Evaluation of a cycle-generative adversarial network-based cone-beam CT to synthetic CT conversion algorithm for adaptive radiation therapy

Miriam Eckl; Lea Hoppen; Gustavo R Sarria; Judit Boda-Heggemann; Anna Simeonova-Chergou; Volker Steil; Frank A Giordano; Jens Fleckenstein

doi:10.1016/j.ejmp.2020.11.007

Evaluation of a cycle-generative adversarial network-based cone-beam CT to synthetic CT conversion algorithm for adaptive radiation therapy

Phys Med. 2020 Dec:80:308-316. doi: 10.1016/j.ejmp.2020.11.007. Epub 2020 Nov 24.

Authors

Miriam Eckl¹, Lea Hoppen², Gustavo R Sarria³, Judit Boda-Heggemann¹, Anna Simeonova-Chergou¹, Volker Steil¹, Frank A Giordano³, Jens Fleckenstein¹

Affiliations

¹ Department of Radiation Oncology, University Medical Center Mannheim, University of Heidelberg, Germany.
² Department of Radiation Oncology, University Medical Center Mannheim, University of Heidelberg, Germany. Electronic address: Lea.Hoppen@umm.de.
³ Department of Radiology and Radiation Oncology, University Hospital Bonn, Germany.

PMID: 33246190
DOI: 10.1016/j.ejmp.2020.11.007

Abstract

Purpose: Image-guided radiation therapy could benefit from implementing adaptive radiation therapy (ART) techniques. A cycle-generative adversarial network (cycle-GAN)-based cone-beam computed tomography (CBCT)-to-synthetic CT (sCT) conversion algorithm was evaluated regarding image quality, image segmentation and dosimetric accuracy for head and neck (H&N), thoracic and pelvic body regions.

Methods: Using a cycle-GAN, three body site-specific models were priorly trained with independent paired CT and CBCT datasets of a kV imaging system (XVI, Elekta). sCT were generated based on first-fraction CBCT for 15 patients of each body region. Mean errors (ME) and mean absolute errors (MAE) were analyzed for the sCT. On the sCT, manually delineated structures were compared to deformed structures from the planning CT (pCT) and evaluated with standard segmentation metrics. Treatment plans were recalculated on sCT. A comparison of clinically relevant dose-volume parameters (D₉₈, D₅₀ and D₂ of the target volume) and 3D-gamma (3%/3mm) analysis were performed.

Results: The mean ME and MAE were 1.4, 29.6, 5.4 Hounsfield units (HU) and 77.2, 94.2, 41.8 HU for H&N, thoracic and pelvic region, respectively. Dice similarity coefficients varied between 66.7 ± 8.3% (seminal vesicles) and 94.9 ± 2.0% (lungs). Maximum mean surface distances were 6.3 mm (heart), followed by 3.5 mm (brainstem). The mean dosimetric differences of the target volumes did not exceed 1.7%. Mean 3D gamma pass rates greater than 97.8% were achieved in all cases.

Conclusions: The presented method generates sCT images with a quality close to pCT and yielded clinically acceptable dosimetric deviations. Thus, an important prerequisite towards clinical implementation of CBCT-based ART is fulfilled.

Keywords: Adaptive radiation therapy; Cone-beam CT; Cycle-generative adversarial network-based image correction; Synthetic CT.

MeSH terms

Algorithms
Cone-Beam Computed Tomography
Humans
Image Processing, Computer-Assisted*
Male
Radiometry
Radiotherapy Dosage
Radiotherapy Planning, Computer-Assisted*