Physics in medicine and biology
-
Convolutional neural networks (CNNs) have become the state-of-the-art method for medical segmentation. However, repeated pooling and striding operations reduce the feature resolution, causing loss of detailed information. Additionally, tumors of different patients are of different sizes. ⋯ The Dice similarity coefficient values of CAC-SPP were 0.78 ± 0.08 and 0.85 ± 0.03, respectively, which were higher than those of U-Net (0.70 ± 0.11 and 0.82 ± 0.04) and ResNet-101 (0.76 ± 0.10 and 0.84 ± 0.03). The segmentation speed of CAC-SPP was comparable with ResNet-101, but about 36% faster than U-Net. In conclusion, the proposed CAC-SPP, which could extract high-resolution features with large receptive fields and capture multi-scale context yields, improves the accuracy of segmentation performance for rectal tumors.
-
The relative biological effectiveness (RBE) of protons varies with multiple physical and biological factors. Phenomenological RBE models have been developed to include such factors in the estimation of a variable RBE, in contrast to the clinically applied constant RBE of 1.1. In this study, eleven published phenomenological RBE models and two plan-based models were explored and applied to simulated patient cases. ⋯ There were considerable variations between the estimations of RBE and RBE-weighted doses from the different models. These variations were a consequence of fundamental differences in experimental databases, model assumptions and regression techniques. The results from the implementation of RBE models in dose planning studies should be evaluated in light of these deviations.