A Benchmark of Medical Out of Distribution Detection

07/08/2020
by   Tianshi Cao, et al.
50

There is a rise in the use of deep learning for automated medical diagnosis, most notably in medical imaging. Such an automated system uses a set of images from a patient to diagnose whether they have a disease. However, systems trained for one particular domain of images cannot be expected to perform accurately on images of a different domain. These images should be filtered out by an Out-of-Distribution Detection (OoDD) method prior to diagnosis. This paper benchmarks popular OoDD methods in three domains of medical imaging: chest x-rays, fundus images, and histology slides. Our experiments show that despite methods yielding good results on some types of out-of-distribution samples, they fail to recognize images close to the training distribution.

READ FULL TEXT

page 3

page 4

page 8

page 9

research
04/02/2019

A Strong Baseline for Domain Adaptation and Generalization in Medical Imaging

This work provides a strong baseline for the problem of multi-source mul...
research
12/22/2019

A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Tasks

Evaluation of Bayesian deep learning (BDL) methods is challenging. We of...
research
12/30/2020

Explainability Matters: Backdoor Attacks on Medical Imaging

Deep neural networks have been shown to be vulnerable to backdoor attack...
research
07/21/2021

Reading Race: AI Recognises Patient's Racial Identity In Medical Images

Background: In medical imaging, prior studies have demonstrated disparat...
research
09/07/2023

Cross-Task Attention Network: Improving Multi-Task Learning for Medical Imaging Applications

Multi-task learning (MTL) is a powerful approach in deep learning that l...
research
03/25/2022

Interpretation of Chest x-rays affected by bullets using deep transfer learning

The potential of deep learning, especially in medical imaging, initiated...
research
11/25/2019

A Unified Deep Learning Approach for Prediction of Parkinson's Disease

The paper presents a novel approach, based on deep learning, for diagnos...

Please sign up or login with your details

Forgot password? Click here to reset