Bayesian approaches for Quantifying Clinicians' Variability in Medical Image Quantification

2022-07-05 · Jaeik Jeon, Yeonggul Jang, Youngtaek Hong, Hackjoon Shim, Sekeun Kim

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.

📄 PDF Abstract BibTeX arXiv:2207.01868

Code (0)

등록된 구현이 없습니다.

Tasks

Segmentation

Uncertainty-driven ensembles of deep architectures for multiclass classification. Application to COVID-19 diagnosis in chest X-ray images

2020-11-27 · Juan E. Arco, A. Ortiz, J. Ramirez, F. J. Martinez-Murcia 외

Respiratory diseases kill million of people each year. Diagnosis of these pathologies is a manual, time-consuming process that has inter and intra-observer variability, delaying diagnosis and treatment. The recent COVID-…

Classification COVID-19 Diagnosis General Classification

QUBIQ: Uncertainty Quantification for Biomedical Image Segmentation Challenge

2024-03-19 · Hongwei Bran Li, Fernando Navarro, Ivan Ezhov, Amirhossein Bayat 외

Uncertainty in medical image segmentation tasks, especially inter-rater variability, arising from differences in interpretations and annotations by various experts, presents a significant challenge in achieving consisten…

Image Segmentation Medical Image Segmentation Segmentation Semantic Segmentation+1

Estimating Uncertainty and Interpretability in Deep Learning for Coronavirus (COVID-19) Detection

2020-03-22 · Biraja Ghoshal, Allan Tucker

Deep Learning has achieved state of the art performance in medical imaging. However, these methods for disease detection focus exclusively on improving the accuracy of classification or predictions without quantifying un…

COVID-19 Diagnosis Deep Learning Diagnostic

Bayesian Spillover Graphs for Dynamic Networks

2022-03-03 · Grace Deng, David S. Matteson

We present Bayesian Spillover Graphs (BSG), a novel method for learning temporal relationships, identifying critical nodes, and quantifying uncertainty for multi-horizon spillover effects in a dynamic system. BSG leverag…

Time Series Time Series Analysis Uncertainty Quantification

Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis

2024-06-11 · Zeinab Abboud, Herve Lombaert, Samuel Kadoury

Efficiently quantifying predictive uncertainty in medical images remains a challenge. While Bayesian neural networks (BNN) offer predictive uncertainty, they require substantial computational resources to train. Although…

Medical Image Analysis Uncertainty Quantification