Evaluation Of Nodes Research Articles

Lymph node assessment in cervical cancer: current approaches

Cervical cancer (CC) is the fourth most common neoplasia in women worldwide. Although early-stage CC is often curable, 40 to 50% of patients are diagnosed at a locally advanced stage. Metastatic disease accounts for the principal cause of death. Lymph node (LN) status is a major factor impacting treatment options and prognosis. Historically, CC was staged based only on clinical findings. However, in 2018, imaging modalities and/or pathological findings were included in the International Federation of Gynecology and Obstetrics (FIGO) staging classification. In the last decades, LN status assessment has evolved considerably. Full pelvic lymphadenectomy used to be the only way to determine LN status. Currently, several options exist: surgery with full lymphadenectomy, sentinel lymph node (SLN) biopsy or imaging modalities such as computed tomography (CT), magnetic resonance imaging (MRI) and positron emission tomography (PET). Regarding surgery, the SLN biopsy technique has become a standard procedure in cases of CC, with indocyanine green (ICG) being the preferred dye. Pelvic MRI is a valuable imaging technique modality for the evaluation of pelvic LNs. In locally advanced or in early-stage disease with suspicious LNs on CT scans or MRI, PET/CT is recommended for assessment of nodal and distant status. The best strategy for LN assessment remains a highly controversial topic in the literature. In this article, we aim to review and compare the advantages and limitations of each modality, i.e. imaging or surgical (lymphadenectomy or SLN biopsy) approaches.

An Intraoperative Ultrasound Evaluation of Axillary Lymph Nodes: Cassandra Predictive Models in Patients with Breast Cancer—A Multicentric Study

Background and Objectives: Axillary lymph node (ALN) staging is crucial for the management of invasive breast cancer (BC). Although various radiological investigations are available, ultrasound (US) is the preferred tool for evaluating ALNs. Despite its immediacy, widespread use, and good predictive value, US is limited by intra- and inter-operator variability. This study aims to evaluate US and Elastosonography Shear Wave (SW-ES) parameters for ALN staging to develop a predictive model, named the Cassandra score (CS), to improve the interpretation of findings and standardize staging. Materials and Methods: Sixty-three women diagnosed with BC and treated at two Italian hospitals were enrolled in the study. A total of 529 lymph nodes were surgically removed, underwent intraoperative US examination, and were individually sent for a final histological analysis. The study aimed to establish a direct correlation between eight US-SWES features (margins, vascularity, roundness index (RI), loss of hilum fat, cortical thickness, shear-wave elastography hardness (SWEH), peripheral infiltration (PI), and hypoechoic appearance) and the histological outcome (benign vs. malignant). Results: Several statistical models were compared. PI was strongly correlated with malignant ALNs. An ROC analysis for Model A revealed an impressive AUC of 0.978 (S.E. = 0.007, p < 0.001), while in Model B, the cut-offs of SWEH and RI were modified to minimize the risk of false negatives (AUC of 0.973, S.E. = 0.009, p < 0.001). Model C used the same cut-offs as Model B, but excluded SWEH from the formula, to make the Cassandra model usable even if the US machine does not have SW-ES capability (AUC of 0.940, S.E. = 0.015, p < 0.001). A two-tiered model was finally set up, leveraging the strong predictive capabilities of SWEH and RI. In the first tier, only SWES and RI were evaluated: a positive result was predicted if both hardness and roundness were present (SWES > 137 kPa and RI < 1.55), and conversely, a negative result was predicted if both were absent (SWES < 137 kPa and RI > 1.55). In the second tier, if there was a mix of the results (SWES > 137 kPa and RI > 1.55 or SWES < 137 kPa and RI < 1.55), the algorithm in Model B was applied. The model demonstrated an overall prediction accuracy of 90.2% in the training set, 87.5% in the validation set, and 88.9% across the entire dataset. The NPV was notably high at 99.2% in the validation set. This model was named the Cassandra score (CS) and is proposed for the clinical management of BC patients. Conclusion: CS is a simple, non-invasive, fast, and reliable method that showed a PPV of 99.1% in the malignancy prediction of ALNs, potentially being also well suited for young sonographers.

Hybrid secure routing and monitoring mechanisms in IoT-based wireless sensor networks using Egret-Harris optimization

ABSTRACT Security is the primary concern when creating security protocols for wireless sensor networks (WSN), which motivates many academics to find security solutions that effectively provide a few benefits, such as low consumption of electricity, flexible communication, and low cost. A few restrictions still remain, including the inability to exactly select the expected cluster, the sensor nodes’ constrained functionality, and their poor efficiency. Thus, Egret-Harris optimization for hybrid secure routing and monitoring mechanisms in IoT-based WSNs (EHO optimized routing protocol in WSN) was introduced in this research. The created EHO algorithm combines the search, fitness function, and hunting phase features from Harris hawks and egrets to determine the best solution among all practical solutions while ensuring safe data transfer from the cluster heads (CHs) to the Base station (BS). Specifically, the EHO-enabled clustering is applied to the suggested model to efficiently choose the ideal group of CHs. Additionally, the EHO algorithm assists in choosing the best possible routes with minimal distance and less delay for facilitating energy-efficient transmission. With 100 nodes analyzed, the suggested EHO-WSN approach without any attacks achieved 22 alive nodes, a delay of 0.10 ms, a normalized energy of 0.346J, and a throughput of 0.64 bps, respectively. Additionally, in the presence of a Sybil attack, the suggested EHO-WSN technique achieves 14, 0.214 J, 0.010 ms, and 0.512 bps for an analysis involving 100 nodes. Compared to previous methods, the suggested EHO-WSN model without attack achieves a delay of 0.07 ms, a throughput of 0.30 bps, an energy of 0.374 J, and 37 alive nodes for 200 node evaluation. For 200 nodes under examination, the EHO-WSN technique yields superior results of attaining 12 alive nodes, a delay of 0.072 ms, a throughput of 0.181 bps, and a normalized energy of 0.330 J even in the presence of the Sybil attack and exceeded other traditional techniques.

The role of frozen pathology in the evaluation of lymph nodes for endometrial intraepithelial neoplasia: A cost-effectiveness model

The role of frozen pathology in the evaluation of lymph nodes for endometrial intraepithelial neoplasia: A cost-effectiveness model

Trends in sentinel lymph node evaluation for vulvar melanoma over time: A National Cancer Database analysis

Trends in sentinel lymph node evaluation for vulvar melanoma over time: A National Cancer Database analysis

Lymph node evaluation for endometrial intraepithelial neoplasia: An analytic model

Lymph node evaluation for endometrial intraepithelial neoplasia: An analytic model

The value of postoperative contrast-enhanced ultrasound parameters in lymph node metastasis, tumor node metastasis, and treatment response evaluation of resected hepatocellular carcinoma.

To explore the application value of postoperative contrast-enhanced ultrasound (CEUS) parameters for lymph node metastasis (LNM), tumor, node, metastasis staging, and treatment response evaluation of resected hepatocellular carcinoma (HCC). We retrospectively analyzed 100 patients with liver cancer who underwent liver CEUS at our hospital between October 2020 and October 2022. The patient's LNM, pathological staging, and therapeutic effects were recorded based on the histopathological results. CEUS parameters were analyzed and compared CEUS parameters between different lymph node metastases, pathological stages, and therapeutic effects. Twenty-three patients experienced LNM, 77 patients did not experience LNM; and the rise time (RT), peak intensity (PI), and area under the curve (AUC) of the metastatic group were significantly smaller than those of the nonmetastatic group (P < .05). 44 cases were classified into groups I to II by pathological staging, and 56 cases were classified into groups III to IV. The RT, PI, and AUC of groups III to IV were significantly lower than those of groups I-II (P < .05). Seventy-nine cases were complete necrosis, 21 cases were residual or recurrent; The RT, PI, and AUC of the residual or recurrent group were significantly lower than those of the complete necrosis group (P < .05). The receiver operating characteristic curve shows that RT, PI, and AUC have a certain value in evaluating LNM, pathological staging, and treatment response of HCC, and the combined evaluation/evaluation value of these 3 factors is relatively high. The postoperative CEUS parameters RT, PI, and AUC can be used for LNM, pathological staging evaluation, and treatment response evaluation of HCC. Moreover, the combination of the 3 parameters is feasible and valuable in evaluating LNM, tumor, node, metastasis staging, and treatment response of HCC.

Research on the Robustness of Command and Control Networks under Cascading Failures

The current analysis of cascading failures in command and control networks pays little attention to their roles and mechanisms, resulting in challenges in quantifying survivability evaluation metrics and limiting practical application. To address these issues, this paper designs a command and control network model with a recovery strategy to improve the scientific evaluation of critical nodes and enhance the reliability of subsequent cascading failure simulations. Two capacity parameters are introduced to analyze the nonlinear behavior between network node load and capacity, and an optimal recovery strategy is proposed. This strategy prioritizes the recovery of critical nodes, thereby minimizing the overall probability of network failure. Simulations were conducted under both random failure and deliberate attack scenarios, comparing the proposed strategy with random recovery and betweenness-priority recovery strategies to identify the optimal recovery approach. The experiments showed that the optimal recovery strategy significantly enhanced the network’s survivability and recovery efficiency, allowing for the restoration of basic network functions in the shortest possible time and reducing the impact of cascading failures. By integrating the operability and uncertainty of real-world command and control networks, this method improved the network’s recovery capability and overall stability in the face of cascading failures through scientific evaluation and strategy optimization.

Upstaging of Invasive Lobular Cancer With FES PET/CT.

A 78-year-old woman diagnosed with left breast invasive lobular carcinoma with left axillary nodal metastasis underwent 18 F-fluoroestradiol (FES) PET/CT imaging for further evaluation of indeterminate right axillary lymph nodes seen on staging 18 F-FDG PET/CT. 18 F-FES PET/CT revealed abnormal 18 F-FES-avid right axillary and bilateral cervical nodes, subsequently biopsy-proven metastases, upstaging the patient from stage II to IV and greatly changing patient management. This case demonstrates the value of 18 F-FES PET/CT in accurately staging metastatic invasive lobular carcinoma at diagnosis, an indication for which 18 F-FES PET/CT "may be appropriate" per current Society of Nuclear Medicine and Molecular Imaging guidelines.

Should we prioritise proper surgical staging for patients with Atypical endometrial hyperplasia (AEH)? Experience from a single-institution tertiary care oncology centre

ObjectiveThe study aimed to evaluate the incidence of concurrent endometrial cancer (EC) and lymph node positivity in patients with Atypical Endometrial Hyperplasia (AEH) who underwent surgical staging with sentinel lymph node evaluation. It also sought to identify the risk factors associated with detecting concurrent endometrial cancer in patients with a preoperative diagnosis of AEH. Study designA retrospective study was conducted at Amrita Institute of Medical Sciences, involving 54 cases of AEH diagnosed on pre-operative biopsy specimens and undergoing staging surgery between January 1, 2015, and December 31, 2020. The study analysed demographic parameters, clinical presentations, pathological features, and clinical outcomes. Categorical variables were expressed in numbers and percentages, normal distribution data were presented as mean, and non-normal distribution data were presented as median and range. ResultsFifty-four patients diagnosed with AEH underwent surgical staging. The median age was 54 years. Final HistoPathology Report (HPR) showed 48.14 % with AEH and 51.85 % with concurrent EC. Among those with concurrent EC, 96.4 % had type I EC, and one patient was upgraded to type 2 EC. Among them, 17.8 % patients belonged to high-intermediate and high-risk categories. Patients with AEH and concurrent EC were more likely to be diabetic (OR: 3.56, p = 0.04), have a BMI ≥25 kg/m2 (OR: 1.47, p = 0.04), exhibit a thickened endometrial lining of ≥9 mm (OR: 3.13, p = 0.05) on ultrasound, and undergo preoperative biopsy at a non-oncology centre (OR: 8.33, p = 0.001) whereas experiencing heavy menstrual bleeding had a substantially lower likelihood (OR: 0.29, p = 0.01) of developing concurrent EC. ConclusionThe study revealed that more than half of patients undergoing staging surgery for AEH were found to be at risk of having concurrent EC in their final HPR. The research also pointed out that surgical staging can help identify both low-risk and high-risk ECs, which may require additional treatment. Higher BMI, diabetes mellitus, and an endometrial thickness of ≥9 mm were identified as significant risk factors for concurrent EC. Additionally, heavy menstrual bleeding was associated with a decreased risk of concurrent EC.

The association of preoperative radiotherapy and surgery for AJCC stage I-III rectal adenocarcinoma: a population-based study

BackgroundWith the increasing application of neoadjuvant therapy in rectal adenocarcinoma, there remain many controversies in clinical practical applications. Preoperative radiotherapy (PR) can limit the surgical plane and potentially affect the quality of surgical treatment. This study aimed to investigate the potential impact of PR on the surgical quality of rectal adenocarcinoma.MethodsThis retrospective study analyzed the clinicopathological data from 6,585 AJCC stage I-III rectal adenocarcinoma in the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2015. Kaplan-Meier survival analysis and multivariate Cox proportional were used to assess the impact of PR on survival. Propensity score matching (PSM) was employed to balance the baseline covariates between the PR and non-PR groups and to compare postoperative pathological differences.ResultsAfter PSM, PR did not improve overall survival (OS) in stages I (p = 0.33), II (p = 0.37), and III (p = 0.14) patients. Multivariate Cox analysis indicated that PR was not an independent prognostic factor for patients. Restricted cubic spline (RCS) analysis demonstrated a nonlinear negative correlation between OS hazard ratios and both circumferential resection margin (CRM) and lymph node evaluation (LNE). Compared to the non-PR group, patients in the PR group had lower tumor deposits (TD) (p < 0.001), positive CRM (p = 0.191), and perineural invasion (PNI) (p = 0.001).ConclusionPR is not an independent prognostic factor for rectal adenocarcinoma patients. However, PR can reduce the likelihood of TD, CRM, and PNI, thereby potentially influencing the quality of surgery.

How Many Lymph Nodes are Enough in Paratesticular Rhabdomyosarcoma?

BackgroundTreatment strategies for paratesticular rhabdomyosarcoma (PT RMS) are based on stage, which requires accurate lymph node (LN) evaluation. Previous methodology for determining quantity of LN for negative nodal status is based on LN positivity rates, without accounting for the relationship between LNs or amongst patients. This study aims to quantify the chance of missing involved LNs based on LN yield (LNY) using a previously established methodology in comparison to current recommendations. MethodsUsing the National Cancer Database, patients with a diagnosis of PT RMS were queried from 2004-2018. Patients >10 years and those ≤10 years with cN1 disease were included, based on COG guidelines for who should undergo retroperitoneal LN sampling (RPLNS). The beta-binomial model was used to calculate the rate of false negative RPLNS and identified the LNY threshold to reduce the risk of a missing an involved LN node to <10%. ResultsSixty-two patients were included for analysis over the study period. Median LNY was 17 (IQR 9-28.75), and the median number of involved LNs was 2.5 (IQR 2-5). The median LN density was 0.27 (IQR 0.10-0.34). Application of the beta-binomial model identified that a LNY of 26 LNs corresponds to a <10% chance of missing occult disease (Figure 3). ConclusionPrevious models estimate that sampling of 7-12 LN is adequate for accurate staging. However, the beta binomial model quantifies sampling at least 26 LNs to reduce the chance of missing occult metastatic disease to <10% in the majority of patients. Surgeons should consider this false negative rate during RPLNS for patients with PT RMS. Level of EvidenceIII

Evaluation of the clinical characteristics, laboratory parameters, and antibiotic treatment in patients diagnosed with tularemia

IntroductionThis retrospective, cross-sectional, multi-center study aimed to evaluate the impact of laboratory results and treatments on the treatment response in patients diagnosed with tularemia. MethodsThe study included 190 adult patients diagnosed with tularemia between November 2023 and June 2024. Results67.9 % were female, mean age was 45.8 ± 14.9 years. The most frequently detected symptoms were sore throat (74.2 %), fatigue (71.6 %), and neck swelling (56.3 %). The most common form of tularemia was oropharyngeal (82.6 %) and glandular (14.2 %). The most used monotherapy was ciprofloxacin (80.5 %, n = 136), and combination therapy was streptomycin-ciprofloxacin (81.0 %, n = 17). Treatment failure was observed in 29 patients (15.2 %). No difference was found between patients who responded and didn't respond to treatment regarding laboratory parameters. Lymph node drainage or excision was performed in 47 patients (23 %). Suppurative lymphadenitis, abscess, necrosis, and conglomerate lymphadenopathy were more common in the lymph node drainage group. Reactive lymph nodes were more common in the group without lymph node drainage. There was no difference between the two groups regarding laboratory parameters of patients with and without lymph node drainage. The duration of antibiotic treatment was longer in patients who underwent lymph node drainage than in those who didn't. ConclusionRadiological evaluation of lymph nodes upon hospital admission, in addition to antibiotic therapy during treatment, may help predict which patients are more likely to require surgical drainage. Laboratory parameters may not provide significant benefits in predicting the need for lymph node drainage and long-term treatment did not affect the treatment response.

EP.07B.09 Lymph Node Evaluation for Stage Cia Non-Small Cell Lung Cancer: Findings from a Single Institution

EP.07B.09 Lymph Node Evaluation for Stage Cia Non-Small Cell Lung Cancer: Findings from a Single Institution

Fertility-sparing treatment with conization versus radical hysterectomy in patients with early-stage cervical cancer: inverse propensity score weighted analysis

ObjectiveTo report 20 years of experience with fertility-sparing surgery for patients with early-stage cervical cancer, comparing the oncological outcomes with outcomes for those who underwent a radical hysterectomy.MethodsPatients with pre-operative...

Lymph node evaluation and nodal metastasis prediction in epithelial ovarian cancers: A retrospective study.

To identify consensus regarding lymph node (LN) evaluation in epithelial ovarian cancer (EOC). The objective of the present study was to evaluate surgico-pathological findings, LN involvement, and the prediction of LN metastasis via preoperative imaging and intraoperative assessment in women with EOC. Women with EOC who underwent cytoreductive surgery (CRS) between Jan 2019 to June 2022 were included. The distribution of histology, stage, and LN metastasis was studied. The predictive value of serum cancer antigen (CA)-125, instead of and radiologically and surgically enlarged LNs with final LN histopathology was studied. A total of 96 women with EOCs underwent CRS. Fifty women (52%) underwent primary CRS and 46 women (48%) underwent interval CRS. Seventy-five women (78.13%) with EOC underwent pelvic and/or para-aortic lymphadenectomy, out of which 23 (30.67%) were histologically positive. High-grade serous carcinoma was the commonest (n=55, 73.33%) histology. The majority of women, 56 (74.67%) were stage III or IV at presentation. Complete cytoreduction was achieved in 59 (78.66%) patients. The receiver operating characteristics curve showed a cutoff for CA-125 of 1360 U/mL (area under the curve 0.702, p=0.002) for LN metastases. Both radiologically and surgically enlarged LNs significantly predicted LN metastasis on histopathology (p=0.02 and 0.006 respectively). The combined sensitivity, specificity, positive predictive value and negative predictive value of both contrast enhanced computed tomography (CECT) and surgically enlarged LNs were 78.26%, 57.69%, 45%, and 85.71%, respectively. Serous histology, high-grade tumors, highCA-125 levels, and suspicious LNs on CECT or during surgery were significantly associated with LN metastasis. However, considering the false-negative rate of 21.74%, the combination of radiologically and surgically enlarged LNs cannot be used as the sole surrogate marker for lymphadenectomy.

Multiregional dynamic contrast-enhanced MRI-based integrated system for predicting pathological complete response of axillary lymph node to neoadjuvant chemotherapy in breast cancer: multicentre study

The accurate evaluation of axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) in breast cancer holds great value. This study aimed to develop an artificial intelligence system utilising multiregional dynamic contrast-enhanced MRI (DCE-MRI) and clinicopathological characteristics to predict axillary pathological complete response (pCR) after NAC in breast cancer. This study included retrospective and prospective datasets from six medical centres in China between May 2018 and December 2023. A fully automated integrated system based on deep learning (FAIS-DL) was built to perform tumour and ALN segmentation and axillary pCR prediction sequentially. The predictive performance of FAIS-DL was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. RNA sequencing analysis were conducted on 45 patients to explore the biological basis of FAIS-DL. 1145 patients (mean age, 50 years±10 [SD]) were evaluated. Among these patients, 506 were in the training and validation sets (axillary pCR rate of 40.3%), 127 in the internal test set (axillary pCR rate of 37.8%), 414 in the pooled external test set (axillary pCR rate of 48.8%), and 98 in the prospective test set (axillary pCR rate of 43.9%). For predicting axillary pCR, FAIS-DL achieved AUCs of 0.95, 0.93, and 0.94 in the internal test set, pooled external test set, and prospective test set, respectively, which were also significantly higher than those of the clinical model and deep learning models based on single-regional DCE-MRI (all P<0.05, DeLong test). In the pooled external and prospective test sets, the FAIS-DL decreased the unnecessary axillary lymph node dissection rate from 47.9% to 6.8%, and increased the benefit rate from 52.2% to 86.5%. RNA sequencing analysis revealed that high FAIS-DL scores were associated with the upregulation of immune-mediated genes and pathways. FAIS-DL has demonstrated satisfactory performance in predicting axillary pCR, which may guide the formulation of personalised treatment regimens for patients with breast cancer in clinical practice. This study was supported by the National Natural Science Foundation of China (82371933), National Natural Science Foundation of Shandong Province of China (ZR2021MH120), Mount Taishan Scholars and Young Experts Program (tsqn202211378), Key Projects of China Medicine Education Association (2022KTM030), China Postdoctoral Science Foundation (314730), and Beijing Postdoctoral Research Foundation (2023-zz-012).

ROS-mediated ITGB5 promotes tongue squamous cell carcinoma metastasis through epithelial mesenchymal transition and cell adhesion signal pathway

PurposeIntegrin β5 (ITGB5) is an integrin β subunit member widely expressed in the human bodies, especially in cancer cells and tissues, which is a key factor in promoting tumor metastasis. In this study we investigated the differential expression of ITGB5 in tongue squamous cell carcinoma (TSCC), especially in those with lymph node metastasis, and revealed the possible mechanism.MethodsThe expression of ITGB5 in TSCC was analyzed by database and verified by immunohistochemistry through 135 TSCC patients’ tissue sections from Sun Yat-sen Memorial Hospital and Guangzhou First People’s Hospital. The relationship between ITGB5 and lymph node metastasis or prognosis was analyzed retrospectively. The effects of ITGB5 on TSCC cells were examined through knocking down or overexpression and its possible regulator and signal pathway were explored.ResultsThe expression of ITGB5 in TSCC was higher than that in adjacent tissue, and the expression in patients with lymph node metastasis was higher than that in patients without lymph node metastasis. The high expression of ITGB5 predicted a worse prognosis. Knock down of ITGB5 suppressed invasion and migration of TSCC cells, while overexpression of ITGB5 contributed to invasion and migration. Reactive oxygen species (ROS) regulated epithelial mesenchymal transition (EMT), and we further verified that ROS enhanced the expression of ITGB5 to promote the metastasis of TSCC. Mechanistically, ITGB5 functions through cell adhesion signal pathway.ConclusionThe increased expression of ITGB5 in tongue squamous cell carcinoma with lymph node metastasis may be a potential target for evaluating lymph node metastasis and worse prognosis of tongue squamous cell carcinoma. Scavenge of ROS or knock down of ITGB5 may be the strategies to overcome metastasis of TSCC.

Stage IC grade 1 endometrioid adenocarcinoma of the ovary: assessment of post-operative chemotherapy de-escalation

ObjectiveGiven limited real-world practice data evaluating the National Comprehensive Cancer Network clinical practice guidelines for possible post-operative chemotherapy omission as a treatment option for patients with stage IC grade 1...

Development of a multi-modal learning-based lymph node metastasis prediction model for lung cancer

PurposeThis study proposed a three-dimensional (3D) multi-modal learning-based model for the automated prediction and classification of lymph node metastasis in patients with non-small cell lung cancer (NSCLC) using computed tomography (CT) images and clinical information. MethodsWe utilized clinical information and CT image data from 4239 patients with NSCLC across multiple institutions. Four deep learning algorithm-based multi-modal models were constructed and evaluated for lymph node classification. To further enhance classification performance, a soft-voting ensemble technique was applied to integrate the outcomes of multiple multi-modal models. ResultsA comparison of the classification performance revealed that the multi-modal model, which integrated CT images and clinical information, outperformed the single-modal models. Among the four multi-modal models, the Xception model demonstrated the highest classification performance, with an area under the curve (AUC) of 0.756 for the internal test dataset and 0.736 for the external validation dataset. The ensemble model (SEResNet50_DenseNet121_Xception) exhibited even better performance, with an AUC of 0.762 for the internal test dataset and 0.751 for the external validation dataset, surpassing the multi-modal model's performance. ConclusionsIntegrating CT images and clinical information improved the performance of the lymph node metastasis prediction models in patients with NSCLC. The proposed 3D multi-modal lymph node prediction model can serve as an auxiliary tool for evaluating lymph node metastasis in patients with non-pretreated NSCLC, aiding in patient screening and treatment planning.