Domain Generalization by Learning from Privileged Medical Imaging Information
This addresses domain shift issues in medical imaging for applications like hospital or machine variations, offering a novel approach that is incremental but specific to medical contexts.
The paper tackles the problem of domain generalization in medical imaging by proposing Learning from Privileged Medical Imaging Information (LPMII), which uses privileged information like tumor shape or location to improve model performance on out-of-distribution data, increasing classification accuracy from 0.911 to 0.934 for retinal fluid severity prediction.
Learning the ability to generalize knowledge between similar contexts is particularly important in medical imaging as data distributions can shift substantially from one hospital to another, or even from one machine to another. To strengthen generalization, most state-of-the-art techniques inject knowledge of the data distribution shifts by enforcing constraints on learned features or regularizing parameters. We offer an alternative approach: Learning from Privileged Medical Imaging Information (LPMII). We show that using some privileged information such as tumor shape or location leads to stronger domain generalization ability than current state-of-the-art techniques. This paper demonstrates that by using privileged information to predict the severity of intra-layer retinal fluid in optical coherence tomography scans, the classification accuracy of a deep learning model operating on out-of-distribution data improves from $0.911$ to $0.934$. This paper provides a strong starting point for using privileged information in other medical problems requiring generalization.