A Prior-mask-guided Few-shot Learning for Skin Lesion Segmentation
| Autor: | Junsheng Xiao, Honghao Gao, Chen Cheng, Wei Zhao, Huahu Xu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Early detection Inference 02 engineering and technology Convolutional neural network Theoretical Computer Science Data acquisition 0202 electrical engineering electronic engineering information engineering medicine Segmentation Numerical Analysis business.industry 020206 networking & telecommunications Patient survival Pattern recognition medicine.disease Computer Science Applications Computational Mathematics Computational Theory and Mathematics 020201 artificial intelligence & image processing Artificial intelligence Skin cancer business Skin lesion Software |
| Zdroj: | Computing. 105:717-739 |
| ISSN: | 1436-5057 0010-485X |
| DOI: | 10.1007/s00607-021-00907-z |
| Popis: | The incidence of skin cancer, which has high mortality, is growing rapidly worldwide. Early detection of skin lesions is crucial for timely diagnosis and treatment to improve the patient survival rate. Computer vision technology based on deep convolutional neural network requires a large amount of labelled data. The cost of data acquisition and annotation is relatively high, especially for skin cancer segmentation tasks. Therefore, we propose a few-shot segmentation network for skin lesion segmentation, which requires only a few pixel-level annotations. First, the co-occurrence region between the support image and query image is obtained, which is used as a prior mask to exclude irrelevant background regions. Second, the results are concatenated and sent to the inference module to predict segmentation of the query image. Third, the proposed network is retrained by reversing the support and query role, which benefits from the symmetrical structure. Extensive experiments performed on ISIC-2017, ISIC-2019, and PH2 demonstrate that our method forms a promising framework for few-shot segmentation of skin lesion. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink