Automatic digitization of applicator and catheters for MRI-guided cervical cancer brachytherapy

MRI is the standard imaging modality for contouring organs-at-risk and clinical target volume in cervical cancer brachytherapy, and is widely used along with CT for treatment planning and image guidance. However, MRI-CT fusion-based approach is time-consuming and error-prone as it requires two imaging sessions and image registration. To realize more efficient and streamlined MRI-guided workflow, we propose an automatic method for digitizing the applicator and catheters using MRI alone.

Applicator digitization consists of applicator mesh reconstruction, applicator ring identification, and alignment of the mesh model with MRIs. For catheter digitization, we employ an uncertainty-aware deep-learning model that simultaneously segments catheters and computes uncertainty on its prediction. These uncertainty facilitate initial localization of the catheters and subsequent refinement.

This study was performed on 35 T2-weighted MRIs from 30 cervical cancer patients treated with the Venezia applicator. The dataset was divided into 80% for development and 20% for testing. The method successfully digitized all applicators, with mean translation and rotation errors of 1.13 ± 0.26 mm and 2.19 ± 2.09°, respectively. All catheters except one were successfully digitized with shaft and tip errors of 0.74 ± 0.32 mm and 2.52 ± 2.04 mm, respectively. Furthermore, plans derived from the automatic digitization showed no significant differences compared to clinical plans (p > 0.05).

The proposed MRI-based applicator and catheters digitization simplifies the brachytherapy planning process by eliminating the need for CT and manual tasks. Our results demonstrate that this approach is feasible and can be integrated into clinical workflows, offering potential improvements in efficiency and accuracy.