Comparison of gross target volumes based on four‐dimensional CT, positron emission tomography‐computed tomography, and magnetic resonance imaging in thoracic esophageal cancer

Li, Huimin; Li, Fengxiang; Li, Jianbin; Zhu, Yingming; Zhang, Yingjie; Guo, Yongxian; Xu, Min; Shao, Qing; Liu, Xijun

doi:10.1002/cam4.3072

Cited by 5 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the planning of radiotherapy, radiotherapists need to outline the GTV on CT images layer by layer. The quality of GTV outlining determines 60% of the overall radiotherapy effectiveness [ 31 ]. Manual outlining by physicians is prone to introduce subjective errors and poor traceability.…”

Section: Discussionmentioning

confidence: 99%

Automatic segmentation of the gross target volume in radiotherapy for lung cancer using transresSEUnet 2.5D Network

Xie

Chen²,

Deng³

et al. 2022

J Transl Med

View full text Add to dashboard Cite

Objective This paper intends to propose a method of using TransResSEUnet2.5D network for accurate automatic segmentation of the Gross Target Volume (GTV) in Radiotherapy for lung cancer. Methods A total of 11,370 computed tomograms (CT), deriving from 137 cases, of lung cancer patients under radiotherapy developed by radiotherapists were used as the training set; 1642 CT images in 20 cases were used as the validation set, and 1685 CT images in 20 cases were used as the test set. The proposed network was tuned and trained to obtain the best segmentation model and its performance was measured by the Dice Similarity Coefficient (DSC) and with 95% Hausdorff distance (HD95). Lastly, as to demonstrate the accuracy of the automatic segmentation of the network proposed in this study, all possible mirrors of the input images were put into Unet2D, Unet2.5D, Unet3D, ResSEUnet3D, ResSEUnet2.5D, and TransResUnet2.5D, and their respective segmentation performances were compared and assessed. Results The segmentation results of the test set showed that TransResSEUnet2.5D performed the best in the DSC (84.08 ± 0.04) %, HD95 (8.11 ± 3.43) mm and time (6.50 ± 1.31) s metrics compared to the other three networks. Conclusions The TransResSEUnet 2.5D proposed in this study can automatically segment the GTV of radiotherapy for lung cancer patients with more accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic segmentation of the gross target volume in radiotherapy for lung cancer using transresSEUnet 2.5D Network

Xie

Chen²,

Deng³

et al. 2022

J Transl Med

View full text Add to dashboard Cite

show abstract

“…In contrast, considering patient acceptability, repeated MRI is generally well tolerated for response assessment ( 14 ). High-resolution MRI for target volume delineation and response assessment in EC is currently of immense clinical interest ( 15 , 16 ). The apparent diffusion coefficient (ADC) map from DW-MRI is a quantitative measure for the motion of water molecules and inversely correlates with tissue density.…”

Section: Introductionmentioning

confidence: 99%

Geometrical Comparison and Quantitative Evaluation of 18F-FDG PET/CT- and DW-MRI-Based Target Delineation Before and During Radiotherapy for Esophageal Squamous Carcinoma

et al. 2021

Front. Oncol.

Self Cite

View full text Add to dashboard Cite

Background and PurposeThis study aimed to evaluate the geometrical differences in and metabolic parameters of 18F-fluorodeoxyglucose positron emission tomography–computed tomography (18F-FDG PET-CT) and diffusion-weighted magnetic resonance imaging (DW-MRI) performed before and during radiotherapy (RT) for patients with esophageal cancer based on the three-dimensional CT (3DCT) medium and explore whether the high signal area derived from DW-MRI can be used as a tool for an individualized definition of the volume in need of dose escalation for esophageal squamous cancer.Materials and MethodsThirty-two patients with esophageal squamous cancer sequentially underwent repeated 3DCT, 18F-FDG PET-CT, and enhanced MRI before the initiation of RT and after the 15th fraction. All images were fused with 3DCT images through deformable registration. The gross tumor volume (GTV) was delineated based on PET Edge on the first and second PET-CT images and defined as GTVPETpre and GTVPETdur, respectively. GTVDWIpre and GTVDWIdur were delineated on the first and second DWI and corresponding T2-weighted MRI (T2W-MRI)-fused images. The maximum, mean, and peak standardized uptake values (SUVs; SUVmax, SUVmean, and SUVpeak, respectively); metabolic tumor volume (MTV); and total lesion glycolysis(TLG) and its relative changes were calculated automatically on PET. Similarly, the minimum and mean apparent diffusion coefficient (ADC; ADCmin and ADCmean) and its relative changes were measured manually using ADC maps.ResultsThe volume of GTVCT exhibited a significant positive correlation with that of GTVPET and GTVDWI (both p < 0.001). Significant differences were observed in both ADCs and 18F-FDG PET metabolic parameters before and during RT (both p < 0.001). No significant correlation was observed between SUVs and ADCs before and during RT (p = 0.072–0.944) and between ∆ADCs and ∆SUVs (p = 0.238–0.854). The conformity index and degree of inclusion of GTVPETpre to GTVDWIpre were significantly higher than those of GTVPETdur to GTVDWIdur (both p < 0.001). The maximum diameter shrinkage rate (∆LDDWI) (24%) and the tumor volume shrinkage rate (VRRDWI) (60%) based on DW-MRI during RT were significantly greater than the corresponding PET-based ∆LDPET (14%) and VRRPET (41%) rates (p = 0.017 and 0.000, respectively).ConclusionBased on the medium of CT images, there are significant differences in spatial position, biometabolic characteristics, and the tumor shrinkage rate for GTVs derived from 18F-FDG PET-CT and DW-MRI before and during RT for esophageal squamous cancer. Further studies are needed to determine if DW-MRI will be used as tool for an individualized definition of the volume in need of dose escalation.

show abstract

“…In the article by Li et al, 1 the funding program number or grant number for National Natural Science Foundation Item is incorrect. The correct funding program number is 81773287, instead of 1773287.…”

mentioning

confidence: 99%

Erratum

2020

Cancer Medicine

View full text Add to dashboard Cite

Comparison of gross target volumes based on four‐dimensional CT, positron emission tomography‐computed tomography, and magnetic resonance imaging in thoracic esophageal cancer

Abstract: This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 5 publications

References 30 publications

Automatic segmentation of the gross target volume in radiotherapy for lung cancer using transresSEUnet 2.5D Network

Automatic segmentation of the gross target volume in radiotherapy for lung cancer using transresSEUnet 2.5D Network

Geometrical Comparison and Quantitative Evaluation of 18F-FDG PET/CT- and DW-MRI-Based Target Delineation Before and During Radiotherapy for Esophageal Squamous Carcinoma

Erratum

Contact Info

Product

Resources

About