Samantha J Ma1,2, Mona Sharifi Sarabi2, Kai Wang2, Wenli Tan2, Huiting Wu3, Lei Hao3, Yulan Dong3, Hong Zhou3, Lirong Yan2, Yonggang Shi2, and Danny JJ Wang2
1Siemens Medical Solutions USA, Inc., Los Angeles, CA, United States, 2University of Southern California, Los Angeles, CA, United States, 3Department of Radiology, The First Affiliated Hospital of University of South China, Hunan, China
1Siemens Medical Solutions USA, Inc., Los Angeles, CA, United States, 2University of Southern California, Los Angeles, CA, United States, 3Department of Radiology, The First Affiliated Hospital of University of South China, Hunan, China
The current work demonstrates an exploratory deep learning framework
trained with images acquired at 3T and 7T on two MRI vendor platforms for
generality to improve automated segmentation of small arteries in non-invasive 3T
black-blood images.
Figure
1. Workflow of the images, pre-processing, data input, network training, and evaluation
of the HighRes3DNet deep learning model. Black blood images from 2 vendor scanners were used for manual segmentation in ITK-SNAP, which served as
supervision. Images were cropped to the same volume with
subcortical coverage regardless of resolution, underwent non-local means
filtering, and split into hemispheres to increase the sample size. The
HighRes3DNet was trained with 10-fold cross-validation on the training set that
included 3T and 7T images, and evaluated on a separate test set.
Figure 3. 3D renderings by ITK-SNAP of LSA segmentation results using ten-fold
validated HighRes3DNet from the test group never seen by the model during
training. The outputs generally agree well with the identification of vessels
by manual labeling, although there is still some disagreement regarding the
distal portions of the vessels. Note the manual segmentation is subject to
human interpretation.
