Uncertainty-Aware Test-Time Adaptation for Inverse Consistent Diffeomorphic Lung Image Registration

Muhammad F. A Chaudhary; Stephanie M Aguilera; Arie Nakhmani; Joseph M Reinhardt; Surya P Bhatt; Sandeep Bodduluri

doi:10.48550/arxiv.2411.07567

Back

Uncertainty-Aware Test-Time Adaptation for Inverse Consistent Diffeomorphic Lung Image Registration

Preprint

Open access

Uncertainty-Aware Test-Time Adaptation for Inverse Consistent Diffeomorphic Lung Image Registration

Muhammad F. A Chaudhary, Stephanie M Aguilera, Arie Nakhmani, Joseph M Reinhardt, Surya P Bhatt and Sandeep Bodduluri

ArXiV.org

Cornell University

11/12/2024

DOI: 10.48550/arxiv.2411.07567

Files and links (1)

url

https://doi.org/10.48550/arxiv.2411.07567View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Diffeomorphic deformable image registration ensures smooth invertible transformations across inspiratory and expiratory chest CT scans. Yet, in practice, deep learning-based diffeomorphic methods struggle to capture large deformations between inspiratory and expiratory volumes, and therefore lack inverse consistency. Existing methods also fail to account for model uncertainty, which can be useful for improving performance. We propose an uncertainty-aware test-time adaptation framework for inverse consistent diffeomorphic lung registration. Our method uses Monte Carlo (MC) dropout to estimate spatial uncertainty that is used to improve model performance. We train and evaluate our method for inspiratory-to-expiratory CT registration on a large cohort of 675 subjects from the COPDGene study, achieving a higher Dice similarity coefficient (DSC) between the lung boundaries (0.966) compared to both VoxelMorph (0.953) and TransMorph (0.953). Our method demonstrates consistent improvements in the inverse registration direction as well with an overall DSC of 0.966, higher than VoxelMorph (0.958) and TransMorph (0.956). Paired t-tests indicate statistically significant improvements.

Computer Science - Computer Vision and Pattern Recognition

Computer Science - Learning

Details

Title: Subtitle: Uncertainty-Aware Test-Time Adaptation for Inverse Consistent Diffeomorphic Lung Image Registration
Creators: Muhammad F. A Chaudhary - University of Alabama at Birmingham
Stephanie M Aguilera - University of Alabama at Birmingham
Arie Nakhmani - University of Alabama at Birmingham
Joseph M Reinhardt - University of Iowa
Surya P Bhatt - University of Alabama at Birmingham
Sandeep Bodduluri - University of Alabama at Birmingham
Resource Type: Preprint
Publication Details: ArXiV.org
DOI: 10.48550/arxiv.2411.07567
ISSN: 2331-8422
Publisher: Cornell University; Ithaca, New York
Language: English
Date posted: 11/12/2024
Academic Unit: Roy J. Carver Department of Biomedical Engineering; Radiology
Record Identifier: 9984747817002771

Metrics

55 Record Views