Sonographic features of primary tumor as independent predictive factors for lymph node metastasis in papillary thyroid carcinoma

Deep learning predicts cervical lymph node metastasis in clinically node-negative papillary thyroid carcinoma

OBJECTIVES

Precise determination of cervical lymph node metastasis (CLNM) involvement in patients with early-stage thyroid cancer is fairly significant for identifying appropriate cervical treatment options. However, it is almost impossible to directly judge lymph node metastasis based on the imaging information of early-stage thyroid cancer patients with clinically negative lymph nodes.

METHODS

Preoperative US images (BMUS and CDFI) of 1031 clinically node negative PTC patients definitively diagnosed on pathology from two independent hospitals were divided into training set, validation set, internal test set, and external test set. An ensemble deep learning model based on ResNet-50 was built integrating clinical variables, BMUS, and CDFI images using a bagging classifier to predict metastasis of CLN. The final ensemble model performance was compared with expert interpretation.

RESULTS

The ensemble deep convolutional neural network (DCNN) achieved high performance in predicting CLNM in the test sets examined, with area under the curve values of 0.86 (95% CI 0.78-0.94) for the internal test set and 0.77 (95% CI 0.68-0.87) for the external test set. Compared to all radiologists averaged, the ensemble DCNN model also exhibited improved performance in making predictions. For the external validation set, accuracy was 0.72 versus 0.59 (p = 0.074), sensitivity was 0.75 versus 0.58 (p = 0.039), and specificity was 0.69 versus 0.60 (p = 0.078).

CONCLUSIONS

Deep learning can non-invasive predict CLNM for clinically node-negative PTC using conventional US imaging of thyroid cancer nodules and clinical variables in a multi-institutional dataset with superior accuracy, sensitivity, and specificity comparable to experts.

CRITICAL RELEVANCE STATEMENT

Deep learning efficiently predicts CLNM for clinically node-negative PTC based on US images and clinical variables in an advantageous manner.

KEY POINTS

• A deep learning-based ensemble algorithm for predicting CLNM in PTC was developed. • Ultrasound AI analysis combined with clinical data has advantages in predicting CLNM. • Compared to all experts averaged, the DCNN model achieved higher test performance.

Artificial intelligence in thyroid ultrasound

Artificial intelligence (AI), particularly deep learning (DL) algorithms, has demonstrated remarkable progress in image-recognition tasks, enabling the automatic quantitative assessment of complex medical images with increased accuracy and efficiency. AI is widely used and is becoming increasingly popular in the field of ultrasound. The rising incidence of thyroid cancer and the workload of physicians have driven the need to utilize AI to efficiently process thyroid ultrasound images. Therefore, leveraging AI in thyroid cancer ultrasound screening and diagnosis cannot only help radiologists achieve more accurate and efficient imaging diagnosis but also reduce their workload. In this paper, we aim to present a comprehensive overview of the technical knowledge of AI with a focus on traditional machine learning (ML) algorithms and DL algorithms. We will also discuss their clinical applications in the ultrasound imaging of thyroid diseases, particularly in differentiating between benign and malignant nodules and predicting cervical lymph node metastasis in thyroid cancer. Finally, we will conclude that AI technology holds great promise for improving the accuracy of thyroid disease ultrasound diagnosis and discuss the potential prospects of AI in this field.

Risk factors and prediction models of lymph node metastasis in papillary thyroid carcinoma based on clinical and imaging characteristics

BACKGROUND

Papillary thyroid carcinoma (PTC) commonly presents with lymph node metastasis, which may be associated with worsened prognosis. This study aimed to comprehensively evaluate the risk factors of lymph node metastasis in PTC based on preoperative clinical and imaging data and to construct a nomogram model to predict the risk of lymph node metastasis.

METHODS

A total of 989 patients with PTC were enrolled and randomly divided into training and validation cohorts in an 8:2 ratio. Independent risk factors for lymph node metastasis in PTC were analyzed using univariate and stepwise multivariate logistic regression. An importance analysis of independent risk factors affecting lymph node metastasis was performed according to the random forest method. Subsequently, a nomogram to predict lymph node metastasis was constructed, and the predictive effect of the nomogram was evaluated using receiver operating characteristic analysis and calibration curves.

RESULTS

Univariate regression analysis revealed that age, sex, body weight, systolic blood pressure, free triiodothyronine, nodule location, nodule number, Thyroid Imaging Reporting and Data System (TI-RADS) grade on color Doppler ultrasound, enlarged lymph node present on imaging, and nodule diameter could affect lymph node metastasis in PTC. Stepwise multivariate regression analysis showed that sex, age, enlarged lymph node present on imaging, nodule diameter, and color Doppler TI-RADS grade were independent risk factors for lymph node metastasis in PTC. Combining these five independent risk factors, a nomogram prediction model was constructed. The area under the curve (AUC) of the nomogram in the training and validation cohorts was 0.742 and 0.765, respectively, with a well-fitted calibration curve.

CONCLUSION

Our study showed that independent risk factors for lymph node metastasis in PTC were sex, age, enlarged lymph node present on imaging, nodule diameter, and color Doppler TI-RADS grade. The nomogram constructed based on these independent risk factors can better predict the risk of lymph node metastasis.

Nomograms based on preoperative multimodal ultrasound of papillary thyroid carcinoma for predicting central lymph node metastasis

OBJECTIVES

To establish a nomogram for predicting central lymph node metastasis (CLNM) based on the preoperative clinical and multimodal ultrasound (US) features of papillary thyroid carcinoma (PTC) and cervical LNs.

METHODS

Overall, 822 patients with PTC were included in this retrospective study. A thyroid tumor ultrasound model (TTUM) and thyroid tumor and cervical LN ultrasound model (TTCLNUM) were constructed as nomograms to predict the CLNM risk. Areas under the curve (AUCs) evaluated model performance. Calibration and decision curves were applied to assess the accuracy and clinical utility.

RESULTS

For the TTUM training and test sets, the AUCs were 0.786 and 0.789 and bias-corrected AUCs were 0.786 and 0.831, respectively. For the TTCLNUM training and test sets, the AUCs were 0.806 and 0.804 and bias-corrected AUCs were 0.807 and 0.827, respectively. Calibration and decision curves for the TTCLNUM nomogram exhibited higher accuracy and clinical practicability. The AUCs were 0.746 and 0.719 and specificities were 0.942 and 0.905 for the training and test sets, respectively, when the US tumor size was ≤ 8.45 mm, while the AUCs were 0.737 and 0.824 and sensitivity were 0.905 and 0.880, respectively, when the US tumor size was > 8.45 mm.

CONCLUSION

The TTCLNUM nomogram exhibited better predictive performance, especially for the CLNM risk of different PTC tumor sizes. Thus, it serves as a useful clinical tool to supply valuable information for active surveillance and treatment decisions.

KEY POINTS

• Our preoperative noninvasive and intuitive prediction method can improve the accuracy of central lymph node metastasis (CLNM) risk assessment and guide clinical treatment in line with current trends toward personalized treatments. • Preoperative clinical and multimodal ultrasound features of primary papillary thyroid carcinoma (PTC) tumors and cervical LNs were directly used to build an accurate and easy-to-use nomogram for predicting CLNM. • The thyroid tumor and cervical lymph node ultrasound model exhibited better performance for predicting the CLNM of different PTC tumor sizes. It may serve as a useful clinical tool to provide valuable information for active surveillance and treatment decisions.

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

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

A computed tomography-based radiomic nomogram for predicting lymph node metastasis in patients with early-stage papillary thyroid carcinoma

BACKGROUND

Accurate assessment of lymph node metastasis (LNM) is important for the selection of the optimal therapeutic strategy in patients with papillary thyroid carcinoma (PTC).

PURPOSE

To develop and validate a radiomics nomogram based on computed tomography (CT) for predicting LNM in patients with early-stage PTC.

MATERIAL AND METHODS

A total of 92 patients with pathologically confirmed PTC were divided into a training cohort (n =  64) and validation cohort (n  =  28). Radiomic features of the tumor and peritumoral interstitium were extracted from contrast-enhanced CT images. The radiomic signature was constructed and the radiomic score (Rad-score) was calculated. Combined with the Rad-score and independent clinical factors, a radiomic nomogram was constructed and its performance was assessed by receiver operating characteristic (ROC) curves and calibration plots. The comparison of ROC curves was performed with DeLong's test.

RESULTS

A combined nomogram model of the thyroid tumor and peritumoral interstitium was constructed based on the Rad-score, tumor location, maximum diameter, and T stage, and it had areas under the ROC curve of 0.956 (95% confidence interval [CI] = 0.913-1.000) and 0.876 (95% CI = 0.741-1.000) in the training and validation cohorts, respectively. Decision curve analysis suggested that the combined nomogram model had better clinical usefulness than the other models.

CONCLUSION

A CT-based radiomics nomogram incorporating the radiomic signature and the selected clinical predictors can be a reliable approach to preoperatively predict the LNM status in patients with early-stage PTC, which is helpful for treatment decisions and prognosis.

Capsular extension at ultrasound is associated with lateral lymph node metastasis in patients with papillary thyroid carcinoma: a retrospective study

BACKGROUND

In patients with papillary thyroid cancer (PTC), cervical lymph node metastasis (LNM) must be carefully assessed to determine the extent of lymph node dissection required and patient prognosis. Few studies attempted to determine whether the ultrasound (US) appearance of the primary thyroid tumor could be used to predict cervical lymph node involvement. This study aimed to identify the US features of the tumor that could predict cervical LNM in patients with PTC.

METHODS

This was a retrospective study of patients with pathologically confirmed PTC. We evaluated the following US characteristics: lobe, isthmus, and tumor size; tumor position; parenchymal echogenicity; the number of lesions (i.e., tumor multifocality); parenchymal and lesional vascularity; tumor margins and shape; calcifications; capsular extension; tumor consistency; and the lymph nodes along the carotid vessels. The patients were grouped as no LNM (NLNM), central LNM (CLNM) alone, and lateral LNM (LLNM) with/without CLNM, according to the postoperative pathological examination.

RESULTS

Totally, 247 patients, there were 67 men and 180 women. Tumor size of > 10 mm was significantly more common in the CLNM (70.2%) and LLNM groups (89.6%) than in the NLNM group (45.4%). At US, capsular extension > 50% was most common in the LLNM group (35.4%). The multivariable analysis revealed that age (OR = 0.203, 95%CI: 0.095-0.431, P < 0.001) and tumor size (OR = 2.657, 95%CI: 1.144-6.168, P = 0.023) were independently associated with CLNM compared with NLNM. In addition, age (OR = 0.277, 95%CI: 0.127-0.603, P = 0.001), tumor size (OR = 6.069, 95%CI: 2.075-17.75, P = 0.001), and capsular extension (OR = 2.09, 95%CI: 1.326-3.294, P = 0.001) were independently associated with LLNM compared with NLNM.

CONCLUSION

Percentage of capsular extension at ultrasound is associated with LLNM. US-guided puncture cytology and eluent thyroglobulin examination could be performed as appropriate to minimize the missed diagnosis of LNM.

Pathological analysis and surgical modalities selection of cT1N0M0 solitary papillary thyroid carcinoma in the isthmus

Background

prognosis, identify clinicopathological characteristics, and determine optimal modalities for cT1N0M0 solitary papillary thyroid carcinoma in the isthmus (PTCI).

Methods

The clinical data of 124 patients with cT1N0M0 solitary PTCI from 3 medical centers were analyzed retrospectively. Of these, 32 participants had undergone total thyroidectomy plus unilateral central neck dissection, 36 had received total thyroidectomy plus bilateral central neck dissection, 24 had less-than-total thyroidectomy plus unilateral central neck dissection, and 32 had less-than-total thyroidectomy plus bilateral central neck dissection. We compared the effects of different surgical modalities and clinicopathological characteristics on the prognosis of cT1N0M0 solitary PTCI.

Results

There was no significant difference in postoperative recurrence-free survival between participants who received different extents of central region lymph node dissection and thyroidectomies (P>0.05). Temporary hypocalcemia occurred in participants who underwent total thyroidectomy plus bilateral central neck dissection [chi-square (χ²) =7.87, P=0.005]. Tumors with primary lesions ≥0.55 cm were prone to have central lymph node metastasis [95% confidence interval (CI): 0.51 to 0.71, P=0.047]. Multiple logistic analysis suggested that age over 55 years [odds ratio (OR) =11.90, 95% CI: 1.36 to 104.03, P=0.025], tumor size greater than 0.55 cm (OR =4.16, 95% CI: 1.28 to 13.52, P=0.018), and absence of nodular goiter (OR =2.57, 95% CI: 1.05 to 6.32, P=0.04) were risk factors for central lymph node metastasis of patients with cT1N0M0 solitary PTCI.

Conclusions

Less-than-total thyroidectomy is recommended for patients with cT1N0M0 solitary PTCI. Central lymph node dissection is recommended for patients who are prone to have central occult lymph node metastases with tumor size ≥55 cm, older than 55 years, and without nodular goiter.

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

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

Risk factors for central lymph node metastasis in the cervical region in papillary thyroid carcinoma: a retrospective study

Background

To investigate the influence of different risk factors on central lymph node metastasis (CLNM) in the cervical region in patients with papillary thyroid carcinoma (PTC).

Methods

This retrospective study included 2586 PTC patients. Potential risk factors were identified by univariate analysis, and the relationships between these factors and CLNM were ascertained by multivariable analysis. A scoring system was constructed, and the optimal cut-off value was determined.

Results

On univariate analysis, sex, age, tumor diameter, multifocality, capsule invasion, vascular invasion, total number of lymph nodes in the central region, and serum thyroid peroxidase antibody (TPOAb) concentration were identified as potential risk factors for CLNM in the cervical region, whereas nerve invasion, thyroid-stimulating hormone concentration, and thyroglobulin antibody (TgAb) concentration were not. Multivariable analysis indicated that male sex, young age, large tumor diameter, multifocality, vascular invasion, a large number of central lymph nodes, and a low TPOAb concentration were significant risk factors. From these factors, a preoperative CLNM risk assessment scale was constructed for predicting CLNM in the cervical region for PTC patients.

Conclusion

Male sex, young age, large tumor diameter, multifocality, vascular invasion, a large number of central lymph nodes, and a low TPOAb concentration were positively correlated with CLNM in the cervical region in PTC patients. The preoperative CLNM risk assessment scale based on these risk factors is expected to offer accurate preoperative assessment of central lymph node status in PTC patients.

The impact of thyroid tumor features on lymph node metastasis in papillary thyroid carcinoma patients in head and neck department at KAMC: A retrospective cross-sectional study

Papillary thyroid carcinoma (PTC) is the most prevalent type of thyroid cancer. It is one of the most common types of malignancy of the thyroid that spreads to cervical lymph nodes. Lymph node metastasis (LNM) is an important factor when determining recurrence risk, and determining the extent of lymph node involvement can guide treatment. Our main objective is to evaluate the association between the size of the tumor and the number of lymph node metastases in patients with PTC. Methods: We conducted an electronic retrospective chart review of 125 patients with PTC followed in the Head and Neck Department at KAMC from 2009 to 2020. Twenty-two patients included in our study were pathologically and clinically diagnosed and confirmed to have LNM of PTC. Results: The study included 22 PTC patients who had undergone lymph node dissections. Patients had a median age of 38.8 years (IQR = 32.2–54.5), and the median tumor size was 20.5 mm. The most commonly affected level of the neck was IV (76.2%). Distant metastasis M1 was seen in only two patients (9.1%). Tumors sizes >30mm (75%) had ≥5 LNM. Most cases were the classic subtype PTC. For the site of the tumor, the site had a significant impact on the number of LNM (p = 0.004). Multifocality had a high impact on LNM (p = 0.019). Conclusions: This study showed no association between the size of PTC and the number of LNMs. The bilaterality of PTC was significantly associated with a high number of LNMs.

•

Lymph nodes in level IV were the most common metastasis site for PTC.

•

Bilateral and multifocal PTC were significantly associated with a higher number of lymph nodes metastasis.

•

The size of the tumor was not significantly related to the number of lymph node metastasis.

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

Non-invasive assessment of the risk of lymph node metastasis (LNM) in patients with papillary thyroid carcinoma (PTC) is of great value for the treatment option selection. The purpose of this paper is to develop a transfer learning radiomics (TLR) model for preoperative prediction of LNM in PTC patients in a multicenter, cross-machine, multi-operator scenario. Here we report the TLR model produces a stable LNM prediction. In the experiments of cross-validation and independent testing of the main cohort according to diagnostic time, machine, and operator, the TLR achieves an average area under the curve (AUC) of 0.90. In the other two independent cohorts, TLR also achieves 0.93 AUC, and this performance is statistically better than the other three methods according to Delong test. Decision curve analysis also proves that the TLR model brings more benefit to PTC patients than other methods.

Prediction of Lymph Node Metastasis in Patients With Papillary Thyroid Carcinoma: A Radiomics Method Based on Preoperative Ultrasound Images

BACKGROUND

Papillary thyroid carcinoma is a type of indolent tumor with a dramatically increasing incidence rate and stably high survival rate. Reducing the overdiagnosis and overtreatment of papillary thyroid carcinoma is clinically emergent and important. A radiomics model is proposed in this article to predict lymph node metastasis, the most important risk factor of papillary thyroid carcinoma, based on noninvasive routine preoperative ultrasound images.

METHODS

Four hundred fifty ultrasound manually segmented images of patients with papillary thyroid carcinoma with lymph node status obtained from pathology report were enrolled in our retrospective study. A radiomics evaluation of 614 high-throughput features were calculated, including size, shape, margin, boundary, orientation, position, echo pattern, posterior acoustic pattern, and calcification features. Then, combined feature selection strategy was used to select features with the greatest ability to discriminate lymph node status. A support vector machine classifier was employed to build and validate the prediction model. Another independent testing cohort was used to further evaluate the performance of the radiomics model.

RESULTS

Among 614 radiomics features, 50 selected features most reflecting echo pattern, posterior acoustic pattern, and calcification showed the superior lymph node status distinguishable performance with area under the receiver operating characteristic curve of 0.753, 0.740, and 0.743 separately when using each type of features predicting the lymph node status. The results of model based on all 50 final features predicting the lymph node status shown an area under the receiver operating characteristic curve of 0.782, and accuracy of 0.712. In the independent testing cohort, the proposed approach showed similar results, with area under the receiver operating characteristic curve of 0.727 and accuracy of 0.710.

CONCLUSION

Papillary thyroid carcinoma with lymph node metastasis usually shows a complex echo pattern, posterior region homogeneity, and macrocalcification or multiple calcification. The radiomics model proposed in this article is a promising method for assessing the risk of papillary thyroid carcinoma metastasis noninvasively.

Associations between Hashimoto Thyroiditis and Clinical Outcomes of Papillary Thyroid Cancer: A Meta-Analysis of Observational Studies

BACKGROUND

Epidemiological studies have suggested an association between Hashimoto thyroiditis (HT) and papillary thyroid cancer (PTC) development. Other studies, however, have reported a protective role of HT against PTC progression. Through this updated meta-analysis, we aimed to clarify the effects of HT on the progression of PTC.

METHODS

We searched citation databases, including PubMed and Embase, for relevant studies from inception to September 2017. From these studies, we calculated the pooled odds ratios (ORs) of clinicopathologic features and the relative risk (RR) of PTC recurrence with 95% confidence intervals (CIs) using the Mantel-Haenszel method. Additionally, the Higgins I² statistic was used to test for heterogeneity.

RESULTS

The meta-analysis included 71 published studies with 44,034 participants, among whom 11,132 had HT. We observed negative associations between PTC with comorbid HT and extrathyroidal extension (OR, 0.74; 95% CI, 0.68 to 0.81), lymph node metastasis (OR, 0.82; 95% CI, 0.72 to 0.94), distant metastasis (OR, 0.49; 95% CI, 0.32 to 0.76), and recurrence (RR, 0.50; 95% CI, 0.41 to 0.61).

CONCLUSION

In this meta-analysis, PTC patients with HT appeared to exhibit more favorable clinicopathologic characteristics and a better prognosis than those without HT.

Comparison of the application of B-mode and strain elastography ultrasound in the estimation of lymph node metastasis of papillary thyroid carcinoma based on a radiomics approach

PURPOSE

B-mode ultrasound (B-US) and strain elastography ultrasound (SE-US) images have a potential to distinguish thyroid tumor with different lymph node (LN) status. The purpose of our study is to investigate whether the application of multi-modality images including B-US and SE-US can improve the discriminability of thyroid tumor with LN metastasis based on a radiomics approach.

METHODS

Ultrasound (US) images including B-US and SE-US images of 75 papillary thyroid carcinoma (PTC) cases were retrospectively collected. A radiomics approach was developed in this study to estimate LNs status of PTC patients. The approach included image segmentation, quantitative feature extraction, feature selection and classification. Three feature sets were extracted from B-US, SE-US, and multi-modality containing B-US and SE-US. They were used to evaluate the contribution of different modalities. A total of 684 radiomics features have been extracted in our study. We used sparse representation coefficient-based feature selection method with 10-bootstrap to reduce the dimension of feature sets. Support vector machine with leave-one-out cross-validation was used to build the model for estimating LN status.

RESULTS

Using features extracted from both B-US and SE-US, the radiomics-based model produced an area under the receiver operating characteristic curve (AUC) [Formula: see text] 0.90, accuracy (ACC) [Formula: see text] 0.85, sensitivity (SENS) [Formula: see text] 0.77 and specificity (SPEC) [Formula: see text] 0.88, which was better than using features extracted from B-US or SE-US separately.

CONCLUSIONS

Multi-modality images provided more information in radiomics study. Combining use of B-US and SE-US could improve the LN metastasis estimation accuracy for PTC patients.

Gender-Specific Risk of Central Compartment Lymph Node Metastasis in Papillary Thyroid Carcinoma

Our aim was to evaluate the impact of gender on the predictive factors of central compartment lymph node metastasis (CLNM) in papillary thyroid carcinoma (PTC). A retrospective study of 590 patients treated for PTC was performed. Univariate and multivariate analyses showed that gender (female; P = 0.001), age (≥45 y; P < 0.001), tumor size (>1 cm; P < 0.001), and multifocality (P = 0.004) were independent predictive factors of CLNM in PTC patients. Patients were divided into male group (n = 152) and female group (n = 438). Age (≥45 y; P = 0.001), T4 (P = 0.006) and multifocality (P = 0.024) were independent predictive risk factors of CLNM in male patients. As for female patients, age (≥45 y; P < 0.001), tumor size (>1 cm; P < 0.001), multifocality (P = 0.002), and microcalcification (P = 0.027) were independently correlated with CLNM. The sensitivity of the multivariate model for predicting CLNM in male patients was 64.9%, specificity was 82.9%, and area under the ROC curve (AUC) was 0.764. As for female patients, the sensitivity was 55.7%, specificity was 77.9%, and AUC was 0.73. This study showed that the predictive factors of CLNM indeed varied according to gender. To have a more accurate evaluation of CLNM, different predictive systems should be used for male and female patients.