Auto-segmentation of target areas and organs-at-risk for total marrow and lymphoid irradiation in children / 中国医学物理学杂志

ABSTRACT

Objective To investigate the feasibility of AccuLearning system for the auto-segmentation of target areas and organs-at-risk(OAR)for total marrow and lymphoid irradiation(TMLI)in children.Methods Thirty pediatric patients who underwent TMLI since 2018 to 2022 were selected.The patients were immobilized in the supine position,and their CT images were acquired on the Philips Brilliance Big Bore CT scanner.After the target areas and OAR were manually delineated and modified,the CT images and manually delineated contours were imported into AccuLearning system for training,validation,and testing of the auto-segmentation model.The auto-segmentation results in 6 TMLI patients in the test set were evaluated in terms of Dice similarity coefficient(DSC),95%Hausdorff distance and average surface distance.Results On the test set with 6 cases,except for the lens that was difficult to be delineated automatically,the DSC values was above 0.70 for all other target areas and OAR,with only one patient having a DSC value of 0.59 for the stomach.The average DSC value for the stomach in all 6 patients was 0.76,and the average DSC values for the other organs were above 0.80.Conclusion The target areas and OAR automatically delineated with the model can meet the requirements of clinical planning after simple modifications.