Differentiable Score-Based Likelihoods: Learning CT Motion Compensation from Clean Images

Thies M, Maul N, Mei S, Pfaff L, Vysotskaya N, Gu M, Utz J, Possart D, Folle L, Wagner F, Maier A (2024)

Publication Type: Conference contribution

Publication year: 2024

Journal

Publisher: Springer

Series: Lecture Notes in Computer Science

City/Town: Cham

Pages Range: 253-263

Conference Proceedings Title: Medical Image Computing and Computer Assisted Intervention – MICCAI 2024

ISBN: 9783031721038

DOI: 10.1007/978-3-031-72104-5_25

Abstract

Motion artifacts can compromise the diagnostic value of computed tomography (CT) images. Motion correction approaches require a per-scan estimation of patient-specific motion patterns. In this work, we train a score-based model to act as a probability density estimator for clean head CT images. Given the trained model, we quantify the deviation of a given motion-affected CT image from the ideal distribution through likelihood computation. We demonstrate that the likelihood can be utilized as a surrogate metric for motion artifact severity in the CT image facilitating the application of an iterative, gradient-based motion compensation algorithm. By optimizing the underlying motion parameters to maximize likelihood, our method effectively reduces motion artifacts, bringing the image closer to the distribution of motion-free scans. Our approach achieves comparable performance to state-of-the-art methods while eliminating the need for a representative data set of motion-affected samples. This is particularly advantageous in real-world applications, where patient motion patterns may exhibit unforeseen variability, ensuring robustness without implicit assumptions about recoverable motion types.

Authors with CRIS profile

How to cite

APA:

Thies, M., Maul, N., Mei, S., Pfaff, L., Vysotskaya, N., Gu, M.,... Maier, A. (2024). Differentiable Score-Based Likelihoods: Learning CT Motion Compensation from Clean Images. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 (pp. 253-263). Cham: Springer.

MLA:

Thies, Mareike, et al. "Differentiable Score-Based Likelihoods: Learning CT Motion Compensation from Clean Images." Proceedings of the Medical Image Computing and Computer Assisted Intervention – MICCAI 2024 Cham: Springer, 2024. 253-263.

BibTeX: Download