Abstract | ||
---|---|---|
Probe-based confocal laser endomicroscopy (pCLE) is an emerging tool for epithelial cancer diagnosis, which enables in-vivo microscopic imaging during endoscopic procedures and facilitates the development of automatic recognition algorithms to identify the status of tissues. In this paper, we propose a transfer recurrent feature learning (TRFL) framework for classification tasks on pCLE videos. At the first stage, the discriminative feature of single pCLE frame is learned via generative adversarial networks based on both pCLE and histology modalities. At the second stage, we use recurrent neural networks to handle the varying length and irregular shape of pCLE mosaics taking the frame-based features as input. The experiments on real pCLE datasets demonstrate that our approach outperforms, with statistical significance, state-of-the-art approaches. A binary classification accuracy of 84.1% has been achieved. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TMI.2018.2872473 | IEEE transactions on medical imaging |
Keywords | Field | DocType |
Videos,Imaging,Feature extraction,Image segmentation,Task analysis,Recurrent neural networks,Visualization | Computer vision,Data set,Binary classification,Recurrent neural network,Artificial intelligence,Recognition algorithm,Discriminative model,Feature learning,Mathematics,Microscopic imaging,Endomicroscopy | Journal |
Volume | Issue | ISSN |
38 | 3 | 1558-254X |
Citations | PageRank | References |
1 | 0.35 | 0 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yun Gu | 1 | 31 | 7.35 |
Khushi Vyas | 2 | 5 | 1.80 |
Jie Yang | 3 | 868 | 87.15 |
Guang-Zhong Yang | 4 | 2812 | 297.66 |