Deep learning nomogram for predicting lymph node metastasis using computed tomography image in cervical cancer

2021 ◽  
pp. 028418512110589
Author(s):  
Peijun Li ◽  
Bao Feng ◽  
Yu Liu ◽  
Yehang Chen ◽  
Haoyang Zhou ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Cervical Cancer ◽  
Deep Learning ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Validation Cohort ◽  
External Validation ◽  
Lymph Node Status ◽  
Internal Validation ◽  
Node Metastasis

Background Deep learning (DL) has been used on medical images to grade, differentiate, and predict prognosis in many tumors. Purpose To explore the effect of computed tomography (CT)-based deep learning nomogram (DLN) for predicting cervical cancer lymph node metastasis (LNM) before surgery. Material and Methods In total, 418 patients with stage IB-IIB cervical cancer were retrospectively enrolled for model exploration (n = 296) and internal validation (n = 122); 62 patients from another independent institution were enrolled for external validation. A convolutional neural network (CNN) was used for DL features extracting from all lesions. The least absolute shrinkage and selection operator (Lasso) logistic regression was used to develop a deep learning signature (DLS). A DLN incorporating the DLS and clinical risk factors was proposed to predict LNM individually. The performance of the DLN was evaluated on internal and external validation cohorts. Results Stage, CT-reported pelvic lymph node status, and DLS were found to be independent predictors and could be used to construct the DLN. The combination showed a better performance than the clinical model and DLS. The proposed DLN had an area under the curve (AUC) of 0.925 in the training cohort, 0.771 in the internal validation cohort, and 0.790 in the external validation cohort. Decision curve analysis and stratification analysis suggested that the DLN has potential ability to generate a personalized probability of LNM in cervical cancer. Conclusion The proposed CT-based DLN could be used as a personalized non-invasive tool for preoperative prediction of LNM in cervical cancer, which could facilitate the choice of clinical treatment methods.

scholarly journals A Clinical-Radiomics Nomogram for Preoperative Prediction of Lymph Node Metastasis in Gallbladder Cancer

2021 ◽  
Vol 11 ◽  
Author(s):  
Xingyu Liu ◽  
Xiaoyuan Liang ◽  
Lingxiang Ruan ◽  
Sheng Yan
Keyword(s):  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Gallbladder Cancer ◽  
Prediction Models ◽  
Validation Cohort ◽  
External Validation ◽  
Training Cohort ◽  
Clinical Variables ◽  
Node Metastasis ◽  
Preoperative Prediction

ObjectivesThe aim of the current study was to develop and validate a nomogram based on CT radiomics features and clinical variables for predicting lymph node metastasis (LNM) in gallbladder cancer (GBC).MethodsA total of 353 GBC patients from two hospitals were enrolled in this study. A Radscore was developed using least absolute shrinkage and selection operator (LASSO) logistic model based on the radiomics features extracted from the portal venous-phase computed tomography (CT). Four prediction models were constructed based on the training cohort and were validated using internal and external validation cohorts. The most effective model was then selected to build a nomogram.ResultsThe clinical-radiomics nomogram, which comprised Radscore and three clinical variables, showed the best diagnostic efficiency in the training cohort (AUC = 0.851), internal validation cohort (AUC = 0.819), and external validation cohort (AUC = 0.824). Calibration curves showed good discrimination ability of the nomogram using the validation cohorts. Decision curve analysis (DCA) showed that the nomogram had a high clinical utility.ConclusionThe findings showed that the clinical-radiomics nomogram based on radiomics features and clinical parameters is a promising tool for preoperative prediction of LN status in patients with GBC.

Novel perioperative parameters-based nomograms for survival outcomes in upper tract urothelial carcinoma after radical nephroureterectomy.

2019 ◽  
Vol 37 (7_suppl) ◽  
pp. 414-414
Author(s):  
Ping Tan ◽  
Lu Yang ◽  
Hang Xu ◽  
Qiang Wei
Keyword(s):  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Prediction Models ◽  
Validation Cohort ◽  
Fibrinogen Level ◽  
External Validation ◽  
Cox Proportional Hazards ◽  
Radical Nephroureterectomy ◽  
Cancer Specific Survival ◽  
Node Metastasis

414 Background: Recently, several postoperative nomograms for cancer-specific survival (CSS) after radical nephroureterectomy (RNU) were proposed, while they did not incorporate the same variables; meanwhile, many preoperative blood-based parameters, which were recently reported to be related to survival, were not included in their models. In addition, no nomogram for overall survival (OS) was available to date. Methods: The full data of 716 patients were available. The whole cohort was randomly divided into two cohorts: the training cohort for developing the nomograms (n = 508) and the validation cohort for validating the models (n = 208). Univariate and multivariate Cox proportional hazards regression models were used for establishing the prediction models. The discriminative accuracy of nomograms were measured by Harrell’s concordance index (C-index). The clinical usefulness and net benefit of the predictive models were estimated and visualized by using Decision curve analyses (DCA). Results: The median follow-up time was 42.0 months (IQR: 18.0-76.0). For CSS, tumor size, grade and pT stage, lymph node metastasis, NLR, PLR and fibrinogen level were identified as independent risk factors in the final model; while tumor grade and pT stage, lymph node metastasis, PLR, Cys-C and fibrinogen level were identified as independent predictors for OS model. The C-index for CSS prediction was 0.82 (95%CI: 0.79-0.85), and the OS nomogram model had an accuracy of 0.83 (95%CI: 0.80-0.86). The results of bootstrapping showed no deviation from the ideal. The calibration plots for the probability of CSS and OS at 3 or 5-year after RNU showed a favorable agreement between the prediction by the nomograms and actual observation. In the external validation cohort, the C-indexes of the nomograms for predicting CSS and OS were 0.79 (95%CI: 0.74-0.84) and 0.80 (95%CI: 0.75-0.85), respectively. As indicated by calibration plots, optimal agreement was observed between prediction and observation in the external cohort. Conclusions: The nomograms developed and validated based on preoperative blood-based parameters were superior to any single variable for predicting CSS and OS after RNU.

scholarly journals Development and validation of a nomogram for preoperative prediction of lymph node metastasis in early gastric cancer

2020 ◽  
Vol 18 (1) ◽  
Author(s):  
Xiao-Yi Yin ◽  
Tao Pang ◽  
Yu Liu ◽  
Hang-Tian Cui ◽  
Tian-Hang Luo ◽  
...  
Keyword(s):  
Gastric Cancer ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Early Gastric Cancer ◽  
Cancer Patients ◽  
Validation Cohort ◽  
External Validation ◽  
Training Cohort ◽  
Node Metastasis ◽  
Gastric Cancer Patients

Abstract Background The status of lymph nodes in early gastric cancer is critical to make further clinical treatment decision, but the prediction of lymph node metastasis remains difficult before operation. This study aimed to develop a nomogram that contained preoperative factors to predict lymph node metastasis in early gastric cancer patients. Methods This study analyzed the clinicopathologic features of 823 early gastric cancer patients who underwent gastrectomy retrospectively, among which 596 patients were recruited in the training cohort and 227 patients in the independent validation cohort. Significant risk factors in univariate analysis were further identified to be independent variables in multivariable logistic regression analysis, which were then incorporated in and presented with a nomogram. And internal and external validation curves were plotted to evaluate the discrimination of the nomogram. Results Totally, six independent predictors, including the tumor size, macroscopic features, histology differentiation, P53, carbohydrate antigen 19-9, and computed tomography-reported lymph node status, were enrolled in the nomogram. Both the internal validation in the training cohort and the external validation in the validation cohort showed the nomogram had good discriminations, with a C-index of 0.82 (95%CI, 0.78 to 0.86) and 0.77 (95%CI, 0.60 to 0.94) respectively. Conclusions Our study developed a new nomogram which contained the most common and significant preoperative risk factors for lymph node metastasis in patients with early gastric cancer. The nomogram can identify early gastric cancer patients with the high probability of lymph node metastasis and help clinicians make more appropriate decisions in clinical practice.

scholarly journals Assessment of retroperitoneal lymph node status in locally advanced cervical cancer

BMC Cancer ◽  
2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Wei Li ◽  
Li Xiong ◽  
Qiaoling Zhu ◽  
Hong Lu ◽  
Meiling Zhong ◽  
...  
Keyword(s):  
Risk Factors ◽  
Cervical Cancer ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Locally Advanced ◽  
Lymph Node Status ◽  
Advanced Cervical Cancer ◽  
Retroperitoneal Lymph Node ◽  
Node Metastasis ◽  
Metastasis Rate

Abstract Background The assessment of retroperitoneal lymph node status in patients with locally advanced cervical cancer is still a problem. This study aimed to explore the choice of these assessment methods. Methods Laparoscopic retroperitoneal lymphadenectomy was performed in 96 patients with advanced cervical cancer. The positive rates of lymph node metastasis were analyzed. The values of computed tomography lymph node minimum axial diameter (MAD) and squamous cell carcinoma antigen (SCC-Ag), and their combination in predicting retroperitoneal lymph node metastasis were compared. High-risk factors for common iliac lymph node (CILN) and/or para-aortic lymph node (PALN) metastasis were analyzed. Results The lymph node metastasis rate was 62.50% and the CILN and/or PALN metastasis rate was 31.25%. Overall, 96 patients had 172 visible lymph nodes. The positive rate of lymph node metastasis was significantly higher in the MAD ≥1.0 cm group (83.33%) than in the 0.5 cm ≤ MAD < 1.0 cm group (26.82%). The critical values of MAD and SCC-Ag in determining lymph node metastasis were 1.0 cm and 5.2 ng/mL, respectively. The accuracy, specificity, and Youden index of MAD ≥1.0 cm combined with SCC-Ag ≥ 5.2 ng/mL for evaluating lymph node metastasis were 75.71%, 100%, and 0.59, respectively, and were significantly different from the values for the MAD ≥1.0 cm (72.09%, 80.56%, and 0.47, respectively) and SCC-Ag ≥ 5.2 ng/mL (71.43%, 68.97%, and 0.42, respectively) groups. Correlation analysis showed that non-squamous cell carcinoma, pelvic lymph node (PLN) MAD ≥1.0 cm plus number ≥ 2, and 1 PLN MAD ≥1.0 cm with CILN and/or PALN MAD 0.5–1.0 cm were risk factors for CILN and/or PALN metastasis. Conclusion Patients with MAD ≥1.0 cm and SCC-Ag ≥ 5.2 ng/mL, as well as high risk factors for CILN and/or PALN metastasis, should undergo resection of enlarged lymph nodes below the common iliac gland and lymphadenectomy of CILN/PALN to reduce tumor burden and to clarify lymph node metastasis status for accurate guidance in follow-up treatment. Patients with MAD < 1.0 cm and SCC-Ag < 5.2 ng/mL may be treated with chemoradiotherapy directly based on imaging, given the low lymph node metastasis rate.

scholarly journals Identifying Clinicopathological Risk Factors of the Regional Lymph Node Metastasis in Patients with T1-2 Mucinous Breast Cancer: A Population-Based Study

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Yu Min ◽  
Xiaoyuan Wei ◽  
Hang Chen ◽  
Ke Xiang ◽  
Guobing Yin ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Risk Factors ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Validation Cohort ◽  
Regional Lymph Node ◽  
Regional Lymph Node Metastasis ◽  
Internal Validation ◽  
Node Metastasis ◽  
Mucinous Breast Cancer

Background. Pure mucinous breast cancer (PMBC) has a better prognosis than other types of invasive breast cancer. However, regional lymph node metastasis (LNM) might reverse this outcome. We aim to determine the independent predictive factors for regional LNM and further develop a nomogram model for clinical practice. Method. Data of PMBC patients from the Surveillance, Epidemiology, and End Results (SEER) program between Jan 2010 and Dec 2015 were retrospectively reviewed. Univariate and multivariate logistic regression analyses were used to determine the risk factors for LNM in T1-2 MBC. The nomogram was constructed and further evaluated by an internal validation cohort. The receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and calibration curves were performed to evaluate the accuracy of this model. Result. Five variables, including age, race, tumor size, grade, and breast subtype, were identified to be significantly associated with regional LNM in female patients with T1-2 PMBC. A nomogram was successfully established with a favorable concordance index (C-index) of 0.780, supported by an internal validation cohort with a C-index of 0.767. Conclusion. A nomogram for predicting regional LNM in female patients with T1-2 PMBC was successfully established and validated via an internal cohort. This visualized model would assist surgeons to make appropriate clinical decisions in the management of primary PMBC, especially in terms of whether axillary lymph node dissection (ALND) is warranted.

Sign in / Sign up

Export Citation Format

Share Document