Asha K Kumaraswamy1,2, Punith B Venkategowda1, Chandrashekar M. Patil2, and Robert Grimm3
1Siemens Healthcare Private Limited, Bengaluru, India, 2Vidyavardhaka College of Engineering, Mysuru, India, 3MR Application Predevelopment, Siemens Healthcare, Erlangen, Germany
1Siemens Healthcare Private Limited, Bengaluru, India, 2Vidyavardhaka College of Engineering, Mysuru, India, 3MR Application Predevelopment, Siemens Healthcare, Erlangen, Germany
Whole body diffusion-weighted MR imaging is a
promising technique for the
evaluation of bone metastases e.g. in prostate and breast cancer. In this work
we present a deep learning method for automatic bone segmentation, based on T1-weighted
imaging or DWI.
Figure 3:
Result of CNN bone segmentation trained on DWI (shown as red contour) using template-based segmentation on T1-weighted images
(green mask) as reference.
Figure 1: 3D CNN architecture considering
a 192x128x64 volume as input and performing conv3d, batch normalization and elu
in all the layers. Last layer with sigmoid activation and adam optimizer for
back propagation.
