Self-Supervised, Semi-Supervised, Multi-Context Learning for the Combined Classification and Segmentation of Medical Images (Student Abstract)

Abdullah-Al-Zubaer Imran, Chao Huang, Hui Tang, Wei Fan, Yuan Xiao, Dingjun Hao, Zhen Qian, Demetri Terzopoulos

AAAI 2020 pp. 13815-13816

doi:10.1609/AAAI.V34I10.7179 /aaai/2020/imran2020aaai-self/

Abstract

To tackle the problem of limited annotated data, semi-supervised learning is attracting attention as an alternative to fully supervised models. Moreover, optimizing a multiple-task model to learn “multiple contexts” can provide better generalizability compared to single-task models. We propose a novel semi-supervised multiple-task model leveraging self-supervision and adversarial training—namely, self-supervised, semi-supervised, multi-context learning (S4MCL)—and apply it to two crucial medical imaging tasks, classification and segmentation. Our experiments on spine X-rays reveal that the S4MCL model significantly outperforms semi-supervised single-task, semi-supervised multi-context, and fully-supervised single-task models, even with a 50% reduction of classification and segmentation labels.

PDF AAAI Semantic Scholar

Cite

Text

Imran et al. "Self-Supervised, Semi-Supervised, Multi-Context Learning for the Combined Classification and Segmentation of Medical Images (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7179

Markdown

[Imran et al. "Self-Supervised, Semi-Supervised, Multi-Context Learning for the Combined Classification and Segmentation of Medical Images (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/imran2020aaai-self/) doi:10.1609/AAAI.V34I10.7179

BibTeX

@inproceedings{imran2020aaai-self,
  title     = {{Self-Supervised, Semi-Supervised, Multi-Context Learning for the Combined Classification and Segmentation of Medical Images (Student Abstract)}},
  author    = {Imran, Abdullah-Al-Zubaer and Huang, Chao and Tang, Hui and Fan, Wei and Xiao, Yuan and Hao, Dingjun and Qian, Zhen and Terzopoulos, Demetri},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13815-13816},
  doi       = {10.1609/AAAI.V34I10.7179},
  url       = {https://mlanthology.org/aaai/2020/imran2020aaai-self/}
}