Deep Learning for Automated Contouring of Gross Tumor Volumes in Esophageal Cancer

Abstract

PurposeThe aim of this study was to propose and evaluate a novel three-dimensional (3D) V-Net and two-dimensional (2D) U-Net mixed (VUMix-Net) architecture for a fully automatic and accurate gross tumor volume (GTV) in esophageal cancer (EC)–delineated contours.MethodsWe collected the computed tomography (CT) scans of 215 EC patients. 3D V-Net, 2D U-Net, and VUMix-Net were developed and further applied simultaneously to delineate GTVs. The Dice similarity coefficient (DSC) and 95th-percentile Hausdorff distance (95HD) were used as quantitative metrics to evaluate the performance of the three models in ECs from different segments. The CT data of 20 patients were randomly selected as the ground truth (GT) masks, and the corresponding delineation results were generated by artificial intelligence (AI). Score differences between the two groups (GT versus AI) and the evaluation consistency were compared.ResultsIn all patients, there was a significant difference in the 2D DSCs from U-Net, V-Net, and VUMix-Net (p=0.01). In addition, VUMix-Net showed achieved better 3D-DSC and 95HD values. There was a significant difference among the 3D-DSC (mean ± STD) and 95HD values for upper-, middle-, and lower-segment EC (p<0.001), and the middle EC values were the best. In middle-segment EC, VUMix-Net achieved the highest 2D-DSC values (p<0.001) and lowest 95HD values (p=0.044).ConclusionThe new model (VUMix-Net) showed certain advantages in delineating the GTVs of EC. Additionally, it can generate the GTVs of EC that meet clinical requirements and have the same quality as human-generated contours. The system demonstrated the best performance for the ECs of the middle segment.

Performance of radiomics-based artificial intelligence systems in the diagnosis and prediction of treatment response and survival in esophageal cancer: a systematic review and meta-analysis of diagnostic accuracy

“… 29 The development of CNN in radiomics has enabled an automated process for organ segmentation in targeted radiotherapy built on deep learning and more recently, improved by a three-dimensional model. 30 In the adjuvant setting, an AI model built for estimating clinical target volume averaged at 25 seconds per patient. 31 …”

Towards deep-learning (DL) based fully automated target delineation for rectal cancer neoadjuvant radiotherapy using a divide-and-conquer strategy: a study with multicenter blind and randomized validation

“…As for GTV, to date only Wang et al [ 16 ] proposed to use Unet for GTV auto-segmentation for rectal cancer neoadjuvant radiotherapy. In addition, there are some attempts to auto-segment GTV for esophageal cancer [ 17 , 18 ].…”

Comparative analysis of automatic segmentation of esophageal cancer using 3D Res-UNet on conventional and 40-keV virtual mono-energetic CT Images: a retrospective study

“…Although there have been some studies on CT-based automatic segmentation of esophageal tumors, automatic segmentation of esophageal tumors in CT images is still a challenging task due to the low contrast between the tumor and surrounding tissues. This field is still in the exploratory stage and requires further research to improve segmentation accuracy and better apply it in clinical practice ( Yousefi et al, 2021 ; Jin et al, 2022 ; Yue et al, 2022 ).…”