Abstract | ||
---|---|---|
Nodule segmentation from breast ultrasound images is challenging yet essential for the diagnosis. Weakly-supervised segmentation (WSS) can help reduce time-consuming and cumbersome manual annotation. Unlike existing weakly-supervised approaches, in this study, we propose a novel and general WSS framework called Flip Learning, which only needs the box annotation. Specifically, the target in the label box will be erased gradually to flip the classification tag, and the erased region will be considered as the segmentation result finally. Our contribution is three-fold. First, our proposed approach erases superpixel level using a Multi-agent Reinforcement Learning framework to exploit the prior boundary knowledge and accelerate the learning process. Second, we design two rewards: classification score and intensity distribution reward, to avoid under- and over-segmentation, respectively. Third, we adopt a coarse-to-fine learning strategy to reduce the residual errors and improve the segmentation performance. Extensively validated on a large dataset, our proposed approach achieves competitive performance and shows great potential to narrow the gap between fully-supervised and weakly-supervised learning. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-87193-2_47 | MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT I |
Keywords | DocType | Volume |
Ultrasound, Weakly-supervised segmentation, Reinforcement learning | Conference | 12901 |
ISSN | Citations | PageRank |
0302-9743 | 0 | 0.34 |
References | Authors | |
0 | 10 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yuhao Huang | 1 | 0 | 3.72 |
Xin Yang | 2 | 79 | 9.59 |
Yuxin Zou | 3 | 0 | 1.01 |
Chaoyu Chen | 4 | 0 | 2.03 |
Jian Wang | 5 | 3 | 1.76 |
Haoran Dou | 6 | 0 | 0.68 |
nishant ravikumar | 7 | 23 | 12.43 |
Alejandro F. Frangi | 8 | 4333 | 309.21 |
Jianqiao Zhou | 9 | 0 | 0.68 |
Dong Ni | 10 | 367 | 37.37 |