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.V33I01.33019985Markdown
[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.V33I01.33019985BibTeX
@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/}
}