed to assess LNM accurately.

PURPOSE

To address this need, we developed the Primary Thyroid Cancer Lymph Node Metastasis Assessment System (PTC-MAS), a transfer learning-based and B-mode ultrasound images-based automatic assessment system for assessing LNM in primary thyroid cancer.

METHODS

The system has two parts: YOLO Thyroid Nodule Recognition System (YOLOS) for obtaining regions of interest (ROIs) of nodules, and LMM assessment system for building the LNM assessment system using transfer learning and majority voting with extracted ROIs as input. We retained the relative size features of nodules to improve the system's performance.

RESULTS

We evaluated three transfer learning-based neural networks (DenseNet, ResNet, and GoogLeNet) and majority voting, which had the area under the curves (AUCs) of 0.802, 0.837, 0.823, and 0.858, respectively. Method III preserved relative size features and achieved higher AUCs than Method II, which fixed nodule size. YOLOS achieved high precision and sensitivity on a test set, indicating its potential for ROIs extraction.

CONCLUSIONS

Our proposed PTC-MAS system effectively assesses primary thyroid cancer LNM based on preserving nodule relative size features. It has potential for guiding treatment modalities and avoiding inaccurate ultrasound results due to tracheal interference.

ENST00000438158 aids ultrasound for predicting lymph node metastasis and inhibits migration and invasion of papillary thyroid carcinoma cells

Cervical lymph node metastasis (CLNM) of papillary thyroid carcinoma (PTC) is directly associated with clinical management and prognosis. In this study, we aimed to evaluate the value of conventional ultrasound (US) combined with ENST00000438158 in predicting CLNM of PTC. Fourty-nine PTC patients underwent US examination and US-guided fine needle aspiration (FNA). ENST00000438158 expression in FNA cytological specimens and PTC cell lines was detected using real-time reverse transcription polymerase chain reaction (qRT-PCR). The role of ENST00000438158 expression in the proliferation, migration, invasion, apoptosis, and cell cycle of PTC cells was investigated by Cell Counting Kit-8 (CCK8) and clone formation experiments, transwell assay, and flow cytometry, respectively. Calcification, capsule contact, and low ENST00000438158 expression were independently associated with PTC with CLNM (all p < 0.05). The combination of multiple US features was more valuable than a single US feature in predicting CLNM in PTC. Adding ENST0000438158 to US greatly improved the value of differentiation of PTC with or without CLNM. In conclusion, ENST00000438158 is a potential molecular marker for predicting CLNM in PTC. ENST00000438158 combined with US features is highly valuable for predicting CLNM in PTC.

Classification of Metastatic Lymph Nodes In Vivo Using Quantitative Ultrasound at Clinical Frequencies

Quantitative ultrasound (QUS) methods characterizing the backscattered echo signal have been of use in assessing tissue microstructure. High-frequency (30 MHz) QUS methods have been successful in detecting metastases in surgically excised lymph nodes (LNs), but limited evidence exists regarding the efficacy of QUS for evaluating LNs in vivo at clinical frequencies (2-10 MHz). In this study, a clinical scanner and 10-MHz linear probe were used to collect radiofrequency (RF) echo data of LNs in vivo from 19 cancer patients. QUS methods were applied to estimate parameters derived from the backscatter coefficient (BSC) and statistics of the envelope-detected RF signal. QUS parameters were used to train classifiers based on linear discriminant analysis (LDA) and support vector machines (SVMs). Two BSC-based parameters, scatterer diameter and acoustic concentration, were the most effective for accurately detecting metastatic LNs, with both LDA and SVMs achieving areas under the receiver operating characteristic (AUROC) curve ≥0.94. A strategy of classifying LNs based on the echo frame with the highest cancer probability improved performance to 88% specificity at 100% sensitivity (AUROC = 0.99). These results provide encouraging evidence that QUS applied at clinical frequencies may be effective at accurately identifying metastatic LNs in vivo, helping in diagnosis while reducing unnecessary biopsies and surgical treatments.

Post-Surgical Imaging Assessment in Rectal Cancer: Normal Findings and Complications

Rectal cancer (RC) is one of the deadliest malignancies worldwide. Surgery is the most common treatment for RC, performed in 63.2% of patients. The type of surgical approach chosen aims to achieve maximum residual function with the lowest risk of recurrence. The selection is made by a multidisciplinary team that assesses the characteristics of the patient and the tumor. Total mesorectal excision (TME), including both low anterior resection (LAR) and abdominoperineal resection (APR), is still the standard of care for RC. Radical surgery is burdened by a 31% rate of major complications (Clavien-Dindo grade 3-4), such as anastomotic leaks and a risk of a permanent stoma. In recent years, less-invasive techniques, such as local excision, have been tested. These additional procedures could mitigate the morbidity of rectal resection, while providing acceptable oncologic results. The "watch and wait" approach is not a globally accepted model of care but encouraging results on selected groups of patients make it a promising strategy. In this plethora of treatments, the radiologist is called upon to distinguish a physiological from a pathological postoperative finding. The aim of this narrative review is to identify the main post-surgical complications and the most effective imaging techniques.

Construction of prediction models for determining the risk of lateral lymph node metastasis in patients with thyroid papillary carcinoma based on gender stratification

BACKGROUND

Lateral lymph node metastasis (LLNM) is associated with poor prognosis in patients with papillary thyroid cancer (PTC). The purpose of this study was to determine the risk factors for LLNM and establish prediction models that could individually assessed the risk of LLNM.

METHODS

A total of 619 PTC patients were retrospectively analyzed in our study. Univariate and multivariate analysis were performed for male and female patients, respectively, to assess relationships between clinicopathological features and LLNM. By integrating independent predictors selected by binary logistic regression modeling, preoperative and postoperative nomograms were developed to estimate the risk of LLNM.

RESULTS

LLNM was detected in 80 of 216 male patients. Of 403 female patients, 114 had LLNM. The preoperative nomogram of male patients included three clinical variables: the number of foci, tuner size, and echogenic foci. In addition to the above three variables, the postoperative nomogram of male patients included extrathyroidal extension (ETE) detected in surgery, central lymph node metastasis (CLNM) and high-volume CLNM. The preoperative nomogram of female patients included the following variables: age, chronic lymphocytic thyroiditis (CLT), BRAF V600E, the number of foci, tumor size and echogenic foci. Variables such as CLT, BRAF V600E, the number of foci, tumor size, ETE detected in surgery, CLNM, high-volume CLNM and central lymph node ratio were included in the postoperative nomogram. Above Nomograms show good discrimination.

CONCLUSIONS

Considering the difference in the incidence rate of LLNM between men and women, a separate prediction system should be established for patients of different genders. These nomograms are helpful in promoting the risk stratification of PTC treatment decision-making and postoperative management.

Predictors of metastasis in cervical indeterminate lymph nodes after thyroid cancer ablation by long-term ultrasound follow-up

OBJECTIVES

To investigate the pattern of change over time and predictors for metastasis in indeterminate lymph nodes (LNs) among patients with thyroid cancer post-ablation.

METHODS

We enrolled patients who developed new cervical LNs after papillary thyroid carcinoma (PTC) ablation. Changes in the ultrasound characteristics of the indeterminate LN were recorded at months 1, 3, 6 and 12 after ablation. LN puncture pathology and long-term follow-up were standard of diagnosis. The indeterminate LNs were divided into benign and malignant groups, the differences between the two groups were compared, and the risk characteristics of malignant LNs were screened using generalized estimating equations (GEE).

RESULTS

In total, we included 138 LNs from 99 patients, of which 48 were indeterminate LNs. When following up indeterminate LNs, non-cervical lymph node metastasis (non-CLNM) lesions demonstrated a statistically significant gradual decrease in volume (p = 0.012), though there was no significant change in the volume of CLNM lesions (p = 0.779). Compared to non-CLNM lesions, the diagnostic efficiency was the highest for CLNM lesions at 1-3 months after ablation, when the LN volume changed by -0.08 to 0.12 mL (p = 0.048). The third month after ablation became an important time point for review. Moreover, GEE analysis showed that microcalcifications, cystic changes, and vascularity were strongly associated with CLNMs (p = 0.004, p = 0.002, and p = 0.010, respectively).

CONCLUSIONS

There is a pattern of volume change of indeterminate LNs after PTC ablation, which, together with microcalcifications, cystic changes, and vascularity, can be used as criteria for differentiating the benignity and malignancy of indeterminate LNs.

Cervical lymph node metastasis prediction of postoperative papillary thyroid carcinoma before 131I therapy based on clinical and ultrasound characteristics

BACKGROUND

The status of lymph nodes is crucial to determine the dose of radioiodine-131(¹³¹I) for postoperative papillary thyroid carcinoma (PTC). We aimed to develop a nomogram for predicting residual and recurrent cervical lymph node metastasis (CLNM) in postoperative PTC before ¹³¹I therapy.

METHOD

Data from 612 postoperative PTC patients who underwent ¹³¹I therapy from May 2019 to December 2020 were retrospectively analyzed. Clinical and ultrasound features were collected. Univariate and multivariate logistic regression analyses were performed to determine the risk factors of CLNM. Receiver operating characteristic (ROC) analysis was used to weigh the discrimination of prediction models. To generate nomograms, models with high area under the curves (AUC) were selected. Bootstrap internal validation, calibration curves and decision curves were used to assess the prediction model's discrimination, calibration, and clinical usefulness.

RESULTS

A total of 18.79% (115/612) of postoperative PTC patients had CLNM. Univariate logistic regression analysis found serum thyroglobulin (Tg), serum thyroglobulin antibodies (TgAb), overall ultrasound diagnosis and seven ultrasound features (aspect transverse ratio, cystic change, microcalcification, mass hyperecho, echogenicity, lymphatic hilum structure and vascularity) were significantly associated with CLNM. Multivariate analysis revealed higher Tg, higher TgAb, positive overall ultrasound and ultrasound features such as aspect transverse ratio ≥ 2, microcalcification, heterogeneous echogenicity, absence of lymphatic hilum structure and abundant vascularity were independent risk factors for CLNM. ROC analysis showed the use of Tg and TgAb combined with ultrasound (AUC = 0.903 for "Tg+TgAb+Overall ultrasound" model, AUC = 0.921 for "Tg+TgAb+Seven ultrasound features" model) was superior to any single variant. Nomograms constructed for the above two models were validated internally and the C-index were 0.899 and 0.914, respectively. Calibration curves showed satisfied discrimination and calibration of the two nomograms. DCA also proved that the two nomograms were clinically useful.

CONCLUSION

Through the two accurate and easy-to-use nomograms, the possibility of CLNM can be objectively quantified before ¹³¹I therapy. Clinicians can use the nomograms to evaluate the status of lymph nodes in postoperative PTC patients and consider a higher dose of ¹³¹I for those with high scores.

Diagnostic value of multiple diagnostic methods for lymph node metastases of papillary thyroid carcinoma: A systematic review and meta-analysis

OBJECTIVE

This study compared the diagnostic value of various diagnostic methods for lymph node metastasis (LNM) of papillary thyroid carcinoma (PTC) through network meta-analysis.

METHODS

In this experiment, databases such as CNKI, Wanfang, PubMed, and Web of Science were retrieved according to the Cochrane database, Prisma, and NMAP command manual. A meta-analysis was performed using STATA 15.0, and the value of the surface under the cumulative ranking curve (SUCRA) was used to determine the most effective diagnostic method. Quality assessments were performed using the Cochrane Collaboration's risk of bias tool, and publication bias was assessed using Deeks' funnel plot.

RESULTS

A total of 38 articles with a total of 6285 patients were included. A total of 12 diagnostic methods were used to study patients with LNM of PTC. The results showed that 12 studies were direct comparisons and 8 studies were indirect comparisons. According to the comprehensive analysis of the area of SUCRA, US+CT(86.8) had the highest sensitivity, FNAC had the highest specificity (92.4) and true positive predictive value (89.4), and FNAC+FNA-Tg had higher negative predictive value (99.4) and accuracy (86.8). In the non-invasive method, US+CT had the highest sensitivity, and the sensitivity (SEN) was [OR=0.59, 95% confidence interval (CI): (0.30, 0.89]. Among the invasive methods, the combined application of FNAC+FNA-Tg had higher diagnostic performance. The sensitivity was [OR=0.62, 95% CI: (0.26, 0.98)], the specificity (SPE) was [OR=1.12, 95% CI: (0.59, 1.64)], the positive predictive value was [OR=0.98, 95% CI: (0.59, 1.37)], the negative predictive value was [OR=0.64, 95% CI (0.38, 0.90)], and the accuracy was [OR=0.71, 95% CI: (0.31, 1.12)].

CONCLUSION

In the non-invasive method, the combined application of US+CT had good diagnostic performance, and in the invasive method, the combined application of FNAC+FNA-Tg had high diagnostic performance, and the above two methods were recommended.

RADIOMICS BASED ON TWO-DIMENSIONAL AND THREE-DIMENSIONAL ULTRASOUND FOR EXTRATHYROIDAL EXTENSION FEATURE PREDICTION IN PAPILLARY THYROID CARCINOMA

Aim

To evaluate the diagnostic performance of radiomics features of two-dimensional (2D) and three-dimensional (3D) ultrasound (US) in predicting extrathyroidal extension (ETE) status in papillary thyroid carcinoma (PTC).

Patients and Methods

2D and 3D thyroid ultrasound images of 72 PTC patients confirmed by pathology were retrospectively analyzed. The patients were assigned to ETE and non-ETE. The regions of interest (ROIs) were obtained manually. From these images, a larger number of radiomic features were automatically extracted. Lastly, the diagnostic abilities of the radiomics models and a radiologist were evaluated using receiver operating characteristic (ROC) analysis. We extracted 1693 texture features firstly.

Results

The area under the ROC curve (AUC) of the radiologist was 0.65. For 2D US, the mean AUC of the three classifiers separately were: 0.744 for logistic regression (LR), 0.694 for multilayer perceptron (MLP), 0.733 for support vector machines (SVM). For 3D US they were 0.876 for LR, 0.825 for MLP, 0.867 for SVM. The diagnostic efficiency of the radiomics was better than radiologist. The LR model had favorable discriminate performance with higher area under the curve.

Conclusion

Radiomics based on US image had the potential to preoperatively predict ETE. Radiomics based on 3D US images presented more advantages over radiomics based on 2D US images and radiologist.

Ultrasound-based radiomics technology in fetal lung texture analysis prediction of neonatal respiratory morbidity

To develop a novel method for predicting neonatal respiratory morbidity (NRM) by ultrasound-based radiomics technology. In this retrospective study, 430 high-throughput features per fetal-lung image were extracted from 295 fetal lung ultrasound images (four-chamber view) in 295 single pregnancies. Images had been obtained between 28⁺³ and 37⁺⁶ weeks of gestation within 72 h before delivery. A machine-learning model built by RUSBoost (Random under-sampling with AdaBoost) architecture was created using 20 radiomics features extracted from the images and 2 clinical features (gestational age and pregnancy complications) to predict the possibility of NRM. Of the 295 standard fetal lung ultrasound images included, 210 in the training set and 85 in the testing set. The overall performance of the neonatal respiratory morbidity prediction model achieved AUC of 0.88 (95% CI 0.83–0.92) in the training set and 0.83 (95% CI 0.79–0.97) in the testing set, sensitivity of 84.31% (95% CI 79.06–89.44%) in the training set and 77.78% (95% CI 68.30–87.43%) in the testing set, specificity of 81.13% (95% CI 78.16–84.07%) in the training set and 82.09% (95% CI 77.65–86.62%) in the testing set, and accuracy of 81.90% (95% CI 79.34–84.41%) in the training set and 81.18% (95% CI 77.33–85.12%) in the testing set. Ultrasound-based radiomics technology can be used to predict NRM. The results of this study may provide a novel method for non-invasive approaches for the prenatal prediction of NRM.

Artificial Neural Network-Based Ultrasound Radiomics Can Predict Large-Volume Lymph Node Metastasis in Clinical N0 Papillary Thyroid Carcinoma Patients

Objective

To evaluate the ability of artificial neural network- (ANN-) based ultrasound radiomics to predict large-volume lymph node metastasis (LNM) preoperatively in clinical N0 disease (cN0) papillary thyroid carcinoma (PTC) patients.

Methods

From January 2020 to April 2021, 306 cN0 PTC patients admitted to our hospital were retrospectively reviewed and divided into a training (n = 183) cohort and a validation cohort (n = 123) in a 6 : 4 ratio. Radiomic features quantitatively extracted from ultrasound images were pruned to train one ANN-based radiomic model and three conventional machine learning-based classifiers in the training cohort. Furthermore, an integrated model using ANN was constructed for better prediction. Meanwhile, the prediction of the two models was evaluated in the papillary thyroid microcarcinoma (PTMC) and conventional papillary thyroid cancer (CPTC) subgroups.

Results

The radiomic model showed better discrimination than other classifiers for large-volume LNM in the validation cohort, with an area under the receiver operating characteristic curve (AUROC) of 0.856 and an area under the precision-recall curve (AUPR) of 0.381. The performance of the integrated model was better, with an AUROC of 0.910 and an AUPR of 0.463. According to the calibration curve and decision curve analysis, the radiomic and integrated models had good calibration and clinical usefulness. Moreover, the models had good predictive performance in the PTMC and CPTC subgroups.

Conclusion

ANN-based ultrasound radiomics could be a potential tool to predict large-volume LNM preoperatively in cN0 PTC patients.

An endorectal ultrasound-based radiomics signature for preoperative prediction of lymphovascular invasion of rectal cancer

Objective

To investigate whether radiomics based on ultrasound images can predict lymphovascular invasion (LVI) of rectal cancer (RC) before surgery.

Methods

A total of 203 patients with RC were enrolled retrospectively, and they were divided into a training set (143 patients) and a validation set (60 patients). We extracted the radiomic features from the largest gray ultrasound image of the RC lesion. The intraclass correlation coefficient (ICC) was applied to test the repeatability of the radiomic features. The least absolute shrinkage and selection operator (LASSO) was used to reduce the data dimension and select significant features. Logistic regression (LR) analysis was applied to establish the radiomics model. The receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to evaluate the comprehensive performance of the model.

Results

Among the 203 patients, 33 (16.7%) were LVI positive and 170 (83.7%) were LVI negative. A total of 5350 (90.1%) radiomic features with ICC values of ≥ 0.75 were reported, which were subsequently subjected to hypothesis testing and LASSO regression dimension reduction analysis. Finally, 15 selected features were used to construct the radiomics model. The area under the curve (AUC) of the training set was 0.849, and the AUC of the validation set was 0.781. The calibration curve indicated that the radiomics model had good calibration, and DCA demonstrated that the model had clinical benefits.

Conclusion

The proposed endorectal ultrasound-based radiomics model has the potential to predict LVI preoperatively in RC.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00813-6.

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.

Prophylactic central lymph node dissection performed selectively with cN0 papillary thyroid carcinoma according to a risk-scoring model

BACKGROUND

This study aimed to explore the risk factors of central lymph node metastasis (CLNM) in patients with clinical central lymph node-negative papillary thyroid carcinoma (PTC), and emphasize the guidance of the risk scoring model for prophylactic central lymph node dissection (pCLND) in patients with clinical lymph node-negative (cN0) PTC.

METHODS

A total of 582 patients with cN0 PTC who underwent unilateral/bilateral thyroidectomy and prophylactic central lymph node dissection (pCLND) in the Affiliated Hospital of Nantong University from January 2020 to February 2021 were retrospectively analyzed. Univariate and multivariate analyses were performed to determine the risk factors of cN0 PTC. According to the independent risk factors of patients with cN0 PTC, a risk-scoring model was established. Then, the rationality of this risk scoring model was verified by additional clinical data of 112 patients with cN0 PTC in the Affiliated Hospital of Nantong University from March 2021 to April 2021.

RESULTS

Among 582 cases of cN0 PTC, 53.6% of the patients with cN0 had CLNM. The independent risk factors for CLNM in patients with cN0 PTC included male gender, <45 years of age, tumor with a maximum diameter of ≥1.0 cm, tumor location: middle/lower poles of the thyroid gland, multifocality, and extrathyroidal extension (ETE), and some ultrasound features, such as intra-nodular vascularity, microcalcification, irregular shape, and infiltrative margin. According to independent risk factors, a 24-point risk scoring model was established to predict CLNM in patients with cN0 PTC.

CONCLUSIONS

Currently, prophylactic central neck lymph node dissection is a controversial operation, which should be selectively performed only for high-risk patients with cN0 PTC. For cN0 PTC patients with scores ≥14 and high-risk patients, even if no CLNM is found before surgery, routine prophylactic CLND is recommended. In addition, for cN0 PTC patients with a score of fewer than 14 points, it is recommended to perform fine-needle aspiration (FNA) before surgery, carefully assess the condition of the central lymph nodes, and then select the best surgical plan based on the results of the assessment.

Deep multimodal learning for lymph node metastasis prediction of primary thyroid cancer

Objective. The incidence of primary thyroid cancer has risen steadily over the past decades because of overdiagnosis and overtreatment through the improvement in imaging techniques for screening, especially in ultrasound examination. Metastatic status of lymph nodes is important for staging the type of primary thyroid cancer. Deep learning algorithms based on ultrasound images were thus developed to assist radiologists on the diagnosis of lymph node metastasis. The objective of this study is to integrate more clinical context (e.g., health records and various image modalities) into, and explore more interpretable patterns discovered by, deep learning algorithms for the prediction of lymph node metastasis in primary thyroid cancer patients.Approach. A deep multimodal learning network was developed in this study with a novel index proposed to compare the contribution of different modalities when making the predictions.Main results. The proposed multimodal network achieved an average F1 score of 0.888 and an average area under the receiver operating characteristic curve (AUC) value of 0.973 in two independent validation sets, and the performance was significantly better than that of three single-modality deep learning networks. Moreover, among three modalities used in this study, the deep multimodal learning network relied generally more on image modalities than the data modality of clinic records when making the predictions.Significance. Our work is beneficial to prospective clinic trials of radiologists on the diagnosis of lymph node metastasis in primary thyroid cancer, and will better help them understand how the predictions are made in deep multimodal learning algorithms.

Application of Machine Learning Methods to Improve the Performance of Ultrasound in Head and Neck Oncology: A Literature Review

Simple Summary

Ultrasound (US) is a non-invasive imaging method that is routinely utilized in head and neck cancer patients to assess the anatomic extent of tumors, nodal and non-nodal neck masses and for imaging the salivary glands. In this review, we summarize the present evidence on whether the application of machine learning (ML) methods can potentially improve the performance of US in head and neck cancer patients. We found that published clinical literature on ML methods applied to US datasets was limited but showed evidence of improved diagnostic and prognostic performance. However, a majority of these studies were based on retrospective evaluation and conducted at a single center with a limited number of datasets. The conduct of multi-center studies could help better validate the performance of ML-based US radiomics and facilitate the integration of these approaches into routine clinical practice.

Abstract

Radiomics is a rapidly growing area of research within radiology that involves the extraction and modeling of high-dimensional quantitative imaging features using machine learning/artificial intelligence (ML/AI) methods. In this review, we describe the published clinical evidence on the application of ML methods to improve the performance of ultrasound (US) in head and neck oncology. A systematic search of electronic databases (MEDLINE, PubMed, clinicaltrials.gov) was conducted according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Of 15,080 initial articles identified, 34 studies were selected for in-depth analysis. Twenty-five out of 34 studies (74%) focused on the diagnostic application of US radiomics while 6 (18%) studies focused on response assessment and 3 (8%) studies utilized US radiomics for modeling normal tissue toxicity. Support vector machine (SVM) was the most commonly employed ML method (47%) followed by multivariate logistic regression (24%) and k-nearest neighbor analysis (21%). Only 11/34 (~32%) of the studies included an independent validation set. A majority of studies were retrospective in nature (76%) and based on single-center evaluation (85%) with variable numbers of patients (12–1609) and imaging datasets (32–1624). Despite these limitations, the application of ML methods resulted in improved diagnostic and prognostic performance of US highlighting the potential clinical utility of this approach.

Serum Linkage-Specific Sialylation Changes Are Potential Biomarkers for Monitoring and Predicting the Recurrence of Papillary Thyroid Cancer Following Thyroidectomy

BACKGROUND

Although papillary thyroid cancer (PTC) could remain indolent, the recurrence rates after thyroidectomy are approximately 20%. There are currently no accurate serum biomarkers that can monitor and predict recurrence of PTC after thyroidectomy. This study aimed to explore novel serum biomarkers that are relevant to the monitoring and prediction of recurrence in PTC using N-glycomics.

METHODS

A high-throughput quantitative strategy based on matrix-assisted laser desorption/ionization time-of-flight mass spectrometry was used to obtain serum protein N-glycomes of well-differentiated PTC, postoperative surveillance (PS), postoperative recurrence (PR), and matched healthy controls (HC) including linkage-specific sialylation information.

RESULTS

Serum N-glycan traits were found to differ among PTC, PS, PR, and HC. The differentially expressed N-glycan traits consisting of sixteen directly detected glycan traits and seven derived glycan traits indicated the response to surgical resection therapy and the potential for monitoring the PTC. Two glycan traits representing the levels of linkage-specific sialylation (H4N3F1L1 and H4N6F1E1) which were down-regulated in PS and up-regulated in PR showed high potential as biomarkers for predicting the recurrence after thyroidectomy.

CONCLUSIONS

To the best of our knowledge, this study provides comprehensive evaluations of the serum N-glycomic changes in patients with PS or PR for the first time. Several candidate serum N-glycan biomarkers including the linkage-specific sialylation have been determined, some of which have potential in the prediction of recurrence in PTC, and others of which can help to explore and monitor the response to initial surgical resection therapy. The findings enhanced the comprehension of PTC.

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.