Dosimetric assessment of patient dose calculation on a deep learning-based synthesized computed tomography image for adaptive radiotherapy

Purpose

Dose computation using cone beam computed tomography (CBCT) images is inaccurate for the purpose of adaptive treatment planning. The main goal of this study is to assess the dosimetric accuracy of synthetic computed tomography (CT)‐based calculation for adaptive planning in the upper abdominal region. We hypothesized that deep learning‐based synthetically generated CT images will produce comparable results to a deformed CT (CTdef) in terms of dose calculation, while displaying a more accurate representation of the daily anatomy and therefore superior dosimetric accuracy.

Methods

We have implemented a cycle‐consistent generative adversarial networks (CycleGANs) architecture to synthesize CT images from the daily acquired CBCT image with minimal error. CBCT and CT images from 17 liver stereotactic body radiation therapy (SBRT) patients were used to train, test, and validate the algorithm.

Results

The synthetically generated images showed increased signal‐to‐noise ratio, contrast resolution, and reduced root mean square error, mean absolute error, noise, and artifact severity. Superior edge matching, sharpness, and preservation of anatomical structures from the CBCT images were observed for the synthetic images when compared to the CTdef registration method. Three verification plans (CBCT, CTdef, and synthetic) were created from the original treatment plan and dose volume histogram (DVH) statistics were calculated. The synthetic‐based calculation shows comparatively similar results to the CTdef‐based calculation with a maximum mean deviation of 1.5%.

Conclusions

Our findings show that CycleGANs can produce reliable synthetic images for the adaptive delivery framework. Dose calculations can be performed on synthetic images with minimal error. Additionally, enhanced image quality should translate into better daily alignment, increasing treatment delivery accuracy.

Intraoperative preplanning for transperineal ultrasound-guided permanent prostate brachytherapy

PURPOSE

To describe our approach to intraoperative preplanning (INTRA-OP) for prostate implants and compare it to our standard method using a pre-implant volume study (STAND).

METHODS AND MATERIALS

Twenty patients (10 STAND, 10 INTRA-OP) were evaluated. Time required for each step of the INTRA-OP procedure was recorded. Overall procedure times and operating room times were obtained for all sessions. Postimplant dosimetry was CT-based.

RESULTS

Mean times required for each stage of the INTRA-OP procedure were as follows: Pre-implant TRUS/prostate stabilization, 26 min; image transfer, 4 min; volume outlining, 8 min; plan generation, 18 min; initial needle loading, 17 min; seed implantation, 57 min. Mean time for the implantation session was 150 min for the INTRA-OP and 120 min for the STAND groups (p = 0.002). However, this difference is negated if the preplanning volume study is included. In addition, there was a trend toward a shorter time for the INTRA-OP patients when evaluating mean total operating room times (200 min vs. 220 min; p = 0.07). The mean postimplant %D80 for the INTRA-OP patients was 104. 8% vs. 116.2% for the STAND group (p = 0.1). The corresponding %D90 values were 85.3% and 94.6%, respectively (p = 0.08).

CONCLUSION

Intraoperative preplanning increased the time required for the implantation session, but appeared to decrease overall operating room time. The overall convenience of the procedure makes intraoperative preplanning an attractive technique for transperineal ultrasound-guided prostate brachytherapy.