Development and Validation a Nomogram for Predicting the Third Station Lymph Node Metastasis in Early Gastric Cancer

This study aimed to evaluate the value of radiomic nomogram in predicting lymph node metastasis in T1-2 gastric cancer according to the No. 3 station lymph nodes. Methods: A total of 159 T1-2 gastric cancer (GC) patients who had undergone surgery with lymphadenectomy between March 2012 and November 2017 were retrospectively collected and divided into a primary cohort (n = 80) and a validation cohort (n = 79). Radiomic features were extracted from both tumor region and No. 3 station lymph nodes (LN) based on computed tomography (CT) images per patient. Then, key features were selected using minimum redundancy maximum relevance algorithm and fed into two radiomic signatures, respectively. Meanwhile, the predictive performance of clinical risk factors was studied. Finally, a nomogram was built by merging radiomic signatures and clinical risk factors and evaluated by the area under the receiver operator characteristic curve (AUC) as well as decision curve. Results: Two Conclusions:

The LNs of the stomach are given station numbers as No.   [22,23]. Among them, the No.3 station LNs are frequently invaded by tumor cells relatively [24][25][26]. Therefore, we evaluate the value of radiomic nomogram in predicting lymph node metastasis in T1-2 GC according to the No. 3 station LNs.

Patients
The Institutional Review Board of our hospital approved this retrospective study and the requirement for informed consent was waived.
The inclusion criteria for the primary and validation cohorts were as follows: (a) patients who underwent surgery with curative intent for T1-2 GC and with pathological results; (b) LN dissection performed; (c) excisional LN with detailed grouping and pathological diagnosis; (d) standard contrast-enhanced CT performed less than 10 days before surgical resection. The exclusion criteria were:(a) hypotensive drug taboo (such as glaucoma, prostatic hypertrophy, etc.); (b) preoperative therapy (radiotherapy, chemotherapy, or chemoradiotherapy); (c) concurrent with other tumors or diseases; (d) patients with variation of the left gastric artery; (e) invisible lesions on CT images.
CT data acquisition All patients fasted for at least 4 hours, and 20 mg anisodamine (654-2) was administered intramuscularly to reduce gastrointestinal peristalsis 10 minutes prior to CT examination. 800-1000 mL warm water was drank to distend the stomach. CT was performed using a 256-Slice (Brilliance iCT, ROYAL PHILIPS, Eindhoven, Netherlands) or a 64-slice (SOMATON sensation64, SIEMENS Healthcare, Muenchhen, Germany) multi-slice spiral CT. Patients underwent both unenhanced and two-phase enhanced CT examinations (arterial phase: 35 s after injection; venous phase: 70 s after injection). The CT scans, covering the entire stomach region, were acquired during a breath-hold with the patient supine in all of the phases. During the enhanced CT scan, patients were infused with 1.5 mL/kg of the non-ionic contrast material (iohexol, Yangzi River Pharmaceutical Group, Jiangsu, China; iIodine concentration: 300 mg/mL) with a pump injector (Ulrich CT Plus 150, Ulrich Medical, Ulm, Germany) at a rate of 3.0 mL/s into the antecubital vein. The imaging parameters were as follows: 120 kV; 220-250 mAs; rotation time: 0.5 s; detector collimation: 128 × 0.625 mm or 32 × 0.6 mm; eld of view: 400 × 400 mm; matrix: 512 × 512; reconstruction slice thickness: 5 mm for axial plane, and 3 mm for coronal and sagittal plane.

Pipeline
The pipeline of this study includes ve steps: lesion detection, region of interest (ROI) segmentation, radiomic feature extraction, radiomic signature building, and nomogram construction and evaluation (Fig. 1).

Detection of Lesion on CT Images
All CT images were reviewed by a radiologist with more than 10 years of experience in GC diagnosis. Localization of GC lesions: The 159 patients selected in this study all had the results of gastroscopy and CT examination. Combined with gastroscopy and CT images (axial, coronal and sagittal images), the lesions could be located. The diagnostic criteria of CT-reported LN metastasis-positive were shown as follows: short-axis diameter of LN ≥ 5 mm, the ratio of short diameter to long diameter of LN ≥ 0.7, and the plain CT value of LN ≥ 25 HU or venous phase CT value of LN ≥ 75 HU; or multiple LNs were fused together even if above conditions were not satis ed.

ROI Segmentation on CT Images
Two 2-dimensional ROIs were manually segmented by a radiologist with more than 10 years of experience in GC diagnosis. The rst ROI (ROI-1) was delineated on the tumor in the slice with the maximum tumor lesion. The second ROI (ROI-2) was delineated on the region of No.3 station LNs around the lesser curvature of stomach. ROI segmentation was performed using ITK-SNAP software (version 2.2.0; www.itksnap.org) on the venous phase CT images with axial view (see Supplementary A1 for detail).

Extraction of Radiomic Features
Two feature groups were extracted from two ROIs, with each group containing 273 features [27,28]. These features were divided into 4 categories: (a) shape and size features, (b) gray intensity features, (c) texture features, and (d) wavelet features. The feature extraction was implemented using MATLAB (version 2014a; Mathworks, Natick, MA, USA). Radiomic features of all patients were standardized by the z-score method, based on the parameters calculated from the primary cohort. More information about the radiomic feature extraction is shown in Supplementary A2.

Radiomic Signature Construction
Radiomic feature selection and signature building were performed in the primary cohort for ROI-1 and ROI-2, respectively. More details are described as follows. In order to avoid model over-tting and improve performance, feature selection was performed to match the sample size (Supplementary A3).
First, the minimum redundancy maximum relevance algorithm (mRMR) ranked each feature based on its relevance to LN metastasis status, and the ranking process was able to consider the redundancy of these features at the same time [29].
Since the number of predictors should be kept within 1/10 − 1/3 of the size of the group that contains the smallest cases in the primary cohort (LN metastasis-positive group, n = 22) [30], the number of potential features was limited to 7 or less in this study.
Second, ve-fold cross-validation was performed multiple times on the primary cohort to nd the optimal number of features with the best performance based on ranked features. Then a radiomic signature (RS1) re ecting phenotype of ROI-1 and a radiomic signature (RS2) re ecting phenotype of ROI-2, were built as independent predictors of LN metastasis using selected features, respectively. For each radiomic signature, the signature score was calculated to re ect the risk of LN metastasis. The predictive performance of the radiomic signatures were quantitatively tested using the area under the receiver operator characteristic (ROC) curve in both the primary and validation cohorts.

Construction and Evaluation of Nomogram
Univariate analysis and multivariate analysis were used to screen out signi cant clinical risk factors. For univariate analysis, continuous variables were assessed using independent t-test or Mann-Whitney U test for differences between different groups, and categorical variables were assessed by Chi-squared test. As for multivariate analysis, we performed multivariate logistic regression to screen out key factors. Furthermore, multivariate logistic regression was used to merge two radiomic signatures and clinical risk factors into a nomogram. Meanwhile, we performed variable selection according to the p-values of the logistic regression. After that, the calibration curves and Hosmer-Lemeshow test were used to assess the goodness-of-t of the nomogram, and the AUC was used to quantify its predictive performance. For assessing over tting, DeLong test was adapted to compare AUCs between primary and validation cohorts. Moreover, we used net reclassi cation index (NRI) to compare the performance between nomogram and clinical risk factors, and quantify the improvement in predictive performance.
Furthermore, a strati ed analysis was used to evaluate the in uence of clinical factors to the nomogram. In addition, we performed a subgroup analysis to evaluate the additional value of the nomogram in the CT-reported LN metastasisnegative (CT-LNM0) subgroup. Since the number of metastasis in No. 4  Finally, to estimate the clinical utility of the nomogram, decision curve analysis (DCA) was performed by calculating the net bene ts using a range of threshold probabilities.

Statistical Analysis
All statistical analysis was performed using R software (version 3.3.4; http://www.Rproject.org). A two-sided P value < 0.05 was used to indicate statistical signi cance.

Results
Clinical characteristics Table 1 summarizes the patients' clinical risk factors in both the primary and validation cohorts. There is no signi cant difference in the probability of LN metastasis between the two cohorts (P = 0.384). Univariable analysis showed that CTreported LN metastasis status from the radiologist were signi cantly correlated with pathological LN metastasis status (P < 0.05), while CA125 was signi cantly correlated with LN metastasis status only in the primary cohort and tumor in ltration depth in the validation cohort. After multivariable analysis we chose the CT-reported LN metastasis status to predict LN metastasis.

Establishment of Radiomic Signature
During the feature selection, mRMR selected top 10 radiomic features from ROI-1 and top 10 radiomic features from ROI-2 in the primary cohort, respectively. As shown in Supplementary Figure S1 and Supplementary

Construction of Nomogram
During the multivariate logistic regression analysis, the two radiomic signatures and one clinical risk factor (CT-reported LN metastasis status) were identi ed as independent predictors of LN metastasis in T1-2 GC patients (Supplementary Table S4). An individualized nomogram was built using the regression method to predict the LN metastasis probability (Fig. 3A).

Evaluation of Nomogram
As shown in Fig. 2 and Table 2, our nomogram reached an AUC of 0.915 (95% CI: 0.832-0.998) in the primary cohort and an AUC of 0.908 (95% CI: 0.814-1.000) in the validation cohort, which were better than CT-reported LN metastasis status, RS1, and RS2. The NRI also demonstrated that the nomogram had better predictive ability than the CT-reported LN metastasis status in the primary cohort (NRI = 0.339, P < 0.001) and validation cohort (NRI = 0.301, P < 0.001). The DeLong test revealed that difference was not signi cant between AUCs of our nomogram in primary and validation cohorts (P = 0.908), further indicating the robust of our nomogram. As shown in Fig. 3B and C, the calibration curves of the nomogram demonstrates a good tness of nomogram in both the primary and validation cohorts. The Hosmer-Lemeshow test also showed good performance of our nomogram in the primary cohort (P = 0.147) and validation cohort (P = 0.903).
We also implemented strati ed analysis, more details were presented in Supplementary A5 and Supplementary Figure  S3. The results showed that our nomogram worked well in gender, age, pathologic grade and tumor in ltration depth subsets (DeLong test, P > 0.05).
Moreover, we selected 9 patients with LN metastasis and 11 patients with non-LN metastasis at No.4 station as a validation set to further validate our nomogram. Interestingly, our nomogram also showed a good performance on this station (AUC, 0.824; 95% CI, 0.517-1; Supplementary Figure S4).
The decision curve of the nomogram is presented in Fig. 5. With a threshold of 0 to 0.85, patients using nomogram will have more diagnostic bene ts than all-metastasis or none-metastasis strategies.

Discussion
In this study, an easy-to-use radiomic nomogram was established to identify LN metastasis of T1-2 GC preoperatively. The nomogram, incorporating two radiomic signatures and CT-reported LN metastasis status, showed the best discrimination ability of LN metastasis in both the primary and validation cohorts. The nomogram could assist the formulation of clinical treatment scheme.  Table S5) [24][25][26]. Therefore, the diagnosis of LN metastasis in No.3 LNs is clinically useful.
We analyzed the radiomic features in the two signi cant radiomic signatures. The radiomic features used in RS1 included: (1) 'X1_fos_skewness' describes the shape of a probability distribution of the voxel intensity histogram, and re ects the distribution symmetry. The CT images also demonstrated that higher heterogeneity of the primary tumor and No.3 LN region leaded to higher probability of LN metastasis.
In this study, CT-reported LN metastasis status from the radiologist was signi cantly correlated with LN metastasis in univariable analysis. This subjective judgement was also included in our nomogram. We also found that CA125 was signi cantly associated with LN metastasis in the primary cohort (P = 0.035), but had no signi cance in the validation cohort. This may be caused by the relatively small sample size and baseline deviation. Moreover, the positive rate of CA125 was very low in early GC [33].
We conducted some strati ed analysis, the results showed that the performance of our nomogram was not affected by gender, age, pathologic grade and tumor in ltration depth factors. In addition, we tested the correlations between the radiomic features and clinical risk factors using Pearson correlation analysis (Supplementary Figure S6). There was no correlation between radiomic features and clinical risk factors, which pointed that the radiomic features might be a good supplement to clinical factors. The good performance of our nomogram in CT-LNM0 subgroup also demonstrated the additional value of the nomogram to the radiologists.
More interestingly, the nomogram trained from phenotype of No.3 station LNs also showed a positive role in predicting LN metastasis in No.4 station LNs. This nding indicated that the radiomic signature from the LN region did re ect the early change of phenotype of LNs. Thus, our nomogram may be used in other stations of LNs.
There are some limitations in this study. Firstly, the relatively small sample size of this study. Secondly, the lack of the external validation. Thirdly, the presence of lymphatic invasion and LN micrometastasis have also been considered as important risk factors for LN metastasis in EGC [34][35][36], however, these factors were not routinely collected in our center.
Finally, cases with invisible lesions on CT images were excluded, so some patients could not use the nomogram. These problems need to be further studied. This study was approved by the institutional review board at the corresponding author's institution (The A liated People's Hospital of JiangSu University). As this is a retrospective case-control study, the need for informed written patient consent was waived by the ethics committee. All patient data were analyzed anonymously.

Consent for publication
The manuscript is approved by all participants for publication.

Availability of data and materials
The datasets used and analyzed during the current study available from the corresponding author on reasonable request (13913433095@163.com).

Competing interests
The authors declare that they have no competing interests.