Name
Abstract | ||
|---|---|---|
Automated and accurate prostate segmentation technique from magnetic resonance images plays an important role in diagnostic and radiological planning. However, this task faces the challenge of extreme scale variation of prostate glands presented in the slices at different locations of MRI volumes. To alleviate problems arising from scale variation. We propose a cascaded prostate segmentation model that includes three stages: Coarse segmentation, segmentation result refinement, and scale normalization segmentation. Segmentation result refinement can remove the coarse segmentation results that do not contain prostates. More importantly, it normalizes the scale of the prostate region on different slice images of the same nuclear magnetic resonance volume according to the result of the coarse segmentation, thereby making the scale normalization segmentation network obtain scale-invariant magnetic resonance images as input. The experimental results demonstrate that this design can significantly reduce the degradation of segmentation performance arising from large scale variation. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1007/978-3-030-34110-7_45 | IMAGE AND GRAPHICS, ICIG 2019, PT II |
Keywords | DocType | Volume |
Prostate segmentation, Scale normalization, Cascaded model, MRI | Conference | 11902 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yuxuan Chen | 1 | 5 | 8.88 |
| Suiyi Li | 2 | 0 | 0.34 |
| Su Yang | 3 | 110 | 14.58 |
| Wuyang Luo | 4 | 0 | 0.34 |