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

Abstract

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 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, 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.

Enhanced Diagnostic Accuracy in Musculoskeletal Radiography: A Comprehensive Ensemble Approach of Deep Learning Models

“…To learn the selective features for the retrieval task in the MURA dataset a pretrained feature extractor network and a Siamese network architecture. The results show that the proposed approach -surpassed several state-of-the-art methods in terms of retrieval accuracy and robustness to corrupt/noisy samples [7].…”