A Radiomics Nomogram Integrated With Clinic-Radiological Features for Preoperative Prediction of DNA Mismatch Repair Deficiency in Gastric Adenocarcinoma

Abstract

Purpose: To develop and validate a radiomics nomogram integrated with clinic-radiological features for preoperative prediction of DNA mismatch repair deficiency (dMMR) in gastric adenocarcinoma.

Materials and methods: From March 2014 to August 2020, 161 patients with pathologically confirmed gastric adenocarcinoma were included from two centers (center 1 as the training and internal testing sets, n = 101; center 2 as the external testing sets, n = 60). All patients underwent preoperative contrast-enhanced computerized tomography (CT) examination. Radiomics features were extracted from portal-venous phase CT images. Max-relevance and min-redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) methods were used to select features, and then radiomics signature was constructed using logistic regression analysis. A radiomics nomogram was built incorporating the radiomics signature and independent clinical predictors. The model performance was assessed using receiver operating characteristic (ROC) curve analysis, calibration curve, and decision curve analysis (DCA).

Results: The radiomics signature, which was constructed using two selected features, was significantly associated with dMMR gastric adenocarcinoma in the training and internal testing sets (P < 0.05). The radiomics signature model showed a moderate discrimination ability with an area under the ROC curve (AUC) of 0.81 in the training set, which was confirmed with an AUC of 0.78 in the internal testing set. The radiomics nomogram consisting of the radiomics signature and clinical factors (age, sex, and location) showed excellent discrimination in the training, internal testing, and external testing sets with AUCs of 0.93, 0.82, and 0.83, respectively. Further, calibration curves and DCA analysis demonstrated good fit and clinical utility of the radiomics nomogram.

Conclusions: The radiomics nomogram combining radiomics signature and clinical characteristics (age, sex, and location) may be used to individually predict dMMR of gastric adenocarcinoma.

Keywords: DNA mismatch repair deficiency; X-ray computed; gastric cancer/adenocarcinoma; nomogram; radiomics; tomography.

Figure 1

Flowchart of the recruiting study population and model construction.

Figure 2

An example of manual segmentation in gastric cancer. (A) Localized thick wall of gastric cancer with enhancement is observed on the portal venous phase computed tomography (CT) image. (B) Manual segmentation on the same axial slice is depicted with red label.

Figure 3

Feature selection with the least absolute shrinkage and selection operator (LASSO) binary logistic regression model. (A) Tuning parameter (λ) selection of the LASSO model. Binomial deviance was drawn versus log(λ). Vertical dotted lines were plotted at the best value using 10-fold cross-validation to tune parameter (λ) selection in the LASSO model. (B) LASSO coefficient profiles of the features. Each colored line represents the corresponding coefficient of each feature. A vertical dotted line was drawn at the selected λ, where non-zero coefficients were obtained with two features.

Figure 4

The CT-based radiomics nomogram. The radiomics nomogram was built in the training cohort, with the radiomics signature, sex (0 is male, 1 is female), age, and tumor location (0 is antrum, 1 is gastric body, 2 is cardia).

Figure 5

The ROC curves (AUC) of the three models in the training set (A) and internal testing set (B).

Figure 6

The ROC curves (AUC) of the external testing set.

Figure 7

Calibration curves of the nomogram in the training set (A), internal testing set (B), and external testing set (C).

Figure 8

Decision curve analysis (DCA) for the radiomics nomogram and clinics model. The DCA indicated that more net benefits within the most of thresholds probabilities were achieved using the radiomics nomogram.