Scanner Independent Deep Learning-Based Segmentation Framework Applied to Mouse Embryos
- Resource Type
- Conference
- Authors
- Aristizabal, Orlando; Turnbull, Daniel H.; Ketterling, Jeffrey A.; Wang, Yao; Qiu, Ziming; Xu, Tongda; Goldman, Hannah; Mamou, Jonathan
- Source
- 2020 IEEE International Ultrasonics Symposium (IUS) Ultrasonics Symposium (IUS),2020 IEEE International. :1-4 Sep, 2020
- Subject
- Bioengineering
Fields, Waves and Electromagnetics
Signal Processing and Analysis
Deep learning
Embryo
Three-dimensional displays
Transducers
Pipelines
Mice
Arrays
mouse embryo
automatic segmentation
convolutional network
- Language
- ISSN
- 1948-5727
We have applied a deep learning framework, trained on mouse embryo images acquired with a 40 MHz annular array, to volumetric data acquired with a VisualSonics Vevo 3100 commercial scanner using a 40-MHz linear array. The deep learning framework was robust enough to accurately segment out the body and the brain ventricle from the 3D data generated by the commercial scanner. These results show that there is no need to retrain the algorithm with hundreds of new manually segmented datasets.