biostudies-literatureUnknown12Yang L<h4>Objectives</h4>To build a radiomics model and combined model based on dual-energy CT (DECT) for diagnosing serosal invasion in gastric adenocarcinoma.<h4>Materials and methods</h4>231 gastric adenocarcinoma patients were enrolled and randomly divided into a training (<i>n</i> = 132), testing (<i>n</i> = 58), and independent validation (<i>n</i> = 41) cohort. Radiomics features were extracted from the rectangular ROI of the 120-kV equivalent mixed images and iodine map (IM) images in the venous phase of DECT, which was manually delineated perpendicularly to the gastric wall in the deepest location of tumor infiltration, including the peritumoral adipose tissue within 5 mm outside the serosa. The random forest algorithm was used for radiomics model construction. Traditional features wereFrontiers in oncology848425https://www.ebi.ac.uk/biostudies/studies/S-EPMC8977467biostudies-literatureDiagnosis of Serosal Invasion in Gastric Adenocarcinoma by Dual-Energy CT Radiomics: Focusing on Localized Gastric Wall and Peritumoral Radiomics Features.PMC8977467Li YLiu JYang LShi GWang XSun JYu XLi MfalseDiagnosis of Serosal Invasion in Gastric Adenocarcinoma by Dual-Energy CT Radiomics: Focusing on Localized Gastric Wall and Peritumoral Radiomics Features.<h4>Objectives</h4>To build a radiomics model and combined model based on dual-energy CT (DECT) for diagnosing serosal invasion in gastric adenocarcinoma.<h4>Materials and methods</h4>231 gastric adenocarcinoma patients were enrolled and randomly divided into a training (<i>n</i> = 132), testing (<i>n</i> = 58), and independent validation (<i>n</i> = 41) cohort. Radiomics features were extracted from the rectangular ROI of the 120-kV equivalent mixed images and iodine map (IM) images in the venous phase of DECT, which was manually delineated perpendicularly to the gastric wall in the deepest location of tumor infiltration, including the peritumoral adipose tissue within 5 mm outside the serosa. The random forest algorithm was used for radiomics model construction. Traditional features were2022-01-01T00:00:00Z20222025-04-19T21:48:31.532Z2025-04-19T21:48:31.532ZS-EPMC89774673538711610.3389/fonc.2022.848425