Development and validation of a CT-based radiomics nomogram for preoperative prediction of tumor histologic grade in gastric adenocarcinoma.

OBJECTIVES: To develop and validate a radiomics nomogram for preoperative prediction of tumor histologic grade in gastric adenocarcinoma (GA). METHODS: This retrospective study enrolled 592 patients with clinicopathologically confirmed GA (low-grade: n=154; high-grade: n=438) from January 2008 to March 2018 who were divided into training (n=450) and validation (n=142) sets according to the time of computed tomography (CT) examination. Radiomic features were extracted from the portal venous phase CT images. The Mann-Whitney U test and the least absolute shrinkage and selection operator (LASSO) regression model were used for feature selection, data dimension reduction and radiomics signature construction. Multivariable logistic regression analysis was applied to develop the prediction model. The radiomics signature and independent clinicopathologic risk factors were incorporated and presented as a radiomics nomogram. The performance of the nomogram was assessed with respect to its calibration and discrimination. RESULTS: A radiomics signature containing 12 selected features was significantly associated with the histologic grade of GA (P<0.001 for both training and validation sets). A nomogram including the radiomics signature and tumor location as predictors was developed. The model showed both good calibration and good discrimination, in which C-index in the training set, 0.752 [95% confidence interval (95% CI): 0.701-0.803]; C-index in the validation set, 0.793 (95% CI: 0.711-0.874). CONCLUSIONS: This study developed a radiomics nomogram that incorporates tumor location and radiomics signatures, which can be useful in facilitating preoperative individualized prediction of histologic grade of GA.

Ultrasound-Based Nomogram for Distinguishing Malignant Tumors from Nodular Sclerosing Adenoses in Solid Breast Lesions.

OBJECTIVES: Nodular sclerosing adenoses (NSAs) and malignant tumors (MTs) may coexist and are often classified into the same Breast Imaging Reporting and Data System (BI-RADS) category. We aimed to build and validate an ultrasound-based nomogram to distinguish MT from NSA for building a precise sequence of biopsies. MATERIALS AND METHODS: The training cohort included 156 patients (156 masses) with NSA or MT at one study institution. We used best subset regression to determine the predictors for building a nomogram from ultrasonic characteristics and patients' age. Model performance and clinical utility were evaluated using Brier score, concordance (C)-index, calibration curve, and decision curve analysis. The independent validation cohort consisted of 162 patients (162 masses) from a separate institution. RESULTS: Through best subset regression, we selected 6 predictors to develop nomogram: age, calcification, echogenic rim, vascularity distribution, tumor size, and thickness of breast parenchyma. Brier score and C-index of the nomogram in the training cohort were 0.068 and 0.967 (95% confidence interval [CI]: 0.941-0.993), respectively. In addition, calibration curve demonstrated good agreement between prediction and pathological result. In the validation cohort, the nomogram still obtained a favorable C-index score of 0.951 (95% CI: 0.919-0.983) and fine calibration. Decision curve analysis showed that the model was clinically useful. CONCLUSIONS: If multiple NSA and MT masses are present in the same patient and are classified into the same BI-RADS category, our nomogram can be used as a supplement to the BI-RADS category for accurate biopsy of the mass most likely to be MT.