Computed Tomography-Based Deep Learning Nomogram Can Accurately Predict Lymph Node Metastasis in Gastric Cancer

Abstract

Background: Computed tomography is the most commonly used imaging modality for preoperative assessment of lymph node status, but the reported accuracy is unsatisfactory.

Aims: To evaluate and verify the predictive performance of computed tomography deep learning on the presurgical evaluation of lymph node metastasis in patients with gastric cancer.

Methods: 347 patients were retrospectively selected (training cohort: 242, test cohort: 105). The enhanced computed tomography arterial phase images of gastric cancer were used for lesion segmentation, radiomics and deep learning feature extraction. Three methods were used for feature selection. Support vector machine (SVM) or random forest (RF) was used to build models. The classification performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC). We also established a nomogram that included clinical predictors.

Results: The model based on ResNet50-RF showed favorable classification performance and was verified in the test cohort (AUC = 0.9803). The nomogram based on deep learning feature scores and the lymph node status reported by computed tomography showed excellent discrimination. AUC of 0.9978 was achieved in the training cohort and verified in the test cohort (AUC = 0.9914). Decision analysis curve showed the value of nomogram in clinical application.

Conclusion: The computed tomography-based deep learning nomogram can accurately and effectively evaluate lymph node metastasis in patients with gastric cancer before surgery.

Keywords: Deep learning; Gastric cancer; Lymph node metastasis; Nomogram.

Fig. 1

Feature selection using LASSO. A MSE: Mean square error. Using tenfold cross-validation and iterating 100,000 times for parameter tuning to filter out the best lambda value. B Using the best lambda value for feature selecting

Fig. 2

Violin chart of deep learning feature scores of training cohort (A) and test cohort (B). 1: Male; 2: Female; The wider parts of the figure indicates that the patients in this group are more likely to adopt the given value and the narrower parts represents the lower probability

Fig. 3

Deep learning nomogram. The deep learning nomogram was constructed in the training cohort, including deep learning feature scores and the LN status reported by CT. Image: The LN status reported by CT. Score: The deep learning feature scores. 0: Lymph node metastasis negative; 1: Lymph node metastasis positive

Fig. 4

ROC curves of the deep learning nomogram in each cohort. p P value of Delong test

Fig. 5

Calibration curves of the deep learning nomogram in each cohort. A Training cohort. B Test cohort. Dashed lines indicate perfect predictions. The prediction performances of the deep learning nomogram are represented by solid lines. The solid line and the dashed line are very close, which indicates that the deep learning nomogram has excellent predictive performance

Fig. 6

DCA for the ResNet50-RF model and the deep learning nomogram in each cohort. A Training cohort. B Test cohort. The gray line indicates that it is assumed that all patients have LN metastasis. The black line indicates that it is assumed that all patients have no LN metastasis