Lymph node metastasis prediction of papillary thyroid carcinoma based on transfer learning radiomics

Preoperative prediction of high-grade osteosarcoma response to neoadjuvant therapy based on a plain CT radiomics model: A dual-center study

Objective

To develop a model combining clinical and radiomics features from CT scans for a preoperative noninvasive evaluation of Huvos grading of neoadjuvant chemotherapy in patients with HOS.

Methods

183 patients from center A and 42 from center B were categorized into training and validation sets. Features derived from radiomics were obtained from unenhanced CT scans.Following dimensionality reduction, the most optimal features were selected and utilized in creating a radiomics model through logistic regression analysis. Integrating clinical features, a composite clinical radiomics model was developed, and a nomogram was constructed. Predictive performance of the model was evaluated using ROC curves and calibration curves. Additionally, decision curve analysis was conducted to assess practical utility of nomogram in clinical settings.

Results

LASSO LR analysis was performed, and finally, three selected image omics features were obtained.Radiomics model yielded AUC values with a good diagnostic effect for both patient sets (AUCs: 0.69 and 0.68, respectively). Clinical models (including sex, age, pre-chemotherapy ALP and LDH levels, new lung metastases within 1 year after surgery, and incidence) performed well in terms of Huvos grade prediction, with an AUC of 0.74 for training set. The AUC for independent validation set stood at 0.70. Notably, the amalgamation of radiomics and clinical features exhibited commendable predictive prowess in training set, registering an AUC of 0.78. This robust performance was subsequently validated in the independent validation set, where the AUC remained high at 0.75. Calibration curves of nomogram showed that the predictions were in good agreement with actual observations.

Conclusion

Combined model can be used for Huvos grading in patients with HOS after preoperative chemotherapy, which is helpful for adjuvant treatment decisions.

Proteomic and Phosphoproteomic analysis of thyroid papillary carcinoma: Identification of potential biomarkers for metastasis

Thyroid cancer has emerged as the most rapidly proliferating solid neoplasm. In this study, we included a cohort of patients who underwent sonographic assessment and surgical intervention at the Sir Run Run Shaw Hospital, associated with the School of Medicine at Zhejiang University, spanning from January 2019 to June 2020. Stratification of cases was based on a combination of preoperative ultrasonographic evaluations and postoperative histopathological diagnoses, resulting in three distinct groups: high-risk papillary thyroid carcinoma (PTC) labeled as C1, low-risk PTC designated as C2, and a control group (N) composed of benign thyroid tissue adjacent to the carcinoma. Proteomic and phosphoproteomic analyses were conducted on PTC specimens. The comparative assessment revealed that proteins up-regulated in the C1/N and C2/N groups were predominantly involved in functions such as amino acid binding, binding of phosphorylated compounds, and serine protease activity. Notably, proteins like NADH dehydrogenase, ATP synthase, oxidoreductases, and iron ion channels were significantly elevated in the C1 versus C2 comparative group. Through meticulous analysis of differential expression multiples, statistical significance, and involvement in metabolic pathways, this study identified eight potential biomarkers pertinent to PTC metastasis diagnostics, encompassing phosphorylated myosin 10, phosphorylated proline-directed protein kinase, leucine tRNA synthetase, 2-oxo-isovalerate dehydrogenase, succinic semialdehyde dehydrogenase, ADP/ATPtranslocase, pyruvate carboxylase, and fibrinogen. Therapeutic assays employing metformin, an AMP-activated protein kinase (AMPK) activator, alongside the phosphorylation-specific inhibitor ML-7 targeting Myosin10, demonstrated attenuated cellular proliferation, migration, and invasion capabilities in thyroid cancer cells, accompanied by a reduction in amino acid pools. Cellular colocalization and interaction studies elucidated that AMPK activation imposes an inhibitory influence on Myosin10 levels. The findings of this research corroborate the utility of proteomic and phosphoproteomic platforms in the identification of metastatic markers for PTC and suggest that modulation of AMPK activity, coupled with the inhibition of Myosin10 phosphorylation, may forge novel therapeutic avenues in the management of thyroid carcinoma. SIGNIFICANCE: The significance of our research lies in its potential to transform the current understanding and management of thyroid papillary carcinoma (PTC), particularly in its metastatic form. By integrating both proteomic and phosphoproteomic analyses, our study not only sheds light on the molecular alterations associated with PTC but also identifies eight novel biomarkers that could serve as indicators of metastatic potential.

Development and validation of a clinical predictive model for high-volume lymph node metastasis of papillary thyroid carcinoma

The central lymph node metastasis (CLNM) status in the cervical region serves as a pivotal determinant for the extent of surgical intervention and prognosis in papillary thyroid carcinoma (PTC). This paper seeks to devise and validate a predictive model based on clinical parameters for the early anticipation of high-volume CLNM (hv-CLNM, > 5 nodes) in high-risk patients. A retrospective analysis of the pathological and clinical data of patients with PTC who underwent surgical treatment at Medical Centers A and B was conducted. The data from Center A was randomly divided into training and validation sets in an 8:2 ratio, with those from Center B serving as the test set. Multifactor logistic regression was harnessed in the training set to select variables and construct a predictive model. The generalization ability of the model was assessed in the validation and test sets. The model was evaluated through the receiver operating characteristic area under the curve (AUC) to predict the efficiency of hv-CLNM. The goodness of fit of the model was examined via the Brier verification technique. The incidence of hv-CLNM in 5897 PTC patients attained 4.8%. The occurrence rates in males and females were 9.4% (128/1365) and 3.4% (156/4532), respectively. Multifactor logistic regression unraveled male gender (OR = 2.17, p < .001), multifocality (OR = 4.06, p < .001), and lesion size (OR = 1.08 per increase of 1 mm, p < .001) as risk factors, while age emerged as a protective factor (OR = 0.95 per an increase of 1 year, p < .001). The model constructed with four predictive variables within the training set exhibited an AUC of 0.847 ([95%CI] 0.815-0.878). In the validation and test sets, the AUCs were 0.831 (0.783-0.879) and 0.845 (0.789-0.901), respectively, with Brier scores of 0.037, 0.041, and 0.056. Subgroup analysis unveiled AUCs for the prediction model in PTC lesion size groups (≤ 10 mm and > 10 mm) as 0.803 (0.757-0.85) and 0.747 (0.709-0.785), age groups (≤ 31 years and > 31 years) as 0.778 (0.720-0.881) and 0.837 (0.806-0.867), multifocal and solitary cases as 0.803 (0.767-0.838) and 0.809 (0.769-0.849), and Hashimoto's thyroiditis (HT) and non-HT cases as 0.845 (0.793-0.897) and 0.845 (0.819-0.871). Male gender, multifocality, and larger lesion size are risk factors for hv-CLNM in PTC patients, whereas age serves as a protective factor. The clinical predictive model developed in this research facilitates the early identification of high-risk patients for hv-CLNM, thereby assisting physicians in more efficacious risk stratification management for PTC patients.

Magnetic resonance imaging-based radiomics and deep learning models for predicting lymph node metastasis of squamous cell carcinoma of the tongue

OBJECTIVE

This study aimed to establish a combined method of radiomics and deep learning (DL) in magnetic resonance imaging (MRI) to predict lymph node metastasis (LNM) preoperatively in patients with squamous cell carcinoma of the tongue.

STUDY DESIGN

In total, MR images of 196 patients with lingual squamous cell carcinoma were divided into training (n = 156) and test (n = 40) cohorts. Radiomics and DL features were extracted from MR images and selected to construct machine learning models. A DL radiomics nomogram was established via multivariate logistic regression by incorporating the radiomics signature, the DL signature, and MRI-reported LN status.

RESULTS

Nine radiomics and 3 DL features were selected. In the radiomics test cohort, the multilayer perceptron model performed best with an area under the receiver operating characteristic curve (AUC) of 0.747, but in the DL cohort, the best model (logistic regression) performed less well (AUC = 0.655). The DL radiomics nomogram showed good calibration and performance with an AUC of 0.934 (outstanding discrimination ability) in the training cohort and 0.757 (acceptable discrimination ability) in the test cohort. The decision curve analysis demonstrated that the nomogram could offer more net benefit than a single radiomics or DL signature.

CONCLUSION

The DL radiomics nomogram exhibited promising performance in predicting LNM, which facilitates personalized treatment of tongue cancer.

A combination of risk stratification systems for thyroid nodules and cervical lymph nodes may improve the diagnosis and management of thyroid nodules

Introduction

To assess the performance of the European Thyroid Association Thyroid Imaging and Reporting Data System (EU-TIRADS) and the Korean Thyroid Imaging Reporting and Data System (K-TIRADS), which combine risk stratification systems for thyroid nodules (TN-RSS) and cervical lymph nodes (LN-RSS) in diagnosing malignant and metastatic thyroid cancer in a single referral center.

Methods

We retrospectively analyzed 2,055 consecutive patients who underwent thyroidectomy or fine-needle aspiration (FNA) from January 2021 to December 2022. TNs and LNs were categorized according to the ultrasonography (US) features of EU-TIRADS and K-TIRADS, respectively. The diagnostic performance and postponed malignancy rate (PMR) were compared with those of EU-TIRADS and K-TIRADS. PMR was defined as the number of patients with malignant nodules not recommended for biopsy among patients with cervical LN metastasis.

Results

According to the EU-TIRADS and K-TIRADS, for TN-RSS alone, there were no significant differences in sensitivity, specificity, accuracy, unnecessary FNA rate (UFR), missed malignancy rate (MMR), and PMR between the two TIRADSs (29.0% vs. 28.8%, 50.5% vs. 51.1%, 32.3% vs. 32.2%, 23.6% vs. 23.5%, 88.6% vs. 88.5%, and 54.2% vs. 54.5%, P > 0.05 for all). Combining the LN-RSS increased the diagnostic accuracy (42.7% vs. 32.3% in EU-TIRADS; 38.8% vs. 32.2% in K-TIRADS) and decreased the PMR (54.2% vs. 33.9% in EU-TIRADS; 54.5% vs. 39.3% in K-TIRADS). EU-TIRADS had higher sensitivity and accuracy and lower PMR than K-TIRADS (41.3% vs. 36.7%, 42.7% vs. 38.8%,33.9% vs. 39.3%, P < 0.05 for all).

Conclusions

A combination of TN-RSS and LN-RSS for the management of thyroid nodules may be associated with a reduction in PMR, with enhanced sensitivity and accuracy for thyroid cancers in EU-TIRADS and K-TIRADS. These results may offer a new direction for the detection of aggressive thyroid cancers.

Computer Vision-Radiomics & Pathognomics

The role of computer vision in extracting radiographic (radiomics) and histopathologic (pathognomics) features is an extension of molecular biomarkers that have been foundational to our understanding across the spectrum of head and neck disorders. Especially within head and neck cancers, machine learning and deep learning applications have yielded advances in the characterization of tumor features, nodal features, and various outcomes. This review aims to overview the landscape of radiomic and pathognomic applications, informing future work to address gaps. Novel methodologies will be needed to potentially engineer ways of integrating multidimensional data inputs to examine disease features to guide prognosis comprehensively and ultimately clinical management.

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.

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.

Recent Insights into the Roles of PEST-Containing Nuclear Protein

PEST-containing nuclear protein (PCNP), a short-lived small nuclear protein with 178 amino acids, is a nuclear protein containing two PEST sequences. PCNP is highly expressed in several malignant tumors such as cervical cancer, rectal cancer, and lung cancer. It is also associated with cell cycle regulation and the phosphoinositide 3-kinase/protein kinase B/mammalian target of rapamycin (PI3K/AKT/mTOR) and Wnt signaling pathways during tumor growth. The present article discuss how PCNP regulates the PI3K/AKT/mTOR and Wnt signaling pathways and related proteins, and the ubiquitination of PCNP regulates tumor cell cycle as well as the progress of the application of PCNP in the pathophysiology and treatment of colon cancer, human ovarian cancer, thyroid cancer, lung adenocarcinoma and oral squamous cell carcinoma. The main relevant articles were retrieved from PubMed, with keywords such as PEST-containing nuclear protein (PCNP), cancer (tumor), and signaling pathways as inclusion/exclusion criteria. Relevant references has been included and cited in the manuscript.

Machine learning to predict the occurrence of thyroid nodules: towards a quantitative approach for judicious utilization of thyroid ultrasonography

Introduction

Ultrasound is instrumental in the early detection of thyroid nodules, which is crucial for appropriate management and favorable outcomes. However, there is a lack of clinical guidelines for the judicious use of thyroid ultrasonography in routine screening. Machine learning (ML) has been increasingly used on big data to predict clinical outcomes. This study aims to leverage the ML approach in assessing the risk of thyroid nodules based on common clinical features.

Methods

Data were sourced from a Chinese cohort undergoing routine physical examinations including thyroid ultrasonography between 2013 and 2023. Models were established to predict the 3-year risk of thyroid nodules based on patients' baseline characteristics and laboratory tests. Four ML algorithms, including logistic regression, random forest, extreme gradient boosting, and light gradient boosting machine, were trained and tested using fivefold cross-validation. The importance of each feature was measured by the permutation score. A nomogram was established to facilitate risk assessment in the clinical settings.

Results

The final dataset comprised 4,386 eligible subjects. Thyroid nodules were detected in 54.8% (n=2,404) individuals within the 3-year observation period. All ML models significantly outperformed the baseline regression model, successfully predicting the occurrence of thyroid nodules in approximately two-thirds of individuals. Age, high-density lipoprotein, fasting blood glucose and creatinine levels exhibited the highest impact on the outcome in these models. The nomogram showed consistency and validity, providing greater net benefits for clinical decision-making than other strategies.

Conclusion

This study demonstrates the viability of an ML-based approach in predicting the occurrence of thyroid nodules. The findings highlight the potential of ML models in identifying high-risk individuals for personalized screening, thereby guiding the judicious use of ultrasound in this context.

BRAFV600E mutation does not predict lymph node metastases and recurrence in Chinese papillary thyroid microcarcinoma patients

OBJECT

Previous studies suggest BRAFV600E mutation is a marker for poor prognosis in papillary thyroid cancer, however, its ability to further risk stratify papillary thyroid microcarcinoma (PTMC) remains controversial. We aimed to explore the association between BRAFV600E mutation and the clinicopathological features and recurrence in Chinese PTMC patients.

METHODS

We retrospectively reviewed 2094 PTMC patients who underwent surgery and had a valid BRAFV600E mutation test result. Among them, 1292 patients had complete follow-up data. The mutation incidence was determined. Moreover, the clinicopathological characteristics, disease-free survival (DFS), and response to therapy distribution were compared between the mutation and non-mutation groups.

RESULTS

BRAFV600E mutation was observed in 90.6 % of all patients and 89.2 % of patients with complete follow-up data. No significant difference was observed in lymph node metastases (LNM) number categories between the mutation and non-mutation groups among all patients (P = 0.329) and 1292 patients (P = 0.408). Neither the 3-year DFS (97.9 % vs. 98.0 %, P = 0.832) nor the response to therapy distribution (P > 0.05) indicated a significant difference between the mutation and non-mutation groups. The 3-year DFS differs among patients having different LNM number categories (99.8 % vs. 98.5 % vs. 77.3 %, P < 0.001). Multivariate analysis revealed that high-volume (over 5) LNM (Total thyroidectomy (TT): OR = 4.000, 95 % CI 2.390-6.694, P < 0.001; Unilateral thyroidectomy (UT): OR = 4.183, 95 % CI 1.565-11.190, P = 0.004), rather than BRAFV600E mutation (P > 0.05), was an independent risk factor of response to therapy.

CONCLUSIONS

Our results suggested that BRAFV600E mutation could not accurately predict LNM or the recurrence of Chinese PTMC patients. Moreover, high-volume LNM is significantly associated with PTMC prognosis.

Clinical prediction models for cervical lymph node metastasis of papillary thyroid carcinoma

PURPOSE

Accurate preoperative diagnosis of lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) remains an unsolved problem. This study aimed to construct a nomogram and scoring system for predicting LNM based on the clinical characteristics of patients with PTC.

METHODS

1400 patients with PTC who underwent thyroidectomy and lymph node dissection at the First Affiliated Hospital of Sun Yat-sen University were retrospectively enrolled and randomly divided into training and internal testing sets. Furthermore, 692 patients with PTC from three other medical centers were collected as external testing sets. Least absolute shrinkage and selection operator (LASSO) was used to screen the predictors, and a nomogram was constructed. In addition, a scoring system was constructed using 10-fold cross-validation. The performances of the two models were verified among datasets and compared with preoperative ultrasound (US).

RESULTS

Six independent predictors were included in the multivariate logistic model: age, sex, US diagnosis of LNM, tumor diameter, location, and thyroid peroxidase antibody level. The areas under the receiver operating characteristic curve (AUROC) (95% confidence interval) of this nomogram in the training, internal testing, and three external testing sets were 0.816 (0.791-0.840), 0.782 (0.727-0.837), 0.759 (0.699-0.819), 0.749 (0.667-0.831), and 0.777 (0.726-0.828), respectively. The AUROC of the scoring system were 0.810 (0.785-0.835), 0.772 (0.718-0.826), 0.736 (0.675-0.798), 0.717 (0.635-0.799) and 0.756 (0.704-0.808), respectively. The prediction performances were both significantly superior to those of preoperative US (P < 0.001).

CONCLUSION

The nomogram and scoring system performed well in different datasets and significantly improved the preoperative prediction of LNM than US alone.

Study of radiochemotherapy decision-making for young high-risk low-grade glioma patients using a macroscopic and microscopic combined radiomics model

OBJECTIVES

As a few types of glioma, young high-risk low-grade gliomas (HRLGGs) have higher requirements for postoperative quality of life. Although adjuvant chemotherapy with delayed radiotherapy is the first treatment strategy for HRLGGs, not all HRLGGs benefit from it. Accurate assessment of chemosensitivity in HRLGGs is vital for making treatment choices. This study developed a multimodal fusion radiomics (MFR) model to support radiochemotherapy decision-making for HRLGGs.

METHODS

A MFR model combining macroscopic MRI and microscopic pathological images was proposed. Multiscale features including macroscopic tumor structure and microscopic histological layer and nuclear information were grabbed by unique paradigm, respectively. Then, these features were adaptively incorporated into the MFR model through attention mechanism to predict the chemosensitivity of temozolomide (TMZ) by means of objective response rate and progression free survival (PFS).

RESULTS

Macroscopic tumor texture complexity and microscopic nuclear size showed significant statistical differences (p < 0.001) between sensitivity and insensitivity groups. The MFR model achieved stable prediction results, with an area under the curve of 0.950 (95% CI: 0.942-0.958), sensitivity of 0.833 (95% CI: 0.780-0.848), specificity of 0.929 (95% CI: 0.914-0.936), positive predictive value of 0.833 (95% CI: 0.811-0.860), and negative predictive value of 0.929 (95% CI: 0.914-0.934). The predictive efficacy of MFR was significantly higher than that of the reported molecular markers (p < 0.001). MFR was also demonstrated to be a predictor of PFS.

CONCLUSIONS

A MFR model including radiomics and pathological features predicts accurately the response postoperative TMZ treatment.

CLINICAL RELEVANCE STATEMENT

Our MFR model could identify young high-risk low-grade glioma patients who can have the most benefit from postoperative upfront temozolomide (TMZ) treatment.

KEY POINTS

• Multimodal radiomics is proposed to support the radiochemotherapy of glioma. • Some macro and micro image markers related to tumor chemotherapy sensitivity are revealed. • The proposed model surpasses reported molecular markers, with a promising area under the curve (AUC) of 0.95.

Accurate preoperative prediction of nodal metastasis in papillary thyroid microcarcinoma: Towards optimal management of patients

OBJECTIVE

To enhance the accuracy in predicting lymph node metastasis (LNM) preoperatively in patients with papillary thyroid microcarcinoma (PTMC), refining the "low-risk" classification for tailored treatment strategies.

METHODS

This study involves the development and validation of a predictive model using a cohort of 1004 patients with PTMC undergoing thyroidectomy along with central neck dissection. The data was divided into a training cohort (n = 702) and a validation cohort (n = 302). Multivariate logistic regression identified independent LNM predictors in PTMC, leading to the construction of a predictive nomogram model. The model's performance was assessed through ROC analysis, calibration curve analysis, and decision curve analysis.

RESULTS

Identified LNM predictors in PTMC included age, tumor maximum diameter, nodule-capsule distance, capsular contact length, bilateral suspicious lesions, absence of the lymphatic hilum, microcalcification, and sex. Especially, tumors larger than 7 mm, nodules closer to the capsule (less than 3 mm), and longer capsular contact lengths (more than 1 mm) showed higher LNM rates. The model exhibited AUCs of 0.733 and 0.771 in the training and validation cohorts respectively, alongside superior calibration and clinical utility.

CONCLUSION

This study proposes and substantiates a preoperative predictive model for LNM in patients with PTMC, honing the precision of "low-risk" categorization. This model furnishes clinicians with an invaluable tool for individualized treatment approach, ensuring better management of patients who might be proposed observation or ablative options in the absence of such predictive information.

Seizing the fate of lymph nodes in immunotherapy: To preserve or not?

Lymph node dissection has been a long-standing diagnostic and therapeutic strategy for metastatic cancers. However, questions over myriad related complications and survival outcomes are continuously debated. Immunotherapy, particularly neoadjuvant immunotherapy, has revolutionized the conventional paradigm of cancer treatment, yet has benefited only a fraction of patients. Emerging evidence has unveiled the role of lymph nodes as pivotal responders to immunotherapy, whose absence may contribute to drastic impairment in treatment efficacy, again posing challenges over excessive lymph node dissection. Hence, centering around this theme, we concentrate on the mechanisms of immune activation in lymph nodes and provide an overview of minimally invasive lymph node metastasis diagnosis, current best practices for activating lymph nodes, and the prognostic outcomes of omitting lymph node dissection. In particular, we discuss the potential for future comprehensive cancer treatment with effective activation of immunotherapy driven by lymph node preservation and highlight the challenges ahead to achieve this goal.

Lateral lymph node metastasis in papillary thyroid cancer: Is there a difference between PTC and PTMC?

Papillary thyroid carcinoma (PTC) and papillary thyroid microcarcinoma (PTMC) are generally characterized as less invasive forms of thyroid cancer with favorable prognosis. However, once lateral cervical lymph node metastasis takes place, the prognosis may be significantly impacted. The purpose of this study was to evaluate whether there is a difference in the pattern of lateral lymph node metastasis between PTC and PTMC. A retrospective analysis was performed for PTC and PTMC patients that underwent central area dissection and unilateral lateral neck lymph node dissection (II-V area) between January 2020 and December 2021. Compared with PTMC group, the PTC group exhibited higher incidence of capsule invasion, extrathyroid invasion and lymphatic vessel invasion. Both the number and rate of central lymph nodes metastasis were elevated in the PTC group. While the number of lateral cervical lymph node metastasis was higher, the metastasis rate did not demonstrate significant difference. No significant differences were identified in the lymph node metastasis patterns between the 2 groups. The determination of the extent of lateral neck lymph node dissection solely based on the tumor size may be unreliable, as PTC and PTMC showed no difference in the number and pattern of lateral neck metastasis. Additional clinical data are warranted to reinforce this conclusion. For patients categorized as unilateral, bilateral, or contralateral cervical lymph node metastasis (including level I, II, III, IV, or V) or retropharyngeal lymph node metastasis who require unilateral lateral neck dissection, the size of the primary tumor may not need to be a central consideration when assessing and deciding the extent of lateral neck dissection.

A CT-based integrated model for preoperative prediction of occult lymph node metastasis in early tongue cancer

Background

Occult lymph node metastasis (OLNM) is an essential prognostic factor for early-stage tongue cancer (cT1-2N0M0) and a determinant of treatment decisions. Therefore, accurate prediction of OLNM can significantly impact the clinical management and outcomes of patients with tongue cancer. The aim of this study was to develop and validate a multiomics-based model to predict OLNM in patients with early-stage tongue cancer.

Methods

The data of 125 patients diagnosed with early-stage tongue cancer (cT1-2N0M0) who underwent primary surgical treatment and elective neck dissection were retrospectively analyzed. A total of 100 patients were randomly assigned to the training set and 25 to the test set. The preoperative contrast-enhanced computed tomography (CT) and clinical data on these patients were collected. Radiomics features were extracted from the primary tumor as the region of interest (ROI) on CT images, and correlation analysis and the least absolute shrinkage and selection operator (LASSO) method were used to identify the most relevant features. A support vector machine (SVM) classifier was constructed and compared with other machine learning algorithms. With the same method, a clinical model was built and the peri-tumoral and intra-tumoral images were selected as the input for the deep learning model. The stacking ensemble technique was used to combine the multiple models. The predictive performance of the integrated model was evaluated for accuracy, sensitivity, specificity, and the area under the receiver operating characteristic curve (AUC-ROC), and compared with expert assessment. Internal validation was performed using a stratified five-fold cross-validation approach.

Results

Of the 125 patients, 41 (32.8%) showed OLNM on postoperative pathological examination. The integrated model achieved higher predictive performance compared with the individual models, with an accuracy of 84%, a sensitivity of 100%, a specificity of 76.5%, and an AUC-ROC of 0.949 (95% CI [0.870-1.000]). In addition, the performance of the integrated model surpassed that of younger doctors and was comparable to the evaluation of experienced doctors.

Conclusions

The multiomics-based model can accurately predict OLNM in patients with early-stage tongue cancer, and may serve as a valuable decision-making tool to determine the appropriate treatment and avoid unnecessary neck surgery in patients without OLNM.

Score based on contrast-enhanced ultrasound predict central lymph node metastasis in papillary thyroid cancer

Objectives

To investigate the association between contrast-enhanced ultrasound (CEUS) features of PTC and central lymph node metastasis (CLNM) and to develop a predictive model for the preoperative identification of CLNM.

Methods

This retrospective study evaluated 750 consecutive patients with PTC from August 2020 to April 2023. Conventional ultrasound and qualitative CEUS features were analyzed for the PTC with or without CLNM using univariate and multivariate logistic regression analysis. A nomogram integrating the predictors was constructed to identify CLNM in PTC. The predictive nomogram was validated using a validation cohort.

Results

A total of 684 patients were enrolled. The 495 patients in training cohort were divided into two groups according to whether they had CLNM (pCLNM, n= 191) or not (nCLNM, n= 304). There were significant differences in terms of tumor size, shape, echogenic foci, enhancement direction, peak intensity, and score based on CEUS TI-RADS between the two groups. Independent predictive US features included irregular shape, larger tumor size (≥ 1.0cm), and score. Nomogram integrating these predictive features showed good discrimination and calibration in both training and validation cohort with an AUC of 0.72 (95% CI: 0.68, 0.77) and 0.79 (95% CI: 0.72, 0.85), respectively. In the subgroup with larger tumor size, age ≤ 35 years, irregular shape, and score > 6 were independent risk factors for CLNM.

Conclusion

The score based on preoperative CEUS features of PTC may help to identify CLNM. The nomogram developed in this study provides a convenient and effective tool for clinicians to determine an optimal treatment regimen for patients with PTC.

Integrated transcriptome sequencing and weighted gene co-expression network analysis reveals key genes of papillary thyroid carcinomas

Objective

Papillary thyroid carcinoma (PTC) accounts for the majority of thyroid cancers and has a high recurrence rate. We aimed to screen key genes involved in PTC to provide novel insights into the mechanisms of PTC.

Methods

Seven microarray datasets of PTC were downloaded from gene expression omnibus database. Differentially expressed genes (DEGs) between PTC and normal samples were screened in the merged dataset. Then, protein-protein interaction (PPIs) functional modules analysis and weighted gene co-expression network analysis (WGCNA) were utilized to identify PTC-associated key genes. The identified key genes were then characterized from various aspects, including gene set enrichment analysis (GSEA) and the associations with immune infiltration, methylation levels and prognosis.

Results

A large numbers of DEGs were identified, and these DEGs are involved in several cancer pathways. Nine key genes (including down-regulated genes GNA14, AVPR1A, and WFS1, and up-regulated genes LAMB3, PLAU, MET, MFGE8, PRSS23, and SERPINA1) were identified. Patients in the AVPR1A and GNA14 high expression groups had better disease-free survival (DFS) than those in the low expression group. Key genes were mainly involved in P53 pathway, estrogen response, apoptosis, glycolysis, NOTCH signaling, epithelial mesenchymal transition, WNT_beta catenin signaling, and inflammatory response. The expression of key genes was associated with immune cell infiltration and corresponding methylation levels. The verification results of key gene proteins and mRNA expression levels using external validation datasets were consistent with our expectations, implying the involvements of key genes in PTC.

Conclusion

The key genes may serve as potential therapeutic targets for PTC. This study provides novel insights into the mechanisms underlying PTC development.

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.

Establishment and validation of a multivariate logistic model for risk factors of thyroid nodules using lasso regression screening

Objective

This study aims to analyze the association between the occurrence of thyroid nodules and various factors and to establish a risk factor model for thyroid nodules.

Methods

The study population was divided into two groups: a group with thyroid nodules and a group without thyroid nodules. Regression with the least absolute shrinkage and selection operator (Lasso) was applied to the complete dataset for variable selection. Binary logistic regression was used to analyze the relationship between various influencing factors and the prevalence of thyroid nodules.

Results

Based on the screening results of Lasso regression and the subsequent establishment of the Binary Logistic Regression Model on the training dataset, it was found that advanced age (OR=1.046, 95% CI: 1.033-1.060), females (OR = 1.709, 95% CI: 1.342-2.181), overweight individuals (OR = 1.546, 95% CI: 1.165-2.058), individuals with impaired fasting glucose (OR = 1.590, 95% CI: 1.193-2.122), and those with dyslipidemia (OR = 1.588, 95% CI: 1.197-2.112) were potential risk factors for thyroid nodule disease (p<0.05). The area under the curve (AUC) of the receiver operating characteristic (ROC) curve for the Binary Logistic Regression Model is 0.68 (95% CI: 0.64-0.72).

Conclusions

advanced age, females, overweight individuals, those with impaired fasting glucose, and individuals with dyslipidemia are potential risk factors for thyroid nodule disease.

Deep learning to assist composition classification and thyroid solid nodule diagnosis: a multicenter diagnostic study

OBJECTIVES

This study aimed to propose a deep learning (DL)-based framework for identifying the composition of thyroid nodules and assessing their malignancy risk.

METHODS

We conducted a retrospective multicenter study using ultrasound images from four hospitals. Convolutional neural network (CNN) models were constructed to classify ultrasound images of thyroid nodules into solid and non-solid, as well as benign and malignant. A total of 11,201 images of 6784 nodules were used for training, validation, and testing. The area under the receiver-operating characteristic curve (AUC) was employed as the primary evaluation index.

RESULTS

The models had AUCs higher than 0.91 in the benign and malignant grading of solid thyroid nodules, with the Inception-ResNet AUC being the highest at 0.94. In the test set, the best algorithm for identifying benign and malignant thyroid nodules had a sensitivity of 0.88, and a specificity of 0.86. In the human vs. DL test set, the best algorithm had a sensitivity of 0.93, and a specificity of 0.86. The Inception-ResNet model performed better than the senior physicians (p < 0.001). The sensitivity and specificity of the optimal model based on the external test set were 0.90 and 0.75, respectively.

CONCLUSIONS

This research demonstrates that CNNs can assist thyroid nodule diagnosis and reduce the rate of unnecessary fine-needle aspiration (FNA).

CLINICAL RELEVANCE STATEMENT

High-resolution ultrasound has led to increased detection of thyroid nodules. This results in unnecessary fine-needle aspiration and anxiety for patients whose nodules are benign. Deep learning can solve these problems to some extent.

KEY POINTS

• Thyroid solid nodules have a high probability of malignancy. • Our models can improve the differentiation between benign and malignant solid thyroid nodules. • The differential performance of one model was superior to that of senior radiologists. Applying this could reduce the rate of unnecessary fine-needle aspiration of solid thyroid nodules.

LncRNAs associated with lymph node metastasis in thyroid cancer based on TCGA database

OBJECTIVE

Long non-coding RNA (lncRNA), especially RNA associated with lymph node metastasis, plays an important role in the development of cancer. Identifying metastasis related lncRNAs and exploring their clinical significance can guide the treatment and prognosis of thyroid cancer patients.

METHODS

RNA expression and clinical data of thyroid cancer was derived from The Cancer Genome Atlas (TCGA) database, while the survival data was obtained from the ULCAN database. R language and SPSS software were used to analyze the correlation between lncRNA and lymph node metastasis of thyroid cancer and the lncRNAs associated with lymph node metastasis were screened.

RESULT

10 lncRNAs showed significant differential expression in thyroid cancer with and without lymph node metastasis. Four lncRNAs (LRRC52-AS1, AP002358.1, AC004847.1, and AC254633.1) were overexpressed in metastatic thyroid cancer, while six lncRNAs (SLC26A4-AS1, LINC01886, LINC01789, AF131216.3, AC062015.1, and AL031710.1) were underexpressed. The expression levels of these lncRNAs were associated with the clinical staging of tumors. Cox regression analysis further showed that elevated expression levels of AP002358.1 and LRRC52-AS1 were associated with poor prognosis in patients with thyroid cancer. In addition, analysis of the UALCAN database indicated that these two lncRNAs were significantly overexpressed in thyroid cancer compared to other cancers, and the expression levels of AF131216.3 and AL031710.1 were associated with progression-free survival in thyroid cancer patients.

CONCLUSION

These lncRNAs may play crucial roles in the development and progression of thyroid cancer and could serve as potential markers for predicting tumor metastasis, clinical stage, and patient prognosis.

Ultrasound-Base Radiomics for Discerning Lymph Node Metastasis in Thyroid Cancer: A Systematic Review and Meta-analysis

PURPOSE

Ultrasound is the imaging modality of choice for preoperative diagnosis of lymph node metastasis (LNM) in thyroid cancer (TC), yet its efficacy remains suboptimal. As radiomics gains traction in tumor diagnosis, its integration with ultrasound for LNM differentiation in TC has emerged, but its diagnostic merit is debated. This study assesses the accuracy of ultrasound-integrated radiomics in preoperatively diagnosing LNM in TC.

METHODS

Literatures were searched in PubMed, Embase, Cochrane, and Web of Science until July 11, 2023. Quality of the studies was assessed by the radiomics quality score (RQS). A meta-analysis was executed using a bivariate mixed effects model, with a subgroup analysis based on modeling variables (clinical features, radiomics features, or their combination).

RESULTS

Among 27 articles (16,410 TC patients, 6356 with LNM), the average RQS was 16.5 (SD:5.47). Sensitivity of the models based on clinical features, radiomics features, and radiomics features plus clinical features were 0.64, 0.76 and 0.69. Specificities were 0.77, 0.78 and 0.82. SROC values were 0.76, 0.84 and 0.81.

CONCLUSION

Ultrasound-based radiomics effectively evaluates LNM in TC preoperatively. Adding clinical features does not notably enhance the model's performance. Some radiomics studies showed high bias, possibly due to the absence of standard application guidelines.

Predicting central cervical lymph node metastasis in papillary thyroid microcarcinoma using deep learning

Background

The aim of this study is to design a deep learning (DL) model to preoperatively predict the occurrence of central lymph node metastasis (CLNM) in patients with papillary thyroid microcarcinoma (PTMC).

Methods

This research collected preoperative ultrasound (US) images and clinical factors of 611 PTMC patients. The clinical factors were analyzed using multivariate regression. Then, a DL model based on US images and clinical factors was developed to preoperatively predict CLNM. The model's efficacy was evaluated using the receiver operating characteristic (ROC) curve, along with accuracy, sensitivity, specificity, and the F1 score.

Results

The multivariate analysis indicated an independent correlation factors including age ≥55 (OR = 0.309, p < 0.001), tumor diameter (OR = 2.551, p = 0.010), macrocalcifications (OR = 1.832, p = 0.002), and capsular invasion (OR = 1.977, p = 0.005). The suggested DL model utilized US images achieved an average area under the curve (AUC) of 0.65, slightly outperforming the model that employed traditional clinical factors (AUC = 0.64). Nevertheless, the model that incorporated both of them did not enhance prediction accuracy (AUC = 0.63).

Conclusions

The suggested approach offers a reference for the treatment and supervision of PTMC. Among three models used in this study, the deep model relied generally more on image modalities than the data modality of clinic records when making the predictions.

Clinical study on the prediction of ALN metastasis based on intratumoral and peritumoral DCE-MRI radiomics and clinico-radiological characteristics in breast cancer

Objective

To investigate the value of predicting axillary lymph node (ALN) metastasis based on intratumoral and peritumoral dynamic contrast-enhanced MRI (DCE-MRI) radiomics and clinico-radiological characteristics in breast cancer.

Methods

A total of 473 breast cancer patients who underwent preoperative DCE-MRI from Jan 2017 to Dec 2020 were enrolled. These patients were randomly divided into training (n=378) and testing sets (n=95) at 8:2 ratio. Intratumoral regions (ITRs) of interest were manually delineated, and peritumoral regions of 3 mm (3 mmPTRs) were automatically obtained by morphologically dilating the ITR. Radiomics features were extracted, and ALN metastasis-related radiomics features were selected by the Mann-Whitney U test, Z score normalization, variance thresholding, K-best algorithm and least absolute shrinkage and selection operator (LASSO) algorithm. Clinico-radiological risk factors were selected by logistic regression and were also used to construct predictive models combined with radiomics features. Then, 5 models were constructed, including ITR, 3 mmPTR, ITR+3 mmPTR, clinico-radiological and combined (ITR+3 mmPTR+ clinico-radiological) models. The performance of models was assessed by sensitivity, specificity, accuracy, F1 score and area under the curve (AUC) of receiver operating characteristic (ROC), calibration curves and decision curve analysis (DCA).

Results

A total of 2264 radiomics features were extracted from each region of interest (ROI), 3 and 10 radiomics features were selected for the ITR and 3 mmPTR, respectively. 5 clinico-radiological risk factors were selected, including lesion size, human epidermal growth factor receptor 2 (HER2) expression, vascular cancer thrombus status, MR-reported ALN status, and time-signal intensity curve (TIC) type. In the testing set, the combined model showed the highest AUC (0.839), specificity (74.2%), accuracy (75.8%) and F1 Score (69.3%) among the 5 models. DCA showed that it had the greatest net clinical benefit compared to the other models.

Conclusion

The intra- and peritumoral radiomics models based on DCE-MRI could be used to predict ALN metastasis in breast cancer, especially for the combined model with clinico-radiological characteristics showing promising clinical application value.

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.

Application of deep-learning to the automatic segmentation and classification of lateral lymph nodes on ultrasound images of papillary thyroid carcinoma

PURPOSE

It is crucial to preoperatively diagnose lateral cervical lymph node (LN) metastases (LNMs) in papillary thyroid carcinoma (PTC) patients. This study aims to develop deep-learning models for the automatic segmentation and classification of LNM on original ultrasound images.

METHODS

This study included 1000 lateral cervical LN ultrasound images (consisting of 512 benign and 558 metastatic LNs) collected from 728 patients at the Chongqing General Hospital between March 2022 and July 2023. Three instance segmentation models (MaskRCNN, SOLO and Mask2Former) were constructed to segment and classify ultrasound images of lateral cervical LNs by recognizing each object individually and in a pixel-by-pixel manner. The segmentation and classification results of the three models were compared with an experienced sonographer in the test set.

RESULTS

Upon completion of a 200-epoch learning cycle, the loss among the three unique models became negligible. To evaluate the performance of the deep-learning models, the intersection over union threshold was set at 0.75. The mean average precision scores for MaskRCNN, SOLO and Mask2Former were 88.8%, 86.7% and 89.5%, respectively. The segmentation accuracies of the MaskRCNN, SOLO, Mask2Former models and sonographer were 85.6%, 88.0%, 89.5% and 82.3%, respectively. The classification AUCs of the MaskRCNN, SOLO, Mask2Former models and sonographer were 0.886, 0.869, 0.90.2 and 0.852 in the test set, respectively.

CONCLUSIONS

The deep learning models could automatically segment and classify lateral cervical LNs with an AUC of 0.92. This approach may serve as a promising tool to assist sonographers in diagnosing lateral cervical LNMs among patients with PTC.

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 ).

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.

The diagnostic value of GICA used for intraoperative lymph node FNA-Tg measurement to evaluate thyroid cancer metastases

Objective

It is crucial to diagnose lymph node (LN) metastases (LNM) before or during thyroid carcinoma surgery. Measurement of thyroglobulin (Tg) in the fine needle aspirate washout (FNA-Tg) is useful to assist in the diagnosis of LNM for papillary thyroid carcinoma (PTC). This study aimed to assess the diagnostic performance of a new technique based on a colloidal gold-based immunochromatographic assay (GICA) for intraoperative FNA-Tg in diagnosing LNM.

Clinical trial information

This study is registered with chictr.org.cn, ID: ChiCTR2200063561 (registered 11 September, 2022).

Methods

This prospective study enrolled 51 PTC patients who underwent cervical LN dissection. A total of 150 LNs dissected from the central and lateral compartments were evaluated by FNA-Tg-GICA at three different time points and compared with frozen sections and the conventional Tg measurement method electrochemiluminescence immunoassay (ECLIA). Receiver operating characteristic curve (ROC) and area under the curve (AUC), cutoff value to discriminate benign and malignant LNs, sensitivity, specificity, and accuracy were provided.

Results

The cutoff value of FNA-Tg to predict LNM was 110.83 ng/mL for ECLIA and 13.19 ng/mL, 38.69 ng/mL, and 77.17 ng/mL for GICA at 3, 10, and 15 min, respectively. There was no significant difference between the AUCs of GICA at different time points compared to using ECLIA and frozen sections. Besides, the diagnostic performance of GICA and ECLIA showed no significant difference in evaluating LNM from central and lateral compartments or between the TgAb-positive subgroup and TgAb-negative subgroup.

Conclusion

GICA is a promising method for intraoperative FNA-Tg measurement and has high value in predicting LNM. It may be a novel alternative or supplementary method to frozen section or ECLIA.

Radiomics using CT images for preoperative prediction of lymph node metastasis in perihilar cholangiocarcinoma: a multi-centric study

OBJECTIVES

To develop a CT-based radiomics model for preoperative prediction of lymph node (LN) metastasis in perihilar cholangiocarcinoma (pCCA).

METHODS

The study enrolled consecutive pCCA patients from three independent Chinese medical centers. The Boruta algorithm was applied to build the radiomics signature for the primary tumor and LN. The k-means algorithm was employed to cluster the selected LNs based on the radiomics signature LN. Support vector machines were used to construct the prediction models. The diagnostic efficiency was measured by the area under the receiver operating characteristic curve (AUC). The optimal model was evaluated in terms of calibration, clinical usefulness, and prognostic value.

RESULTS

A total of 214 patients were included in the study (mean age: 61.6 years ± 9.4; 130 male). The selected LNs were classified into two clusters, which were significantly correlated with LN metastasis in all cohorts (p < 0.001). The model incorporated the clinical risk factors, radiomics signature primary tumor, and the LN cluster obtained the best discrimination, with AUC values of 0.981 (95% CI: 0.962-1), 0.896 (95% CI: 0.810-0.982), and 0.865 (95% CI: 0.768-0.961) in the training, internal validation, and external validation cohorts, respectively. High-risk patients predicted by the optimal model had shorter overall survival than low-risk patients (median, 13.7 vs. 27.3 months, p < 0.001).

CONCLUSIONS

The study proposed a radiomics model with good performance to predict LN metastasis in pCCA. As a noninvasive preoperative prediction tool, this model may help in patient risk stratification and personalized treatment.

CLINICAL RELEVANCE STATEMENT

A CT-based radiomics model accurately predicts lymph node metastasis in perihilar cholangiocarcinoma patients. This noninvasive preoperative tool can aid in patient risk stratification and personalized treatment, potentially improving patient outcomes.

KEY POINTS

• The radiomics model based on contrast-enhanced CT is a useful tool for preoperative prediction of lymph node metastasis in perihilar cholangiocarcinoma. • Radiomics features extracted from lymph nodes show great potential for predicting lymph node metastasis. • The study is the first to identify a lymph node phenotype with a high probability of metastasis based on radiomics.

A narrative review of deep learning in thyroid imaging: current progress and future prospects

Background and Objective

Deep learning (DL) has contributed substantially to the evolution of image analysis by unlocking increased data and computational power. These DL algorithms have further facilitated the growing trend of implementing precision medicine, particularly in areas of diagnosis and therapy. Thyroid imaging, as a routine means to screening for thyroid diseases on large-scale populations, is a massive data source for the development of DL models. Thyroid disease is a global health problem and involves structural and functional changes. The objective of this study was to evaluate the general rules and future directions of DL networks in thyroid medical image analysis through a review of original articles published between 2018 and 2023.

Methods

We searched for English-language articles published between April 2018 and September 2023 in the databases of PubMed, Web of Science, and Google Scholar. The keywords used in the search included artificial intelligence or DL, thyroid diseases, and thyroid nodule or thyroid carcinoma.

Key Content and Findings

The computer vision tasks of DL in thyroid imaging included classification, segmentation, and detection. The current applications of DL in clinical workflow were found to mainly include management of thyroid nodules/carcinoma, risk evaluation of thyroid cancer metastasis, and discrimination of functional thyroid diseases.

Conclusions

DL is expected to enhance the quality of thyroid images and provide greater precision in the assessment of thyroid images. Specifically, DL can increase the diagnostic accuracy of thyroid diseases and better inform clinical decision-making.

Dual-Energy Computed Tomography Parameters Combined With Inflammatory Indicators Predict Cervical Lymph Node Metastasis in Papillary Thyroid Cancer

BACKGROUND AND OBJECTIVE

Cervical lymph node metastasis (CLNM) is considered a marker of papillar Fethicy thyroid cancer (PTC) progression and has a potential impact on the prognosis of PTC. The purpose of this study was to screen for predictors of CLNM in PTC and to construct a predictive model to guide the surgical approach in patients with PTC.

METHODS

This is a retrospective study. Preoperative dual-energy computed tomography images of 114 patients with pathologically confirmed PTC between July 2019 and April 2023 were retrospectively analyzed. The dual-energy computed tomography parameters [iodine concentration (IC), normalized iodine concentration (NIC), the slope of energy spectrum curve (λHU)] of the venous stage cancer foci were measured and calculated. The independent influencing factors for predicting CLNM were determined by univariate and multivariate logistic regression analysis, and the prediction models were constructed. The clinical benefits of the model were evaluated using decision curves, calibration curves, and receiver operating characteristic curves.

RESULTS

The statistical results show that NIC, derived neutrophil-to-lymphocyte ratio (dNLR), prognostic nutritional index (PNI), gender, and tumor diameter were independent predictors of CLNM in PTC. The AUC of the nomogram was .898 (95% CI: .829-.966), and the calibration curve and decision curve showed that the prediction model had good predictive effect and clinical benefit, respectively.

CONCLUSION

The nomogram constructed based on dual-energy CT parameters and inflammatory prognostic indicators has high clinical value in predicting CLNM in PTC patients.

CT-based intratumoral and peritumoral deep transfer learning features prediction of lymph node metastasis in non-small cell lung cancer

BACKGROUND

The main metastatic route for lung cancer is lymph node metastasis, and studies have shown that non-small cell lung cancer (NSCLC) has a high risk of lymph node infiltration.

OBJECTIVE

This study aimed to compare the performance of handcrafted radiomics (HR) features and deep transfer learning (DTL) features in Computed Tomography (CT) of intratumoral and peritumoral regions in predicting the metastatic status of NSCLC lymph nodes in different machine learning classifier models.

METHODS

We retrospectively collected data of 199 patients with pathologically confirmed NSCLC. All patients were divided into training (n = 159) and validation (n = 40) cohorts, respectively. The best HR and DTL features in the intratumoral and peritumoral regions were extracted and selected, respectively. Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Light Gradient Boosting Machine (Light GBM), Multilayer Perceptron (MLP), and Logistic Regression (LR) models were constructed, and the performance of the models was evaluated.

RESULTS

Among the five models in the training and validation cohorts, the LR classifier model performed best in terms of HR and DTL features. The AUCs of the training cohort were 0.841 (95% CI: 0.776-0.907) and 0.955 (95% CI: 0.926-0.983), and the AUCs of the validation cohort were 0.812 (95% CI: 0.677-0.948) and 0.893 (95% CI: 0.795-0.991), respectively. The DTL signature was superior to the handcrafted radiomics signature.

CONCLUSIONS

Compared with the radiomics signature, the DTL signature constructed based on intratumoral and peritumoral areas in CT can better predict NSCLC lymph node metastasis.

Development and validation of survival nomograms for patients with differentiated thyroid cancer with distant metastases: a SEER Program-based study

BACKGROUND

We aimed to develop a nomogram model of overall survival (OS) and cancer-specific survival (CSS) in patients with differentiated thyroid cancer with distant metastases, and to evaluate and validate the nomogram. Also, its prognostic value was compared with that of the 8th edition of the American Joint Committee on Cancer tumor-node-metastasis staging system (AJCC8SS).

METHODS

Patients with distant metastatic differentiated thyroid cancer (DMDTC) from 2004 to 2015 were selected from the Surveillance, Epidemiology, and End Results (SEER) Program to extract the clinical variables used for analysis. A total of 906 patients were divided into a training set (n = 634) and validation set (n = 272). OS and CSS were selected as the primary end point and secondary end point. LASSO regression analysis and multivariate Cox regression analysis were applied to screen variables for constructing OS and CSS nomograms for survival probability at 3, 5, and 10 years. Nomograms were evaluated and validated using the consistency index (C-index), time-dependent receiver operator characteristic (ROC) curves, area under the ROC curve, calibration curves, and decision curve analysis (DCA). The predictive survival of the nomogram was compared with that of AJCC8SS. Kaplan-Meier curves and log-rank tests were used to evaluate the risk-stratification ability OS and CSS nomograms.

RESULTS

CS and CSS nomograms included six independent predictors: age, marital status, type of surgical procedure, lymphadenectomy, radiotherapy, and T stage. The C-index for the OS nomogram was 0.7474 (95% CI = 0.7199-0.775), and that for the CSS nomogram was 0.7572 (0.7281-0.7862). The nomogram showed good agreement with the "ideal" calibration curve in the training set and validation sets. DCA confirmed that the survival probability predicted by the nomogram had high clinical predictive value. The nomogram could stratify patients more accurately, and showed more robust accuracy and predictive power, than AJCC8SS.

CONCLUSIONS

We established and validated prognostic nomograms for patients with DMDTC, which had significant clinical value compared with AJCC8SS.

Development and Validation of a Dual-Energy CT-Based Model for Predicting the Number of Central Lymph Node Metastases in Clinically Node-Negative Papillary Thyroid Carcinoma

RATIONALE AND OBJECTIVES

This study aimed to develop and validate a dual-energy CT (DECT)-based model for preoperative prediction of the number of central lymph node metastases (CLNMs) in clinically node-negative (cN0) papillary thyroid carcinoma (PTC) patients.

MATERIALS AND METHODS

Between January 2016 and January 2021, 490 patients who underwent lobectomy or thyroidectomy, CLN dissection, and preoperative DECT examinations were enrolled and randomly allocated into the training (N = 345) and validation cohorts (N = 145). The patients' clinical characteristics and quantitative DECT parameters obtained on primary tumors were collected. Independent predictors of> 5 CLNMs were identified and integrated to construct a DECT-based prediction model, for which the area under the curve (AUC), calibration, and clinical usefulness were assessed. Risk group stratification was performed to distinguish patients with different recurrence risks.

RESULTS

More than 5 CLNMs were found in 75 (15.3%) cN0 PTC patients. Age, tumor size, normalized iodine concentration (NIC), normalized effective atomic number (nZeff) and the slope of the spectral Hounsfield unit curve (λHu) in the arterial phase were independently associated with> 5 CLNMs. The DECT-based nomogram that incorporated predictors demonstrated favorable performance in both cohorts (AUC: 0.842 and 0.848) and significantly outperformed the clinical model (AUC: 0.688 and 0.694). The nomogram showed good calibration and added clinical benefit for predicting> 5 CLNMs. The KaplanMeier curves for recurrence-free survival showed that the high- and low-risk groups stratified by the nomogram were significantly different.

CONCLUSION

The nomogram based on DECT parameters and clinical factors could facilitate preoperative prediction of the number of CLNMs in cN0 PTC patients.

Prediction of central lymph node metastasis in patients with papillary thyroid microcarcinoma by gradient-boosting decision tree model based on ultrasound radiomics and clinical features

Background

In recent years, the study of radiomics in thyroid diseases has developed rapidly. This study aimed to establish a preoperative radiomics prediction model for central compartment lymph node metastases (CLNMs) in papillary thyroid microcarcinoma (PTMC) patients using gradient-boosting decision tree (GBDT) model and evaluate the performance of the model.

Methods

A total of 274 patients with PTMC admitted for thyroid surgery at China-Japan Union Hospital of Jilin University from January 2020 to July 2022 were retrospectively analyzed. Patients were randomized into training and validation cohorts according to a ratio of 8:2. Radiomics features were extracted from the ultrasound (US) images of PTMC lesions. The open-source software Pyradiomics was used to extract radiomics features, and WEKA software was used to select CLNM-related radiomics features. Clinical risk factors for CLNM were screened by statistical methods. The GBDT model was constructed by combining radiomics features and clinical risk factors, and compared with the diagnostic efficacy of US-reported cervical lymph node status. Shapley Additive exPlanations (SHAP) was applied to visualize and analyze the GBDT model globally and locally.

Results

A total of seven radiomics features were significantly correlated with central lymph node status in the training and validation cohorts. The predictors in the GBDT model included the radiomics features, sex, age, and body mass index (BMI). The area under the curve (AUC) values of the GBDT model in the training and validation cohorts were 0.946 [95% confidence interval (CI): 0.920-0.972] and 0.845 (95% CI: 0.714-0.976), respectively, compared with 0.583 (95% CI: 0.508-0.659) and 0.582 (95% CI: 0.430-0.736) for US-reported lymph node status alone. The Delong test showed a significant difference between AUS in the training and validation cohorts (P<0.001, respectively). SHAP visual analysis showed the effect of each parameter on the GBDT model globally and locally. Decision curve analysis demonstrated the clinical utility of the GBDT model.

Conclusions

The prediction of CLNM by the GBDT model, based on US radiomics features and clinical factors, can be better than that by using US alone in patients with PTMC. Furthermore, the GBDT model may serve a guidance of clinical decision for patient's treatment strategy.

Tetraspanin 1 regulates papillary thyroid tumor growth and metastasis through c-Myc-mediated glycolysis

Papillary thyroid cancer (PTC) is the most common form of thyroid cancer and is characterized by its tendency for lymphatic metastasis, leading to a poor prognosis. Tetraspanin 1 (TSPAN1) is a member of the tetra-transmembrane protein superfamily and has been implicated in tumorigenesis and cancer metastasis in various studies. However, the role of TSPAN1 in PTC tumor development remains unclear. In this study, we aimed to investigate the impact of TSPAN1 on PTC cell behavior. Our results demonstrate that knockdown of TSPAN1 inhibits PTC cell proliferation, migration, and invasion, while overexpression of TSPAN1 has the opposite effect. These findings suggest that TSPAN1 might play a role in the tumorigenesis and invasiveness of PTC. Mechanistically, we found that TSPAN1 activates the ERK pathway by increasing its phosphorylation, subsequently leading to upregulated expression of c-Myc. Additionally, we observed that TSPAN1-ERK-c-Myc axis activation promotes glycolytic activity in PTC cells, as evidenced by the upregulation of glycolytic genes such as LDHA. Taken together, our findings indicate that TSPAN1 acts as an oncogene in PTC by regulating glycolytic metabolism. This discovery highlights the potential of TSPAN1 as a promising therapeutic target for PTC treatment. Further research in this area could provide valuable insights into the development of targeted therapies for PTC patients.

A model for predicting lymph node metastasis of thyroid carcinoma: a multimodality convolutional neural network study

Background

Early preoperative evaluation of cervical lymph node metastasis (LNM) in papillary thyroid carcinoma (PTC) is critical for further surgical treatment. However, insufficient accuracy in predicting LNM status for PTC based on ultrasound images is a problem that needs to be urgently resolved. This study aimed to clarify the role of convolutional neural networks (CNNs) in predicting LNM for PTC based on multimodality ultrasound.

Methods

In this study, the data of 308 patients who were clinically diagnosed with PTC and had confirmed LNM status via postoperative pathology at Beijing Tiantan Hospital, Capital Medical University, from August 2018 to April 2022 were incorporated into CNN algorithm development and evaluation. Of these patients, 80% were randomly included into the training set and 20% into the test set. The ultrasound examination of cervical LNM was performed to assess possible metastasis. Residual network 50 (Resnet50) was employed for feature extraction from the B-mode and contrast-enhanced ultrasound (CEUS) images. For each case, all of features were extracted from B-mode ultrasound images and CEUS images separately, and the ultrasound examination data of cervical LNM information were concatenated together to produce a final multimodality LNM prediction. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were used to evaluate the performance of the predictive model. Heatmaps were further developed for visualizing the attention region of the images of the best-working model.

Results

Of the 308 patients with PTC included in the analysis, 158 (51.3%) were diagnosed as LNM and 150 (48.7%) as non-LNM. In the test set, when a triple-modality method (i.e., B-mode image, CEUS image, and ultrasound examination of cervical LNM) was used, accuracy was maximized at 80.65% (AUC =0.831; sensitivity =80.65%; specificity =82.26%), which showed an expected increased performance over B-mode alone (accuracy =69.00%; AUC =0.720; sensitivity =70.00%; specificity =73.00%) and a dual-modality method (B-mode image plus CEUS image: accuracy =75.81%; AUC =0.742; sensitivity =74.19%; specificity =77.42%). The heatmaps of our triple-modality model demonstrated a possible focus area and revealed the model's flaws.

Conclusions

The PTC lymph node prediction model based on the triple-modality features significantly outperformed all the other feature configurations. This deep learning model mimics the workflow of a human expert and leverages multimodal data from patients with PTC, thus further supporting clinical decision-making.

Predictive factors of lymph node metastasis in papillary thyroid cancer

This study aimed to evaluate factors that predict lymph node metastasis (LNM) in papillary thyroid cancer (PTC). This retrospective cross-sectional study compared the demographic, clinical, and ultrasonographic findings of patients with PTC with and without LNM. Subgroup analysis was conducted for micro-PTCs (<1 cm). Among total (n = 512; mean age, 47.3 ± 12.7 years) and micro-PTC patients (n = 312), 35.7% and 19.6% had LNM, respectively. Younger age, male sex, tumor size, bilaterality, and suspicious ultrasound features of the tumor were associated with LNM. In multiple logistic regression analysis, among all patients, age, tumor size, and extrathyroidal extension were independent risk factors for LNM (all p<0.05). In the micro-PTC subgroup, age, extrathyroidal extension, bilaterality of tumor, and presence of autoimmune thyroid disease were independent risk and protective factors for LNM (all p<0.05). In the receiver operating characteristic analysis, the accuracy of the multivariable logistic regression model for predicting LNM among all patients and micro-PTC was acceptable (area under the curve = 0.729 and 0.733, respectively). Age, sex, tumor size, and extrathyroidal extension can assist in predicting LNM in PTC patients. Additionally, the bilaterality of tumors and presence of autoimmune thyroid disease can assist in predicting LNM in micro-PTCs.

AI diagnosis of Bethesda category IV thyroid nodules

Thyroid nodules are a common disease, and fine needle aspiration cytology (FNAC) is the primary method to assess their malignancy. For the diagnosis of follicular thyroid nodules, however, FNAC has limitations. FNAC can classify them only as Bethesda IV nodules, leaving their exact malignant status and pathological type undetermined. This imprecise diagnosis creates difficulties in selecting the follow-up treatment. In this retrospective study, we collected ultrasound (US) image data of Bethesda IV thyroid nodules from 2006 to 2022 from five hospitals. Then, US image-based artificial intelligence (AI) models were trained to identify the specific category of Bethesda IV thyroid nodules. We tested the models using two independent datasets, and the best AI model achieved an area under the curve (AUC) between 0.90 and 0.95, demonstrating its potential value for clinical application. Our research findings indicate that AI could change the diagnosis and management process of Bethesda IV thyroid nodules.

Radiomics diagnostic performance in predicting lymph node metastasis of papillary thyroid carcinoma: A systematic review and meta-analysis

PURPOSE

To evaluate the diagnostic performance of radiomics in lymph node metastasis (LNM) prediction in patients with papillary thyroid carcinoma (PTC) through a systematic review and meta-analysis.

METHOD

A literature search of PubMed, EMBASE, and Web of Science was conducted to find relevant studies published until February 18th, 2023. Studies that reported the accuracy of radiomics in different imaging modalities for LNM prediction in PTC patients were selected. The methodological quality of included studies was evaluated by radiomics quality score (RQS) and quality assessment of diagnostic accuracy studies (QUADAS-2) tools. General characteristics and radiomics accuracy were extracted. Overall sensitivity, specificity, and area under the curve (AUC) were calculated for diagnostic accuracy evaluation. Spearman correlation coefficient and subgroup analysis were performed for heterogeneity exploration.

RESULTS

In total, 25 studies were included, of which 22 studies provided adequate data for meta-analysis. We conducted two types of meta-analysis: one focused solely on radiomics features models and the other combined radiomics and non-radiomics features models in the analysis. The pooled sensitivity, specificity, and AUC of radiomics and combined models were 0.75 [0.68, 0.80] vs. 0.77 [0.74, 0.80], 0.77 [0.74, 0.81] vs. 0.83 [0.78, 0.87] and 0.80 [0.73, 0.85] vs 0.82 [0.75, 0.88], respectively. The analysis showed a high heterogeneity level among the included studies. There was no threshold effect. The subgroup analysis demonstrated that utilizing ultrasonography, 2D segmentation, central and lateral LNM detection, automatic segmentation, and PyRadiomics software could slightly improve diagnostic accuracy.

CONCLUSIONS

Our meta-analysis shows that the radiomics has the potential for pre-operative LNM prediction in PTC patients. Although methodological quality is sufficient but we still need more prospective studies with larger sample sizes from different centers.

Ultrasonic Feature Prediction of Large-Number Central Lymph Node Metastasis in Clinically Node-Negative Solitary Papillary Thyroid Carcinoma

BACKGROUND

The purpose of this study was to investigate the preoperative prediction of large-number central lymph node metastasis (CLNM) in single thyroid papillary carcinoma (PTC) with negative clinical lymph nodes.

METHODS

A total of 634 patients with clinically lymph node-negative single PTC who underwent thyroidectomy and central lymph node dissection at the First Affiliated Hospital of Anhui Medical University and the Nanchong Central Hospital between September 2018 and September 2021 were analyzed retrospectively. According to the CLNM status, the patients were divided into two groups: small-number (≤5 metastatic lymph nodes) and large-number (>5 metastatic lymph nodes). Univariate and multivariate analyses were used to determine the independent predictors of large-number CLNM. Simultaneously, a nomogram based on risk factors was established to predict large-number CLNM.

RESULTS

The incidence of large-number CLNM was 7.7%. Univariate and multivariate analyses showed that age, tumor size, and calcification were independent risk factors for predicting large-number CLNM. The combination of the three independent predictors achieved an AUC of 0.806. Based on the identified risk factors that can predict large-number CLNM, a nomogram was developed. The analysis of the calibration map showed that the nomogram had good performance and clinical application.

CONCLUSION

In patients with single PTC with negative clinical lymph nodes large-number CLNM is related to age, size, and calcification in patients with a single PTC with negative clinical lymph nodes. Surgeons and radiologists should pay more attention to patients with these risk factors. A nomogram can help guide the surgical decision for PTC.

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.

A novel wavelet-transform-based convolution classification network for cervical lymph node metastasis of papillary thyroid carcinoma in ultrasound images

Preoperative assessment of cervical lymph nodes metastasis (CLNM) for accurate qualitative and locating diagnosis is important for choosing the best treatment option for patients with papillary thyroid cancer. Non-destructive, non-invasive ultrasound is currently the imaging method of choice for lymph node metastatic assessment. For lymph node characteristics and ultrasound images, this paper proposes a multitasking network framework for diagnosing metastatic lymph nodes in ultrasound images, in which localization module not only provides information on the location of lymph nodes to focus on the peripheral and self regions of lymph nodes, but also provides structural features of lymph nodes for subsequent classification module. In the classification module, we design a novel wavelet-transform-based convolution network. Wavelet transform is introduced into the deep learning convolution module to analyze ultrasound images in both spatial and frequency domains, which effectively enriches the feature information and improves the classification performance of the model without increasing the model parameters. We collected 510 patient data (N = 1376) from Shanghai Sixth People's Hospital regarding ultrasound lymph nodes in the neck, as well as used three publicly available ultrasound datasets, including SCUI2020 (N = 2914), DDTI (N = 480), and BUSI (N = 780). Compared to the optimal two-stage model, our model has improved its accuracy and AUC indexes by 5.83% and 4%, which outperforms the two-stage architectures and also surpasses the latest classification networks.

Predictive Factors Affecting the Development of Lateral Lymph Node Metastasis in Papillary Thyroid Cancer

Objectives

Lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) determines the extent of surgery to be performed and the prognosis of the disease. In this study, we aimed to evaluate the clinicopathological risk factors affecting the development of LLNM.

Methods

We retrospectively evaluated the demographic and clinicopathological data of 346 cases with PTC who were operated in our clinic between May 2012 and September 2020. The patients were divided into 2 groups as patients with LLNM (Group 1) and without LLNM (Group 2).

Results

Thirty-six (10.4%) patients out of 346 patients with PTC had LLNM. A statistically significant difference was found between Group 1 and Group 2 regarding the male gender (M/F: 38.9% vs. 21.6%; p=0.020), tumor size (2.30±1.99 cm vs. 1.31±1.40 cm; p=0.000), lymphovascular invasion (69.4 vs. 20.6%; p=0.000), multicentricity (69.4% vs. 35.5%; p=0.000), multifocality (p=0.000), aggressive variant (22.2% vs. 9.4%; p=0.000), extrathyroidal extension (50% vs. 16.1% p=0.000), central lymph node metastasis (CLNM) rates (75% vs. 6.5%; p=0.000), and ≥3 cm lymph node metastasis (48.5% vs. 0%, p=0.000), distant metastasis (2.1% vs. 0%, p=0.000), respectively. Multivariance analysis determined the presence of CLNM as an independent risk factor for the development of LLNM.

Conclusion

The presence of CLNM in patients with PTC was determined as an independent risk factor for the development of LLNM. Although there has been increasing debate about prophylactic central neck dissection (pCND) in LLNM, pCND should still be considered in these patients as the rate of CLNM is high in patients with LLNM. CLNM might be a reference for surgeons to determine the extent of surgery. In addition, the presence of CLNM is important for close follow-up for the early detection of LLNM recurrence.

Insight of novel biomarkers for papillary thyroid carcinoma through multiomics

Introduction

The overdiagnosing of papillary thyroid carcinoma (PTC) in China necessitates the development of an evidence-based diagnosis and prognosis strategy in line with precision medicine. A landscape of PTC in Chinese cohorts is needed to provide comprehensiveness.

Methods

6 paired PTC samples were employed for whole-exome sequencing, RNA sequencing, and data-dependent acquisition mass spectrum analysis. Weighted gene co-expression network analysis and protein-protein interactions networks were used to screen for hub genes. Moreover, we verified the hub genes' diagnostic and prognostic potential using online databases. Logistic regression was employed to construct a diagnostic model, and we evaluated its efficacy and specificity based on TCGA-THCA and GEO datasets.

Results

The basic multiomics landscape of PTC among local patients were drawn. The similarities and differences were compared between the Chinese cohort and TCGA-THCA cohorts, including the identification of PNPLA5 as a driver gene in addition to BRAF mutation. Besides, we found 572 differentially expressed genes and 79 differentially expressed proteins. Through integrative analysis, we identified 17 hub genes for prognosis and diagnosis of PTC. Four of these genes, ABR, AHNAK2, GPX1, and TPO, were used to construct a diagnostic model with high accuracy, explicitly targeting PTC (AUC=0.969/0.959 in training/test sets).

Discussion

Multiomics analysis of the Chinese cohort demonstrated significant distinctions compared to TCGA-THCA cohorts, highlighting the unique genetic characteristics of Chinese individuals with PTC. The novel biomarkers, holding potential for diagnosis and prognosis of PTC, were identified. Furthermore, these biomarkers provide a valuable tool for precise medicine, especially for immunotherapeutic or nanomedicine based cancer therapy.

Three-dimensional ultrasound-based radiomics nomogram for the prediction of extrathyroidal extension features in papillary thyroid cancer

Purpose

To develop and validate a three-dimensional ultrasound (3D US) radiomics nomogram for the preoperative prediction of extrathyroidal extension (ETE) in papillary thyroid cancer (PTC).

Methods

This retrospective study included 168 patients with surgically proven PTC (non-ETE, n = 90; ETE, n = 78) who were divided into training (n = 117) and validation (n = 51) cohorts by a random stratified sampling strategy. The regions of interest (ROIs) were obtained manually from 3D US images. A larger number of radiomic features were automatically extracted. Finally, a nomogram was built, incorporating the radiomics scores and selected clinical predictors. Receiver operating characteristic (ROC) curves were performed to validate the capability of the nomogram on both the training and validation sets. The nomogram models were compared with conventional US models. The DeLong test was adopted to compare different ROC curves.

Results

The area under the receiver operating characteristic curve (AUC) of the radiologist was 0.67 [95% confidence interval (CI), 0.580-0.757] in the training cohort and 0.62 (95% CI, 0.467-0.746) in the validation cohort. Sixteen features from 3D US images were used to build the radiomics signature. The radiomics nomogram, which incorporated the radiomics signature, tumor location, and tumor size showed good calibration and discrimination in the training cohort (AUC, 0.810; 95% CI, 0.727-0.876) and the validation cohort (AUC, 0.798; 95% CI, 0.662-0.897). The result suggested that the diagnostic efficiency of the 3D US-based radiomics nomogram was better than that of the radiologist and it had a favorable discriminate performance with a higher AUC (DeLong test: p < 0.05).

Conclusions

The 3D US-based radiomics signature nomogram, a noninvasive preoperative prediction method that incorporates tumor location and tumor size, presented more advantages over radiologist-reported ETE statuses for PTC.