To develop a deep learning model (AbsegNet) that produces accurate contours of 16 organs at risk (OARs) for abdominal malignancies, as an essential part of a fully automated radiation treatment planning.Three datasets with 544 computed tomography (CT) scans were retrospectively collected. Dataset 1 was split into 300 training cases and 128 test cases (cohort 1) for AbsegNet. Dataset 2, including cohort 2 (n = 24) and cohort 3 (n = 20), were used to validate AbsegNet externally. Dataset 3, including cohort 4 (n = 40) and cohort 5 (n = 32) were used to clinically assess the accuracy of AbsegNet-generated contours. Each cohort was from a different center. The Dice similarity coefficient (DSC) and 95th-percentile Hausdorff distance (HD95) were calculated to evaluate the delineation quality for each OAR. Clinical accuracy evaluation was classified into three levels: no revision, minor revisions (0% < volumetric revision degrees (VRD) ≤ 10%), moderate revisions (10% ≤ VRD < 20%), and major revisions (VRD ≥ 20%).For all OARs, AbsegNet achieved a mean DSC of 86.73%, 85.65%, and 88.04% in cohort 1, cohort 2, and cohort 3, respectively, and a mean HD95 of 8.92mm, 10.18mm, and 12.40mm, respectively. The performance of AbsegNet outperformed SwinUNETR, DeepLabV3+, Attention-UNet, UNet and 3D-UNet. When experts evaluated contours from cohorts 4 and 5, four OARs (liver, kidney_L, kidney_R, and spleen) of all patients were scored as having no revision, and over 87.5% of patients with contours of the stomach, esophagus, adrenals, or rectum were considered as having no or minor revisions. Only 15.0% of patients with contours of the colon and small bowel required major revisions.We propose a novel deep learning model to delineate OARs on diverse datasets. Most contours produced by AbsegNet are accurate and robust, therefore clinically applicable and helpful to facilitate radiotherapy workflow.Copyright © 2023. Published by Elsevier Inc.