Gayoung Kim

Dual convolution-transformer UNet (DCT-UNet) for organs at risk and clinical target volume segmentation in MRI for cervical cancer brachytherapy

Abstract Objective. MRI is the standard imaging modality for high-dose-rate brachytherapy of cervical cancer. Precise contouring of organs at risk (OARs) and high-risk clinical target volume (HR-CTV) from MRI is a crucial step for radiotherapy planning and treatment. However, conventional manual contouring has limitations in terms of accuracy as well as procedural time. To overcome these, we propose a deep learning approach to automatically segment OARs (bladder, rectum, and sigmoid colon) and HR-CTV from female pelvic MRI. Approach. In the proposed pipeline, a coarse multi-organ segmentation model first segments all structures, from which a region of interest is computed for each structure. Then, each organ is segmented using an organ-specific fine segmentation model separately trained for each organ. To account for variable sizes of HR-CTV, a size-adaptive multi-model approach was employed. For coarse and fine segmentations, we designed a dual convolution-transformer UNet (DCT-UNet) which uses dual-path encoder consisting of convolution and transformer blocks. To evaluate our model, OAR segmentations were compared to the clinical contours drawn by the attending radiation oncologist. For HR-CTV, four sets of contours (clinical + three additional sets) were obtained to produce a consensus ground truth as well as for inter/intra-observer variability analysis. Main results. DCT-UNet achieved dice similarity coefficient (mean ± SD) of 0.932 ± 0.032 (bladder), 0.786 ± 0.090 (rectum), 0.663 ± 0.180 (sigmoid colon), and 0.741 ± 0.076 (HR-CTV), outperforming other state-of-the-art models. Notably, the size-adaptive multi-model significantly improved HR-CTV segmentation compared to a single-model. Furthermore, significant inter/intra-observer variability was observed, and our model showed comparable performance to all observers. Computation time for the entire pipeline per subject was 12.59 ± 0.79 s, which is significantly shorter than the typical manual contouring time of >15 min. Significance. These experimental results demonstrate that our model has great utility in cervical cancer brachytherapy by enabling fast and accurate automatic segmentation, and has potential in improving consistency in contouring. DCT-UNet source code is available at https://github.com/JHU-MICA/DCT-UNet.

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.