English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper aims to solve a fundamental problem in intensity-based 2D/3Dregistration, which concerns the limited capture range and need for very goodinitialization of state-of-the-art image registration methods. We propose aregression approach that learns to predict rotation and translations ofarbitrary 2D image slices from 3D volumes, with respect to a learned canonicalatlas co-ordinate system. To this end, we utilize Convolutional Neural Networks(CNNs) to learn the highly complex regression function that maps 2D imageslices into their correct position and orientation in 3D space. Our approach isattractive in challenging imaging scenarios, where significant subject motioncomplicates reconstruction performance of 3D volumes from 2D slice data. Weextensively evaluate the effectiveness of our approach quantitatively onsimulated MRI brain data with extreme random motion. We further demonstratequalitative results on fetal MRI where our method is integrated into a fullreconstruction and motion compensation pipeline. With our CNN regressionapproach we obtain an average prediction error of 7mm on simulated data, andconvincing reconstruction quality of images of very young fetuses whereprevious methods fail. We further discuss applications to Computed Tomographyand X-ray projections. Our approach is a general solution to the 2D/3Dinitialization problem. It is computationally efficient, with prediction timesper slice of a few milliseconds, making it suitable for real-time scenarios.

Predicting Slice-to-Volume Transformation in Presence of Arbitrary Subject Motion