.png){kind=icon}
返回
Visual attribution using Adversarial Latent Transformations
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compbiomed.2023.107521.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The ability to accurately locate all indicators of disease within medical images is vital for comprehending the effects of the disease, as well as for weakly-supervised segmentation and localization of the diagnostic correlators of disease. Existing methods either use classifiers to make predictions based on class-salient regions or else use adversarial learning based image-to-image translation to capture such disease effects. However, the former does not capture all relevant features for visual attribution (VA) and are prone to data biases; the latter can generate adversarial (misleading) and inefficient solutions when dealing in pixel values. To address this issue, we propose a novel approach Visual Attribution using Adversarial Latent Transformations (VA2LT). Our method uses adversarial learning to generate counterfactual (CF) normal images from abnormal images by finding and modifying discrepancies in the latent space. We use cycle consistency between the query and CF latent representations to guide our training. We evaluate our method on three datasets including a synthetic dataset, the Alzheimer's Disease Neuroimaging Initiative dataset, and the BraTS dataset. Our method outperforms baseline and related methods on all datasets.
Keyword:
Visual attribution
Domain translation
Generative adversarial networks
Medical imaging
Explainable artificial intelligence
期刊
IF:
6.3
论文数:
8.3K
被引数:
3.3W
机构
引用论文
Brain tumor segmentation based on the fusion of deep semantics and edge information in multimodal MRI基于深度语义和边缘信息融合的多模态MRI脑肿瘤分割.png)
INFORMATION FUSION
INFORMATION FUSIONIF15.5
PREAI
分享收藏Efficient Deep Network Architectures for Fast Chest X-Ray Tuberculosis Screening and VisualizationSCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏
查看更多内容