Guo, XiaoyuanDuan, JialiPurkayastha, SaptarshiTrivedi, HariGichoya, Judy WawiraBanerjee, Imon2022-10-052022-10-052022Guo, X., Duan, J., Purkayastha, S., Trivedi, H., Gichoya, J. W., & Banerjee, I. (2022). OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System. arXiv preprint arXiv:2204.03074. https://doi.org/10.48550/arXiv.2204.03074https://hdl.handle.net/1805/30212Improving the retrieval relevance on noisy datasets is an emerging need for the curation of a large-scale clean dataset in the 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 similarities 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, nintra, ninter) sampling strategy, where intra-class negatives nintra are sampled from bins of the same class other than the bin anchor a belongs to, while niner 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.enAttribution-NonCommercial-ShareAlike 4.0 Internationalmedical image retrievaldeep metric learningoutlier detectionArticle