OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System

Xiaoyuan Guo, Jiali Duan, Saptarshi Purkayastha, Hari Trivedi, Judy Wawira Gichoya, Imon Banerjee
2022 Proceedings of the 2022 International Conference on Multimedia Retrieval  
Improving the retrieval relevance on noisy datasets is an emerging need for the curation of a large-scale clean dataset in medical domain. While existing methods can be applied for class-wise retrieval (aka. inter-class), they cannot distinguish the granularity of likeness within the same class (aka. intra-class). The problem is exacerbated on medical external datasets, where noisy samples of the same class are treated equally during training. Our goal is to identify both intra/inter-class
more » ... arities for fine-grained retrieval. To achieve this, we propose an Outlier-Sensitive Content-based rAdiologhy Retrieval System (OSCARS), consisting of two steps. First, we train an outlier detector on a clean internal dataset in an unsupervised manner. Then we use the trained detector to generate the anomaly scores on the external dataset, whose distribution will be used to bin intra-class variations. Second, we propose a quadruplet (𝑎, 𝑝, 𝑛 𝑖𝑛𝑡𝑟𝑎 , 𝑛 𝑖𝑛𝑡𝑒𝑟 ) sampling strategy, where intra-class negatives 𝑛 𝑖𝑛𝑡𝑟𝑎 are sampled from bins of the same class other than the bin anchor 𝑎 belongs to, while 𝑛 𝑖𝑛𝑡𝑒𝑟 are randomly sampled from inter-classes. We suggest a weighted metric learning objective to balance the intra and inter-class feature learning. We experimented on two representative public radiography datasets. Experiments show the effectiveness of our approach. The code is available at https://github.com/XiaoyuanGuo/oscars. CCS CONCEPTS • Information systems → Learning to rank.
doi:10.1145/3512527.3531425 fatcat:iiqp22hksfdttprkye2fophb5e