A Strong Baseline for Domain Adaptation and Generalization in Medical Imaging

04/02/2019

∙

This work provides a strong baseline for the problem of multi-source multi-target domain adaptation and generalization in medical imaging. Using a diverse collection of ten chest X-ray datasets, we empirically demonstrate the benefits of training medical imaging deep learning models on varied patient populations for generalization to out-of-sample domains.

READ FULL TEXT

A Strong Baseline for Domain Adaptation and Generalization in Medical Imaging

Unsupervised domain adaptation for medical imaging segmentation with self-ensembling

A Benchmark of Medical Out of Distribution Detection

Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models

An Empirical Framework for Domain Generalization in Clinical Settings

In-context Cross-Density Adaptation on Noisy Mammogram Abnormalities Detection

Deep Feature Learning from a Hospital-Scale Chest X-ray Dataset with Application to TB Detection on a Small-Scale Dataset

Multi-institution encrypted medical imaging AI validation without data sharing

A Strong Baseline for Domain Adaptation and Generalization in Medical Imaging

Related Research

Unsupervised domain adaptation for medical imaging segmentation with self-ensembling

A Benchmark of Medical Out of Distribution Detection

Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models

An Empirical Framework for Domain Generalization in Clinical Settings

In-context Cross-Density Adaptation on Noisy Mammogram Abnormalities Detection

Deep Feature Learning from a Hospital-Scale Chest X-ray Dataset with Application to TB Detection on a Small-Scale Dataset

Multi-institution encrypted medical imaging AI validation without data sharing