Timezone: »
Disease-related representations play a crucial role in image-based disease prediction such as cancer diagnosis, due to its considerable generalization capacity. However, it is still a challenge to identify lesion characteristics in obscured images, as many lesions are obscured by other tissues. In this paper, to learn the representations for identifying obscured lesions, we propose a disentanglement learning strategy under the guidance of alpha blending generation in an encoder-decoder framework (DAB-Net). Specifically, we take mammogram mass benign/malignant classification as an example. In our framework, composite obscured mass images are generated by alpha blending and then explicitly disentangled into disease-related mass features and interference glands features. To achieve disentanglement learning, features of these two parts are decoded to reconstruct the mass and the glands with corresponding reconstruction losses, and only disease-related mass features are fed into the classifier for disease prediction. Experimental results on one public dataset DDSM and three in-house datasets demonstrate that the proposed strategy can achieve state-of-the-art performance. DAB-Net achieves substantial improvements of 3.9%∼4.4% AUC in obscured cases. Besides, the visualization analysis shows the model can better disentangle the mass and glands in the obscured image, suggesting the effectiveness of our solution in exploring the hidden characteristics in this challenging problem.
Author Information
Chu-ran Wang (Center for Data Science, Peking University)
Fei Gao (Peking University)
Fandong Zhang (Deepwise AI Lab)
Fangwei Zhong (Peking University)
Yizhou Yu (The University of Hong Kong)
Yizhou Wang (Peking University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: Disentangling Disease-related Representation from Obscure for Disease Prediction »
Thu. Jul 21st through Fri the 22nd Room Hall E #127
More from the Same Authors
-
2021 : ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind »
Yuanfei Wang · Fangwei Zhong · Jing Xu · Yizhou Wang -
2021 Poster: Towards Distraction-Robust Active Visual Tracking »
Fangwei Zhong · Peng Sun · Wenhan Luo · Tingyun Yan · Yizhou Wang -
2021 Spotlight: Towards Distraction-Robust Active Visual Tracking »
Fangwei Zhong · Peng Sun · Wenhan Luo · Tingyun Yan · Yizhou Wang -
2018 Poster: End-to-end Active Object Tracking via Reinforcement Learning »
Wenhan Luo · Peng Sun · Fangwei Zhong · Wei Liu · Tong Zhang · Yizhou Wang -
2018 Poster: MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning »
Bo Zhao · Xinwei Sun · Yanwei Fu · Yuan Yao · Yizhou Wang -
2018 Oral: End-to-end Active Object Tracking via Reinforcement Learning »
Wenhan Luo · Peng Sun · Fangwei Zhong · Wei Liu · Tong Zhang · Yizhou Wang -
2018 Oral: MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning »
Bo Zhao · Xinwei Sun · Yanwei Fu · Yuan Yao · Yizhou Wang