Feasibility of artificial intelligence-driven interfractional monitoring of organ changes by mega-voltage computed tomography in intensity-modulated radiotherapy of prostate cancer

PURPOSE

High-dose radiotherapy (RT) for localized prostate cancer requires careful consideration of target position changes and adjacent organs-at-risk (OARs), such as the rectum and bladder. Therefore, daily monitoring of target position and OAR changes is crucial in minimizing interfractional dosimetric uncertainties. For efficient monitoring of the internal condition of patients, we assessed the feasibility of an auto-segmentation of OARs on the daily acquired images, such as megavoltage computed tomography (MVCT), via a commercial artificial intelligence (AI)-based solution in this study.

MATERIALS AND METHODS

We collected MVCT images weekly during the entire course of RT for 100 prostate cancer patients treated with the helical TomoTherapy system. Based on the manually contoured body outline, the bladder including prostate area, and rectal balloon regions for the 100 MVCT images, we trained the commercially available fully convolutional (FC)-DenseNet model and tested its auto-contouring performance.

RESULTS

Based on the optimally determined hyperparameters, the FC-DenseNet model successfully auto-contoured all regions of interest showing high dice similarity coefficient (DSC) over 0.8 and a small mean surface distance (MSD) within 1.43 mm in reference to the manually contoured data. With this well-trained AI model, we have efficiently monitored the patient's internal condition through six MVCT scans, analyzing DSC, MSD, centroid, and volume differences.

CONCLUSION

We have verified the feasibility of utilizing a commercial AI-based model for auto-segmentation with low-quality daily MVCT images. In the future, we will establish a fast and accurate auto-segmentation and internal organ monitoring system for efficiently determining the time for adaptive replanning.

Assessment of inter- and intra-fractional volume of bladder and body contour by mega-voltage computed tomography in helical tomotherapy for pelvic malignancy

Purpose

We describe the daily bladder volume change observed by mega-voltage computed tomography (MVCT) during pelvic radiotherapy with potential predictors of increased bladder volume variations.

Materials and Methods

For 41 patients who received pelvic area irradiation, the volumes of bladder and pelvic body contour were measured twice a day with pre- and post-irradiation MVCT from the 1st to the 10th fraction. The median prescription dose was 20 Gy (range, 18 to 30 Gy) up to a 10th fraction. The upper and lower margin of MVCT scanning was consistent during the daily treatments. The median age was 69 years (range, 33 to 86 years) and 10 patients (24.4%) were treated postoperatively.

Results

Overall bladder volume on planning computed tomography was 139.7 ± 92.8 mL. Generally, post-irradiation bladder volume (POSTBV) was larger than pre-irradiation bladder volume (PREBV) (p < 0.001). The mean PREBV and POSTBV was reduced after 10 fraction treatments by 21.3% (p = 0.028) and 25.4% (p = 0.007), respectively. The MVCT-scanned body contour volumes had a tendency to decrease as the treatment sessions progressed (p = 0.043 at the 8th fraction and p = 0.044 at the 10th fraction). There was a statistically significant correlation between bladder filling time and PREBV (p = 0.001).

Conclusion

Daily MVCT-based bladder volume assessment was feasible both intra- and inter-fractionally.