Abstract | ||
---|---|---|
A fully automatic brain tissue segmentation framework is introduced in current paper, it is based on a parallel architecture of a specialized convolutional deep neuronal network designed to develop binary segmentation. The main contributions of this proposal imply its ability to segment brain RMI images of different acquisition modes, it does not require the initialization of any parameter; apart from the foregoing, it does not require any preprocessing stage to improve the quality of each slice. Experimental tests were developed considering BrainWeb and BraTS 2017 databases. The robustness and effectiveness of this proposal is verified by quantitative and qualitative results. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1007/978-3-030-21077-9_20 | PATTERN RECOGNITION, MCPR 2019 |
Keywords | Field | DocType |
Brain RMI segmentation, Parallel architecture, Convolutional deep neuronal network | Binary segmentation,Computer vision,Segmentation,Computer science,Nonparametric statistics,Robustness (computer science),Preprocessor,Artificial intelligence,Initialization,Brain tissue,Parallel architecture | Conference |
Volume | ISSN | Citations |
11524 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dante Mújica-Vargas | 1 | 10 | 2.55 |
Alicia Martínez | 2 | 0 | 0.34 |
Manuel Matuz-Cruz | 3 | 0 | 0.34 |
Antonio Luna-Alvarez | 4 | 0 | 0.34 |
Mildred Morales-Xicohtencatl | 5 | 0 | 0.34 |