xiang liu1, chao han1, and xiaoying wang1
1department of radiology, peking university first hospital, Beijing, China
1department of radiology, peking university first hospital, Beijing, China
The 3D U-Net CNN showed good quantitative and
qualitative performances in the segmentation of pelvic bones on mpMRI images, which may provide reliable skeletal geometric information for subsequent detection of pelvic tumor bone
metastases
Figure
3. Examples of the comparison between
CNN-predicted and manual segmentation. (a) Section examples of eight
bones on DWI image; (b) The corresponding overlapping images between
manual segmentation (white background) and CNN-predicted segmentation; (c)
Section examples of eight bones on ADC image; (d) The corresponding
overlapping images between manual segmentation (white background) and
CNN-predicted segmentation .CNN: Convolution neural network.
Figure
2.
The SCORE system and evaluation criteria on DWI and ADC images. Condition A
refers to that the location of the predicted CD is consistent with manual CD,
and the range of the predicted CD is larger than (A1) or less than (A2) the
manual CD, or partially overlaps with the manual CD (A3). CD: connected domain,
which is defined as the label with a continuous structure in 3D space. DSC:
Dice similarity coefficient.
