Skip to main content
Fig. 5 | Radiation Oncology

Fig. 5

From: Dosimetric impact of deep learning-based CT auto-segmentation on radiation therapy treatment planning for prostate cancer

Fig. 5

Differences between the two treatment plans optimized using U-Net- and manually-generated contours. DVH parameters for (top) OARs (bladder and rectum) and (bottom) TV (prostate, prostate + 3 mm margin). Each patient is represented by a single data point, while whiskers indicate the 5th–95th percentile. Dose values correspond to the total dose of 74 Gy delivered during fractionated treatment. Asterisks indicate the statistically significant differences

Back to article page