Medical Image Imputation From Image Collections

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 data sets of clinical images contain a wealth of information, time constraints during acquisition result in sparse scans...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2019-02, Vol.38 (2), p.504-514
Main Authors: Dalca, Adrian V., Bouman, Katherine L., Freeman, William T., Rost, Natalia S., Sabuncu, Mert R., Golland, Polina
Format: Article
Language:English
Subjects:
Algorithms
Biomedical imaging
Brain
brain scans
Brain slice preparation
clinical scans
Computational neuroscience
Data collection
Data models
Data processing
Domains
High resolution
Image acquisition
Image analysis
Image processing
Image resolution
Image restoration
Imputation
Magnetic resonance imaging
Medical imaging
Missing data
MRI
sparse slices
State of the art
Statistics
super-resolution
thick slices
Three-dimensional displays
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 data sets of clinical images contain a wealth of information, time constraints during acquisition result in sparse scans that fail to capture much of the anatomy. These characteristics often render computational analysis impractical as many image analysis algorithms tend to fail when applied to such images. Highly specialized algorithms that explicitly handle sparse slice spacing do not generalize well across problem domains. In contrast, we aim to enable the application of existing algorithms that were originally developed for high-resolution research scans to significantly undersampled scans. We introduce a generative model that captures a fine-scale anatomical structure across subjects in clinical image collections and derives an algorithm for filling in the missing data in scans with large inter-slice spacing. Our experimental results demonstrate that the resulting method outperforms the state-of-the-art upsampling super-resolution techniques, and promises to facilitate subsequent analysis not previously possible with scans of this quality. Our implementation is freely available at https://github.com/adalca/papago.
ISSN:0278-0062
1558-254X
DOI:10.1109/TMI.2018.2866692