CVApr 23, 2024

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

arXiv:2404.14747v11 citationsh-index: 10MICCAI
Originality Incremental advance
AI Analysis

This addresses motion correction in CT imaging for medical diagnostics, offering a robust solution that handles unforeseen motion variability, though it is incremental as it builds on existing score-based models.

The paper tackles motion artifacts in CT images by training a score-based model to estimate the probability density of clean head CT images, then using likelihood as a metric to optimize motion parameters and reduce artifacts, achieving performance comparable to state-of-the-art methods without needing motion-affected data.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes