Assessment Of Lymph Node Metastasis Research Articles

Diagnostic performance of diffusion-weighted magnetic resonance imaging in assessing lymph node metastasis of esophageal cancer compared with PET

BackgroundAlthough diffusion-weighted magnetic resonance imaging (DWI) for detecting lymph node (LN) metastasis is reported to be a successful modality for primary malignant tumors, there are few studies relating to esophageal cancer. This study aimed to clarify the diagnostic performance of DWI for assessing LN metastasis compared with positron emission tomography (PET) in patients with esophageal squamous cell cancer (eSCC).MethodsSeventy-six patients with histologically proven eSCC who underwent curative esophagectomy without neoadjuvant treatment were reviewed retrospectively. Harvested LNs were divided into 1229 node stations with 94 metastases. Diagnostic abilities and prognostic significance were compared.ResultsIn a station-by-station evaluation, the sensitivity was higher in DWI than PET (67% vs. 32%, P < 0.001). DWI showed more than 80% sensitivity for middle- and large-sized cancer nests and large area of cancer nests. The DWI-N0 group had a better 5-year relapse-free survival rate than the DWI-N+ group (78.5% vs. 34.2%, P < 0.001), as did the PET-N0 group. DWI-N status was an independent prognostic factor (hazard ratio [HR], 2.642; P = 0.048), as was PET-N status (HR 2.481; P = 0.033).ConclusionsDWI, which depends on cancer cell volume followed by elevated intranodal density, is a non-invasive modality and showed higher sensitivity than PET. It has clinical impact in predicting postoperative survival for patients with eSCC alongside its diagnostic ability and has significant performance in clinical practice.

Preoperative Risk Assessment of Lymph Node Metastasis in cT1 Lung Cancer: A Retrospective Study from Eastern China.

Background Lymph node status of clinical T1 (diameter ≤ 3 cm) lung cancer largely affects the treatment strategies in the clinic. In order to assess lymph node status before operation, we aim to develop a noninvasive predictive model using preoperative clinical information. Methods We retrospectively reviewed 924 patients (development group) and 380 patients (validation group) of clinical T1 lung cancer. Univariate analysis followed by polytomous logistic regression was performed to estimate different risk factors of lymph node metastasis between N1 and N2 diseases. A predictive model of N2 metastasis was established with dichotomous logistic regression, externally validated and compared with previous models. Results Consolidation size and clinical N stage based on CT were two common independent risk factors for both N1 and N2 metastases, with different odds ratios. For N2 metastasis, we identified five independent predictors by dichotomous logistic regression: peripheral location, larger consolidation size, lymph node enlargement on CT, no smoking history, and higher levels of serum CEA. The model showed good calibration and discrimination ability in the development data, with the reasonable Hosmer-Lemeshow test (p = 0.839) and the area under the ROC being 0.931 (95% CI: 0.906-0.955). When externally validated, the model showed a great negative predictive value of 97.6% and the AUC of our model was better than other models. Conclusion In this study, we analyzed risk factors for both N1 and N2 metastases and built a predictive model to evaluate possibilities of N2 metastasis of clinical T1 lung cancers before the surgery. Our model will help to select patients with low probability of N2 metastasis and assist in clinical decision to further management.

Deep-UV excitation fluorescence microscopy for detection of lymph node metastasis using deep neural network

Deep-UV (DUV) excitation fluorescence microscopy has potential to provide rapid diagnosis with simple technique comparing to conventional histopathology based on hematoxylin and eosin (H&E) staining. We established a fluorescent staining protocol for DUV excitation fluorescence imaging that has enabled clear discrimination of nucleoplasm, nucleolus, and cytoplasm. Fluorescence images of metastasis-positive/-negative lymph nodes of gastric cancer patients were used for patch-based training with a deep neural network (DNN) based on Inception-v3 architecture. The performance on small patches of the fluorescence images was comparable with that of H&E images. Gradient-weighted class activation mapping analysis revealed the areas where the trained model identified metastatic lesions in the images containing cancer cells. We extended the method to large-size image analysis enabling accurate detection of metastatic lesions. We discuss usefulness of DUV excitation fluorescence imaging with the aid of DNN analysis, which is promising for assisting pathologists in assessment of lymph node metastasis.

Multiplanar MRI-Based Predictive Model for Preoperative Assessment of Lymph Node Metastasis in Endometrial Cancer.

Introduction: Assessment of lymph node metastasis (LNM) is crucial for treatment decision and prognosis prediction for endometrial cancer (EC). However, the sensitivity of the routinely used magnetic resonance imaging (MRI) is low in assessing normal-sized LNM (diameter, 0–0.8 cm). We aimed to develop a predictive model based on magnetic resonance (MR) images and clinical parameters to predict LNM in normal-sized lymph nodes (LNs).Materials and Methods: A total of 200 retrospective patients were enrolled and divided into a training cohort (n = 140) and a test cohort (n = 60). All patients underwent preoperative MRI and had pathological result of LNM status. In total, 4,179 radiomic features were extracted. Four models including a clinical model, a radiomic model, and two combined models were built. Area under the receiver operating characteristic (ROC) curves (AUC) and calibration curves were used to assess these models. Subgroup analysis was performed according to LN size. All patients underwent surgical staging and had pathological results.Results: All of the four models showed predictive ability in LNM. One of the combined models, ModelCR1, consisting of radiomic features, LN size, and cancer antigen 125, showed the best discrimination ability on the training cohort [AUC, 0.892; 95% confidence interval [CI], 0.834–0.951] and test cohort (AUC, 0.883; 95% CI, 0.786–0.980). The subgroup analysis showed that this model also indicated good predictive ability in normal-sized LNs (0.3–0.8 cm group, accuracy = 0.846; <0.3 cm group, accuracy = 0.849). Furthermore, compared with the routinely preoperative MR report, the sensitivity and accuracy of this model had a great improvement.Conclusions: A predictive model was proposed based on MR radiomic features and clinical parameters for LNM in EC. The model had a good discrimination ability, especially for normal-sized LNs.

Preoperative assessment of lymph node metastasis in clinically node-negative rectal cancer patients based on a nomogram consisting of five clinical factors.

Currently, reliable approaches for accurate assessment of lymph node metastases (LNM), which is an important indication of preoperative chemoradiotherapy (CRT), are not available for clinically node-negative rectal cancer patients. This study aims to identify clinical factors associated with LNM and to establish a nomogram for LNM prediction in clinically node-negative rectal cancer patients. The least absolute shrinkage and selection operator (LASSO) aggression and multivariate logistic regression analyses were applied to identify clinical factors associated with LNM. A nomogram was established to predict the probability of LNM in clinically node-negative rectal cancer patients based on the multivariate logistic regression model. Six potential risk factors were selected on the basis of LASSO aggression analysis, and five of them were identified as independent risk factors for LNM based on multivariate analysis, including MRI-reported tumor location, clinical T classification, MRI-reported tumor diameter, white blood cell count (WBC), and preoperative elevated tumor markers. A nomogram consisting of the five clinical factors was established and showed good discrimination. Decision curve analysis demonstrated that the established nomogram was reliable and accurate for LNM prediction in clinically node-negative rectal cancer patients. A nomogram based on five clinical factors, including MRI-reported tumor location, clinical T classification, MRI-reported tumor diameter, WBC, and preoperative elevated tumor markers, are useful for assessing LNM in clinically node-negative rectal cancer patients, which is important for preoperative CRT regimens.

Comparison of integrated PET/MRI with PET/CT in evaluation of endometrial cancer: a retrospective analysis of 81 cases.

BackgroundThe objective of this study was to compare the diagnostic value of integrated PET/MRI with PET/CT for assessment of regional lymph node metastasis and deep myometrial invasion detection of endometrial cancer.MethodsEighty-one patients with biopsy-proven endometrial cancer underwent preoperative PET/CT (n = 37) and integrated PET/MRI (n = 44) for initial staging. The diagnostic performance of PET/CT and integrated PET/MRI for assessing the extent of the primary tumor and metastasis to the regional lymph nodes was evaluated by two experienced readers. Histopathological and follow-up imaging results were used as the gold standard. McNemar’s test was employed for statistical analysis.ResultsIntegrated PET/MRI and PET/CT both detected 100% of the primary tumors. Integrated PET/MRI proved significantly more sensitivity and specificity than PET/CT in regional lymph node metastasis detection (P = 0.015 and P < 0.001, respectively). The overall accuracy of myometrial invasion detection for PET/CT and Integrated PET/MRI was 45.9% and 81.8%, respectively. Integrated PET/MRI proved significantly more accurate than PET/CT (P < 0.001).ConclusionIntegrated PET/MRI, which complements the individual advantages of MRI and PET, is a valuable technique for the assessment of the lymph node metastasis and myometrial invasion in patients with endometrial cancer.

Diagnostic accuracy of imaging studies for initial staging of T2b to T4b melanoma patients: A cross-sectional study

There is no consensus on the imaging tests that should be performed at the initial staging of melanoma patients. To evaluate the diagnostic accuracy of 4 imaging studies for the initial staging of melanoma patients. Cross-sectional study with prospectively collected data, from January 2011 to April 2017, including patients with clinical stage T2b to T4b according to 2009 American Joint Committee on Cancer, without evidence of metastasis. Initial staging of 308 patients detected 16.6% of metastases and 5.8% false-positive results, overall. Regional lymph node ultrasonography showed a metastasis detection rate (MDR) of 12.8%, false-positive rate of 0.8%, and accuracy of 96.0%. Computed tomography (CT) and positron emission tomography-CT had the highest detection rates at stage T4b: MDR, 13.3%; false-positive rate, 8.9%; accuracy, 91.1%; and MDR, 6.9%; false-positive rate, 0%; and accuracy, 93.1%, respectively. Brain magnetic resonance imaging showed a MDR of 2.0% in T4b. Single-center study. Performing ultrasound scans for assessing lymph node metastasis in patients with American Joint Committee on Cancer T2b stage and above is advisable. In patients with stage T4b, CT or positron emission tomography-CT are suitable for the detection of metastasis. Brain magnetic resonance imaging at T4b deserves further discussion, considering the ultimate clinical benefit in management and therapeutic options for asymptomatic patients.

A Scoring System for Prediction of Cervical Lymph Node Metastasis in Patients with Head and Neck Squamous Cell Carcinoma.

An accurate and comprehensive assessment of lymph node metastasis in patients with head and neck squamous cell cancer is crucial in daily practice. This study constructed a predictive model with a risk scoring system based on CT characteristics of lymph nodes and tumors for patients with head and neck squamous cell carcinoma to stratify the risk of lymph node metastasis. Data included 476 cervical lymph nodes from 191 patients with head and neck squamous cell carcinoma from a historical cohort. We analyzed preoperative CT images of lymph nodes, including diameter, ratio of long-to-short axis diameter, necrosis, conglomeration, infiltration to adjacent soft tissue, laterality and T-stage of the primary tumor. The reference standard comprised pathologic results. Multivariable logistic regression analysis was performed to develop the risk scoring system. Internal validation was performed with 1000-iteration bootstrapping. Shortest axial diameter, ratio of long-to-short axis diameter, necrosis, and T-stage were used to develop a 9-point risk scoring system. The risk of malignancy ranged from 7.3% to 99.8%, which was positively associated with increased scores. Areas under the curve of the risk scoring systems were 0.886 (95% CI, 0.881-0.920) and 0.879 (95% CI, 0.845-0.914) in internal validation. The Hosmer-Lemeshow goodness-of-fit test indicated that the risk scoring system was well-calibrated (P = .160). We developed a comprehensive and simple risk scoring system using CT characteristics in patients with head and neck squamous cell carcinoma to stratify the risk of lymph node metastasis. It could facilitate decision-making in daily practice.

Diagnostic Accuracy of Preoperative Diagnostic Procedure in the Assessment of Lymph Node Metastases by NF-PanNENs

Diagnostic Accuracy of Preoperative Diagnostic Procedure in the Assessment of Lymph Node Metastases by NF-PanNENs

Radiomic nomogram for prediction of axillary lymph node metastasis in breast cancer.

To develop a radiomic nomogram for preoperative prediction of axillary lymph node (LN) metastasis in breast cancer patients. Preoperative magnetic resonance imaging data from 411 breast cancer patients was studied. Patients were assigned to either a training cohort (n = 279) or a validation cohort (n = 132). Eight hundred eight radiomic features were extracted from the first phase of T1-DCE images. A support vector machine was used to develop a radiomic signature, and logistic regression was used to develop a nomogram. The radiomic signature based on 12 LN status-related features was constructed to predict LN metastasis, its prediction ability was moderate, with an area under the curve (AUC) of 0.76 and 0.78 in training and validation cohorts, respectively. Based on a radiomic signature and clinical features, a nomogram was developed and showed excellent predictive ability for LN metastasis (AUC 0.84 and 0.87 in training and validation sets, respectively). Another radiomic signature was constructed to distinguish the number of metastatic LNs (less than 2 positive nodes/more than 2 positive nodes), which also showed moderate performance (AUC 0.79). We developed a nomogram and a radiomic signature that can be used to identify LN metastasis and distinguish the number of metastatic LNs (less than 2 positive nodes/more than 2 positive nodes). Both nomogram and radiomic signature can be used as tools to assist clinicians in assessing LN metastasis in breast cancer patients. • ALNM is an important factor affecting breast cancer patients' treatment and prognosis. • Traditional imaging examinations have limited value for evaluating axillary LNs status. • We developed a radiomic nomogram based on MR imagings to predict LN metastasis.

Suboptimal Sensitivity and Specificity of PET and Other Gross Imaging Techniques in Assessing Lymph Node Metastasis.

Suboptimal Sensitivity and Specificity of PET and Other Gross Imaging Techniques in Assessing Lymph Node Metastasis.

Siewert type I and II oesophageal adenocarcinoma: sensitivity/specificity of computed tomography, positron emission tomography and endoscopic ultrasound for assessment of lymph node metastases in groups of thoracic and abdominal lymph node stations.

In Siewert type I/II oesophageal adenocarcinoma, the sensitivity and specificity of computed tomography (CT), positron emission tomography (PET)-CT and endoscopic ultrasound (EUS) for assessment of the N descriptor in defined groups of lymph nodes were investigated. CT, PET/CT, EUS images and the pathological data of 101 oesophageal adenocarcinomas submitted to primary resection were compared. The lymph nodes were identified as (a) right paratracheal/subcarinal/pulmonary ligament; (b) paraoesophageal; (c) paracardial; (d) left gastric artery, lesser curvature; (e) coeliac trunk, hepatic/splenic artery. Of the 2451 lymph nodes identified, 273 (11.1%) were histologically positive. Overall sensitivity, specificity and negative and positive predictive value for detection of lymph nodes metastatic were respectively: CT sensitivity 39%, specificity 86%, negative 58% and positive 74% predictive value; PET/CT sensitivity 30%, specificity 98%, negative 58% and positive 93% predictive value; EUS sensitivity 50%, specificity 81%, negative 72% and positive 62% predictive value. The sensitivity of CT, PET/CT and EUS in the thoracic nodal groups (a) and (b) was, respectively, 58.3%, 7.1% and 87.5% and 33.3%, 20% and 80%. Sensitivity was below 47% for all tests in the abdominal nodal groups. In contrast, specificity (88.6-100%) was super imposable in all nodal groups. The strength of agreement among the 3 imaging techniques was poor (kappa < 0.30) for the thoracic anatomical groups of interest: (a) lower paratracheal/subcarinal/pulmonary ligament and (b) paraoesophageal; it was moderate/good (kappa >0.30) for the abdominal N groups of interest: c, d and e. The diagnostic performance of CT, PET and EUS for assessing the N descriptor in the paracardial and abdominal stations close to the primary tumour is not satisfactory. EUS can efficiently assess the presence/absence of nodal metastases in the thoracic stations. ClinicalTrials.gov number: NCT03529968.

OC08.02: A preoperative risk model with ultrasound variables to assess lymph node metastasis in endometrial cancer patients: a model development and validation study by the IETA group

OC08.02: A preoperative risk model with ultrasound variables to assess lymph node metastasis in endometrial cancer patients: a model development and validation study by the IETA group

Research status of indication of endoscopic treatment of early gastric cancer

Early gastric cancer(EGC) that has a better prognosis is superficial in the depth and low in the rate of lymph node metastasis. A standard treatment of gastrectomy and lymph node resection can radically remove EGC, however, it inflicts a greater trauma on patients, and has a greater impact on postoperative quality of life. Compared with surgery, endoscopic resection(ER) approaches a similar outcome and thus becomes a new research hotspot. However, accurate assessment of lymph node metastasis before procedure and indication of ER is crucial to the safety of treatment. This article will give an overview of current research status of indication of endoscopic treatment. Key words: Stomach neoplasms; Lymph nodes; Review; Endoscopic submucosal dissection; Indication

Risk assessment of lymph node metastases in early gastric adenocarcinoma fulfilling expanded endoscopic resection criteria

Early gastric cancer (EGC) is known to present a low rate of lymph node metastases (LNMs). Gastrectomy with D2 lymphadenectomy is usually curative for EGC. Endoscopic submucosal dissection (ESD) is a well-accepted treatment modality for lesions that meet the classic criteria: those mucosal differentiated adenocarcinoma measuring 20mm or less, without ulceration. Expanded criteria for ESD have been proposed based on a null LNM rate from large gastrectomy series from Japan. Patients with LNM have been reported in Western centers, heightening the need for validation of expanded criteria. Our aim was to assess the risk of LNM in gastrectomy specimens of patients with EGC who met the expanded criteria for ESD. We conducted an evaluation of gastrectomy specimens including LNM staging of patients submitted to gastrectomy for EGC in a 39-year retrospective cohort. A total of 389 surgical specimens were included. From them, 135 fulfilled criteria for endoscopic resection. None of the 31 patients with classic criteria had LNM. From the 104 patients with expanded criteria, 3 had LNM (n= 104 [2.9%], 95% confidence interval, .7%-8.6%), all of them with undifferentiated tumors without ulceration, measuring less than 20mm. There is a small risk of LNM in EGC when expanded criteria for ESD are met. Refinement of the expanded criteria for the risk of LNM may be desirable in a Brazilian cohort. Meanwhile, the decision to complement the endoscopic treatment with gastrectomy will have to take into consideration the individual risk of perioperative morbidity and mortality.

IMAGING TECHNIQUES FOR THE DETECTION OF LYMPH NODE METASTASIS IN PATIENTS WITH LARYNGEAL ANF HYPOPHARYNGEAL CANCER

The purposeof the study was a systematic literature review of imaging assessment of lymph node metastasis in patients with laryngeal and hypopharyngeal cancer.Material and methods.In order to review the most relevant scientific literature available, we searched Elibrary, Medline databases (from January 2005 to December 2017). Of 735 identified studies, 32 were assessed.Results. The role of ultrasonography, spiral computer tomography, magnetic resonance tomography, positron emission tomography in the assessment of regional metastatic spread in patients with laryngeal and hypopharyngeal cancer was analyzed. All these imaging techniques failed to reliably identify clinically occult lymph node metastases. However, the choice of treatment options for laryngeal and hypopharyngeal cancer depends considerably on the diagnostic accuracy. In this context, the concept of sentinel lymph nodes deserves special attention.Conclusion.Further studies of the sentinel lymph node concept using various radiopharmaceutical drugs in the detection of preclinical regional metastasis in patients with laryngeal and hypopharyngeal cancer are required.

The impact of complete embedding of remaining tissue in gynecological lymph node dissection specimen in surgical pathology on lymph node yield: is it clinically relevant?

The assessment of nodal metastases in gynecological surgical specimen is an important staging parameter, directing further therapeutic procedures. Since the number of lymph nodes (LNs) removed is seen as an indicator of surgical and pathological quality, the demand for higher lymph node (LN) counts is raising. The goal of this prospective study was the comparison between lymph node counts of macroscopically detectable LNs and the LN yield by complete embedding and proceeding of all submitted LN-containing tissue in the pathology laboratory. One hundred six cases of cervical, uterine, or ovarian cancer, treated in three different hospitals within 3years, were analyzed. All tissue submitted to the pathology from the surgically performed LN dissections was completely dissected and embedded in the institute of pathology. Subsequently, the amount of LN of all macroscopically detectable nodes was compared to the final histologically reached numbers of LN. Furthermore the histologically visible area of the LNs and their metastases was analyzed to assess the relation of LN numbers to the whole examined LN area. Complete embedding raises the average number of LN counted by 3 to 7 but did only minimally increase the LN area for microscopical examination by about 5% due to the small area of the additional LNs in the remaining fat tissue. The staging was in no case altered by complete embedding, even when additional nodal metastases were detected in the remaining fat tissue, since this was only seen in cases which had already metastatic nodes. Complete embedding of LN-containing tissue did not provide relevant additional staging information and seems therefore unnecessarily laborious, careful pathological work-up assumed.

Predictive Factors of Lymph Node Metastasis in Follicular Variant of Papillary Thyroid Carcinoma.

Compared with conventional papillary thyroid carcinoma (PTC), follicular variant of PTC (FV-PTC) shows less aggressive behavior and better prognosis. Nonetheless, regional lymph node (LN) metastasis was found in 22.8% of FV-PTC patients. Because LN metastasis is a proven predictor of recurrence in PTC, it is important to assess LN metastasis in FV-PTC patients. We retrospectively reviewed 134 FV-PTC patients who underwent thyroidectomy with neck dissection. Central LN metastasis (CLNM) and lateral LN metastasis (LLNM) were found in 50 (37.3%) and 16 (11.9%) patients, respectively. In the multivariate analysis for CLNM, male sex (adjusted OR 4.735, p=0.001), nonencapsulated form (adjusted OR 2.863, p=0.022), and tumor size>1.0cm (adjusted OR 3.157, p=0.008) were independent predictors of high prevalence of CLNM in FV-PTC patients. In the multivariate analysis for LLNM, microscopic extrathyroidal extension (ETE) (adjusted OR 3.939, p=0.041) and CLNM (adjusted OR 13.340, p=0.001) were independent predictors of high prevalence of LLNM in FV-PTC patients. Meticulous perioperative evaluation and prophylactic central neck dissection may be beneficial for FV-PTC patients with male sex, nonencapsulated form, and tumor size>1.0cm. Moreover, cautious perioperative evaluation of lateral neck LN may be mandatory for FV-PTC patients with microscopic ETE and CLNM.

THE CRITERIA FOR LYMPH NODE METASTATIC DISEASE IN UTERINE CERVIX CANCER PATIENTS BASED ON MRI FINDINGS

Introduction. The state of pelvic and retroperitoneal lymph nodes is an important prognostic factor for cervical cancer. Lymph node size is the most widely used CT and MR criteria for assessing lymph node status. Lymph nodes measuring more than 1cm in the short axis diameter are considered malignant. However this criterion (nodal size) is not foolproof because of a high percentage of diagnostic errors. The purpose of the study was to develop objective MRI criteria for assessing lymph node metastasis in patients with cervical cancer by measuring the short- and the long-axis diameters of lymph nodes, short axis/long axis ratio (configuration index) and to evaluate their diagnostic value. Materials and methods. The prospective study included 31 patients with histologically confirmed cervical cancer, who underwent radical surgery with standard lymph node dissection. Sixty removed lymph nodes were evaluated. MRI examinations were performed using a 1.5 T scanner in T2- weighted images (T2-WI), T1-WI and T2 weighted sequences with fatty tissue signal suppressing and diffusionweighted MRI. Results. Lymph nodes measuring ≥0.8 cm in the short axis diameter were considered suspicious for metastatic disease. The sensitivity and specificity with a cutoff of ≥0.8cm were 68 % (CI 48.3‑82.9) and 80 % (CI 63.8‑90.3), respectively; the positive and negative predictive values were 71 % and 78 %, respectively; and the accuracy was 75 % (CI 62.7‑84.3). The short axis/long axis ratio (configuration index) of &lt;1.47 indicated a likelihood of pathology in the lymph node. The absence of the hypointense signal from the fatty hilum of lymph nodes was considered as a predictor of lymph node metastasis. The analysis of this criterion showed 80 % sensitivity (CI 60.4‑91.6), 85.7 % specificity (60.4‑91.6), 80 % PPV, 85.1 % NPV and 83.3 % accuracy (CI 60.4‑91.6). Conclusion. Lymph node size of ≥0.8 cm in the short axis diameter and the short axis/long axis ratio (configuration index) of &lt;1.47 appeared to be significant MRI criteria in the assessment of lymph node metastasis. The additional use of MRI criterion such as the absence of the hypointense signal from the fatty hilum of the lymph node made it possible to improve diagnostic accuracy up to 92 % (CI 80.9–97.4).

Support Vector Machines Model of Computed Tomography for Assessing Lymph Node Metastasis in Esophageal Cancer with Neoadjuvant Chemotherapy.

ObjectiveThe aim of this study was to diagnose lymph node metastasis of esophageal cancer by support vector machines model based on computed tomography.Materials and MethodsA total of 131 esophageal cancer patients with preoperative chemotherapy and radical surgery were included. Various indicators (tumor thickness, tumor length, tumor CT value, total number of lymph nodes, and long axis and short axis sizes of largest lymph node) on CT images before and after neoadjuvant chemotherapy were recorded. A support vector machines model based on these CT indicators was built to predict lymph node metastasis.ResultsSupport vector machines model diagnosed lymph node metastasis better than preoperative short axis size of largest lymph node on CT. The area under the receiver operating characteristic curves were 0.887 and 0.705, respectively.ConclusionsThe support vector machine model of CT images can help diagnose lymph node metastasis in esophageal cancer with preoperative chemotherapy.