Aleatoric uncertainty estimation with test-time augmentation for medical image segmentation with convolutional neural networks

07/19/2018
by   Guotai Wang, et al.
12

Despite the state-of-the-art performance for medical image segmentation, deep convolutional neural networks (CNNs) have rarely provided uncertainty estimations regarding their segmentation outputs, e.g., model (epistemic) and image-based (aleatoric) uncertainties. In this work, we analyze these different types of uncertainties for CNN-based 2D and 3D medical image segmentation tasks. We additionally propose a test-time augmentation-based aleatoric uncertainty to analyze the effect of different transformations of the input image on the segmentation output. Test-time augmentation has been previously used to improve segmentation accuracy, yet not been formulated in a consistent mathematical framework. Hence, we also propose a theoretical formulation of test-time augmentation, where a distribution of the prediction is estimated by Monte Carlo simulation with prior distributions of parameters in an image acquisition model that involves image transformations and noise. We compare and combine our proposed aleatoric uncertainty with model uncertainty. Experiments with segmentation of fetal brains and brain tumors from 2D and 3D Magnetic Resonance Images (MRI) showed that 1) the test-time augmentation-based aleatoric uncertainty provides a better uncertainty estimation than calculating the test-time dropout-based model uncertainty alone and helps to reduce overconfident incorrect predictions, and 2) our test-time augmentation outperforms a single-prediction baseline and dropout-based multiple predictions.

READ FULL TEXT

page 6

page 8

page 9

research
07/19/2018

Test-time augmentation with uncertainty estimation for deep learning-based medical image segmentation

Data augmentation has been widely used for training deep learning system...
research
04/12/2020

Improving Calibration and Out-of-Distribution Detection in Medical Image Segmentation with Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are powerful medical image segmenta...
research
04/09/2020

Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation

Convolutional Neural Networks (CNNs) work very well for supervised learn...
research
05/05/2021

CUAB: Convolutional Uncertainty Attention Block Enhanced the Chest X-ray Image Analysis

In recent years, convolutional neural networks (CNNs) have been successf...
research
03/01/2022

How certain are your uncertainties?

Having a measure of uncertainty in the output of a deep learning method ...
research
07/11/2023

SAM-U: Multi-box prompts triggered uncertainty estimation for reliable SAM in medical image

Recently, Segmenting Anything has taken an important step towards genera...
research
10/03/2018

PADDIT: Probabilistic Augmentation of Data using Diffeomorphic Image Transformation

For proper generalization performance of convolutional neural networks (...

Please sign up or login with your details

Forgot password? Click here to reset