Towards Reducing Aleatoric Uncertainty for Medical Imaging Tasks

TL;DR

This paper introduces a novel data augmentation method that leverages self-supervised uncertainty estimation to reduce aleatoric uncertainty in medical image segmentation, improving reliability without sacrificing accuracy.

Contribution

It proposes a new approach that uses self-supervised data uncertainty to enhance data augmentation for reducing aleatoric uncertainty in medical imaging tasks.

Findings

Significantly reduces aleatoric uncertainty in segmentation.

Achieves better or comparable performance to standard augmentation.

Effective on a benchmark medical imaging dataset.

Abstract

In safety-critical applications like medical diagnosis, certainty associated with a model's prediction is just as important as its accuracy. Consequently, uncertainty estimation and reduction play a crucial role. Uncertainty in predictions can be attributed to noise or randomness in data (aleatoric) and incorrect model inferences (epistemic). While model uncertainty can be reduced with more data or bigger models, aleatoric uncertainty is more intricate. This work proposes a novel approach that interprets data uncertainty estimated from a self-supervised task as noise inherent to the data and utilizes it to reduce aleatoric uncertainty in another task related to the same dataset via data augmentation. The proposed method was evaluated on a benchmark medical imaging dataset with image reconstruction as the self-supervised task and segmentation as the image analysis task. Our findings demonstrate the effectiveness of the proposed approach in significantly reducing the aleatoric uncertainty in the image segmentation task while achieving better or on-par performance compared to the standard augmentation techniques.