Effect of magnesium oxide on interfraction prostate motion and rectal filling in prostate cancer radiotherapy

Automatic gas detection in prostate cancer patients during image-guided radiation therapy using a deep convolutional neural network

PURPOSE

The detection of intestinal/rectal gas is very important during image-guided radiation therapy (IGRT) of prostate cancer patients because intestinal/rectal gas increases the inter- and intra-fractional prostate motion. We propose a deep convolutional neural network (DCNN) to detect intestinal/rectal gas in the pelvic region.

MATERIAL AND METHODS

We selected 300 anterior-posterior kilo-voltage (kV) X-ray images from 30 prostate cancer patients. Thirty images were randomly chosen for a test set, and the remaining 270 images used as the training set. The intestinal/rectal gas was manually delineated on kV X-ray images and segmented. The training images were augmented by applying artificial shifts and fed into a DCNN. The network models were trained to keep the quality of the output image close to the quality of the input image by pooling and upsampling. The training set was used to adjust the parameters of the DCNN, and the test set was used to assess the performance of the model. The performance of the DCNN was evaluated using a fivefold cross-validation procedure. The dice similarity coefficient (DSC) was calculated to evaluate the detection accuracy between the manual contour and auto-segmentation.

RESULTS

The DCNN was trained within approximately 17 min with a time step of 20 s/epoch. The training and validation accuracy of the models after 50epochs were 0.94 and 0.85, respectively. The average ± standard deviation of the DSC for 30 test images was 0.85 ± 0.08.

CONCLUSIONS

The proposed DCNN method can automatically detect the intestinal/rectal gas in kV images with good accuracy.

The effect of bowel preparation regime on interfraction rectal filling variation during image guided radiotherapy for prostate cancer

Background

This study aimed to investigate the tolerability and impact of milk of magnesia (MoM) on interfraction rectal filling during prostate cancer radiotherapy.

Methods

Two groups were retrospectively identified, each consisting of 40 patients with prostate cancer treated with radiotherapy to prostate+/-seminal vesicles, with daily image-guidance in 78Gy/39fractions/8 weeks. The first-group followed anti-flatulence diet with MoM started 3-days prior to planning-CT and continued during radiotherapy, while the second-group followed the same anti-flatulence diet only. The rectum between upper and lower limit of the clinical target volume (CTV) was delineated on planning-CT and on weekly cone-beam-CT (CBCT). Rectal filling was assessed by measurement of anterio-posterior diameter of the rectum at the superior and mid levels of CTV, rectal volume (RV), and average cross-sectional rectal area (CSA; RV/length).

Results

Overall 720 images (80 planning-CT and 640 CBCT images) from 80 patients were analyzed. Using linear mixed models, and after adjusting for baseline values at the time of planning-CT to test the differences in rectal dimensions between both groups over the 8-week treatment period, there were no significant differences in RV (p = 0.4), CSA (p = 0.5), anterio-posterior diameter of rectum at superior (p = 0.4) or mid level of CTV (p = 0.4). In the non-MoM group; 22.5% of patients had diarrhea compared to 60% in the MoM group, while 40% discontinued use of MoM by end of radiotherapy.

Conclusion

The addition of MoM to antiflatulence diet did not reduce the interfraction variation in rectal filling but caused diarrhea in a substantial proportion of patients who then discontinued its use.