Towards to Reasonable Decision Basis in Automatic Bone X-Ray Image Classification: A Weakly-Supervised Approach

Abstract

A weakly-supervised framework is proposed that cannot only make class inference but also provides reasonable decision basis in bone X-ray images. We implement it in three stages progressively: (1) design a classification network and use positive class activation map (PCAM) for attention location; (2) generate masks from attention maps and lead the model to make classification prediction from the activation areas; (3) label lesions in very few images and guide the model to learn simultaneously. We test the proposed method on a bone X-ray dataset. Results show that it achieves significant improvements in lesion location.

Cite

Text

Lu and Tong. "Towards to Reasonable Decision Basis in Automatic Bone X-Ray Image Classification: A Weakly-Supervised Approach." AAAI Conference on Artificial Intelligence, 2019. doi:10.1609/AAAI.V33I01.33019985

Markdown

[Lu and Tong. "Towards to Reasonable Decision Basis in Automatic Bone X-Ray Image Classification: A Weakly-Supervised Approach." AAAI Conference on Artificial Intelligence, 2019.](https://mlanthology.org/aaai/2019/lu2019aaai-reasonable/) doi:10.1609/AAAI.V33I01.33019985

BibTeX

@inproceedings{lu2019aaai-reasonable,
  title     = {{Towards to Reasonable Decision Basis in Automatic Bone X-Ray Image Classification: A Weakly-Supervised Approach}},
  author    = {Lu, Jianjie and Tong, Kai-Yu},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {9985-9986},
  doi       = {10.1609/AAAI.V33I01.33019985},
  url       = {https://mlanthology.org/aaai/2019/lu2019aaai-reasonable/}
}