Uncertainty quantification using Bayesian neural networks in classification: Application to biomedical image segmentation

By Yongchan Kwon, Joong-Ho Won, Beomjoon Kim, Myunghee Cho Paik. Computational Statistics & Data Analysis, 2020

419 citations recorded by the source corpus.

Abstract Most recent research of deep neural networks in the field of computer vision has focused on improving performances of point predictions by developing network architectures or learning algorithms. Reliable uncertainty quantification accompanied by point estimation can lead to a more informed decision, and the quality of prediction can be improved. In this paper, we invoke a Bayesian neural network and propose a natural way of quantifying uncertainties in classification problems by decomposing the moment-based predictive uncertainty into two parts: aleatoric and epistemic uncertainty. The proposed method takes into account the discrete nature of the outcome, yielding the correct interpretation of each uncertainty. We demonstrate that the proposed uncertainty quantification method provides additional insights into the point prediction using two Ischemic Stroke Lesion Segmentation Challenge datasets and the Digital Retinal Images for Vessel Extraction dataset.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, Medical Imaging

View Paper: https://doi.org/10.1016/J.CSDA.2019.106816

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Sridha Sridharan
2. Simon Denman
3. Qiang Zhai
4. Deng-Ping Fan
5. Clinton Fookes
6. Tharindu Fernando
7. Fan Yang
8. Xin Li

In Computer Vision and Pattern Recognition

1. Fan Yang
2. Qiang Zhai
3. Xin Li
4. Rui Huang
5. Sridha Sridharan
6. Simon Denman
7. Deng-Ping Fan
8. Clinton Fookes

In Radiology, Nuclear Medicine and Imaging

1. Simon Denman
2. Deng-Ping Fan
3. Clinton Fookes

Citations in the corpus

• Deep Learning for Medical Anomaly Detection – A Survey (2020, methodology): “Furthermore, Bayesian uncertainty estimation has been applied for estimating the quality of medical image segmentation [135], [136], [137], and sclerosis lesion detection [138].”
• Uncertainty-Guided Transformer Reasoning for Camouflaged Object Detection (2021, methodology): “These techniques have been successfully applied to modeling uncertainty for semantic segmentation / scene parsing [19, 23], person reidentification [56] and medical image analysis [28].”