English

Bayesian approaches for Quantifying Clinicians' Variability in Medical Image Quantification

Image and Video Processing 2022-07-07 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

Medical imaging, including MRI, CT, and Ultrasound, plays a vital role in clinical decisions. Accurate segmentation is essential to measure the structure of interest from the image. However, manual segmentation is highly operator-dependent, which leads to high inter and intra-variability of quantitative measurements. In this paper, we explore the feasibility that Bayesian predictive distribution parameterized by deep neural networks can capture the clinicians' inter-intra variability. By exploring and analyzing recently emerged approximate inference schemes, we evaluate whether approximate Bayesian deep learning with the posterior over segmentations can learn inter-intra rater variability both in segmentation and clinical measurements. The experiments are performed with two different imaging modalities: MRI and ultrasound. We empirically demonstrated that Bayesian predictive distribution parameterized by deep neural networks could approximate the clinicians' inter-intra variability. We show a new perspective in analyzing medical images quantitatively by providing clinical measurement uncertainty.

Keywords

Cite

@article{arxiv.2207.01868,
  title  = {Bayesian approaches for Quantifying Clinicians' Variability in Medical Image Quantification},
  author = {Jaeik Jeon and Yeonggul Jang and Youngtaek Hong and Hackjoon Shim and Sekeun Kim},
  journal= {arXiv preprint arXiv:2207.01868},
  year   = {2022}
}

Comments

Interpretable Machine Learning in Healthcare

R2 v1 2026-06-24T12:14:09.073Z