Population Based Image Imputation

Abstract

We present an algorithm for creating high resolution anatomically plausible images consistent with acquired clinical brain MRI scans with large inter-slice spacing. Although large databases of clinical images contain a wealth of information, medical acquisition constraints result in sparse scans that miss much of the anatomy. These characteristics often render computational analysis impractical as standard processing algorithms tend to fail when applied to such images. Highly specialized or application-specific algorithms that explicitly handle sparse slice spacing do not generalize well across problem domains. In contrast, our goal is to enable application of existing algorithms that were originally developed for high resolution research scans to significantly undersampled scans. We introduce a model that captures fine-scale anatomical similarity across subjects in clinical image collections and use it to fill in the missing data in scans with large slice spacing. Our experimental results demonstrate that the proposed method outperforms current upsampling methods and promises to facilitate subsequent analysis not previously possible with scans of this quality.

Model-based multi-parameter mapping

“…One possibility, inspired by Brudfors, Ashburner, Nachev, Balbastre, 2019 , Brudfors, Balbastre, Flandin, Nachev, Ashburner, 2020 , is to include a multivariate Gaussian mixture model of the log-parameter maps, with learned tissue parameters (means, covariances, tissue probability maps). Alternatively, priors based on learned dictionaries of patches could be used ( Dalca et al., 2017 ).…”

Model-based multi-parameter mapping

“…One possibility, inspired by Brudfors et al (2019Brudfors et al ( , 2020, is to include a multivariate Gaussian mixture model of the log-parameter maps, with learned tissue parameters (means, covariances, tissue probability maps). Alternatively, priors based on learned dictionaries of patches could be used (Dalca et al, 2017).…”

Unsupervised Data Imputation via Variational Inference of Deep Subspaces

“…where W O selects the rows of W that correspond to observed entries in y. Using the proposed learning strategy (9) and the pseudo-inverse of W , we can choose the approximating posterior,…”

“…Our work is motivated by a challenging real world medical imaging problem. In many clinical settings, medical image scanning time is limited by cost and physical or patient care constraints, leading to severely under-sampled images [8, 9,43]. For example, in many clinical settings, only every sixth 2D slice is acquired in a 3D MRI scan, resulting in 83% of the anatomical data being missing.…”