Frontiers in Public Health (Mar 2022)

Dosimetric Study of Deep Learning-Guided ITV Prediction in Cone-beam CT for Lung Stereotactic Body Radiotherapy

  • Shujun Zhang,
  • Bo Lv,
  • Xiangpeng Zheng,
  • Ya Li,
  • Weiqiang Ge,
  • Libo Zhang,
  • Fan Mo,
  • Jianjian Qiu

DOI
https://doi.org/10.3389/fpubh.2022.860135
Journal volume & issue
Vol. 10

Abstract

Read online

PurposeThe purpose of this study was to evaluate the accuracy of a lung stereotactic body radiotherapy (SBRT) treatment plan with the target of a newly predicted internal target volume (ITVpredict) and the feasibility of its clinical application. ITVpredict was automatically generated by our in-house deep learning model according to the cone-beam CT (CBCT) image database.MethodA retrospective study of 45 patients who underwent SBRT was involved, and Mask R-CNN based algorithm model helped to predict the internal target volume (ITV) using the CBCT image database. The geometric accuracy of ITVpredict was verified by the Dice Similarity Coefficient (DSC), 3D Motion Range (R3D), Relative Volume Index (RVI), and Hausdorff Distance (HD). The PTVpredict was generated by ITVpredict, which was registered and then projected on free-breath CT (FBCT) images. The PTVFBCT was margined from the GTV on FBCT images gross tumor volume on free-breath CT (GTVFBCT). Treatment plans with the target of Predict planning target volume on CBCT images (PTVpredict) and planning target volume on free-breath CT (PTVFBCT) were respectively re-established, and the dosimetric parameters included the ratio of the volume of patients receiving at least the prescribed dose to the volume of PTV (R100%), the ratio of the volume of patients receiving at least 50% of the prescribed dose to the volume of PTV in the Radiation Therapy Oncology Group (RTOG) 0813 Trial (R50%), Gradient Index (GI), and the maximum dose 2 cm from the PTV (D2cm), which were evaluated via Plan4DCT, plan which based on PTVpredict (Planpredict), and plan which based on PTVFBCT (PlanFBCT).ResultThe geometric results showed that there existed a good correlation between ITVpredict and ITV on the 4-dimensional CT [ITV4DCT; DSC= 0.83 ±0.18]. However, the average volume of ITVpredict was 10% less than that of ITV4DCT (p = 0.333). No significant difference in dose coverage was found in V100% for the ITV with 99.98 ± 0.04% in the ITV4DCT vs. 97.56 ± 4.71% in the ITVpredict (p = 0.162). Dosimetry parameters of PTV, including R100%, R50%, GI and D2cm showed no statistically significant difference between each plan (p > 0.05).ConclusionDosimetric parameters of Planpredict are clinically comparable to those of the original Plan4DCT. This study confirmed that the treatment plan based on ITVpredict produced by our model could automatically meet clinical requirements. Thus, for patients undergoing lung SBRT, the model has great potential for using CBCT images for ITV contouring which can be used in treatment planning.

Keywords