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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Anatomical landmark correspondences in medical images can provide additionalguidance information for the alignment of two images, which, in turn, iscrucial for many medical applications. However, manual landmark annotation islabor-intensive. Therefore, we propose an end-to-end deep learning approach toautomatically detect landmark correspondences in pairs of two-dimensional (2D)images. Our approach consists of a Siamese neural network, which is trained toidentify salient locations in images as landmarks and predict matchingprobabilities for landmark pairs from two different images. We trained ourapproach on 2D transverse slices from 168 lower abdominal Computed Tomography(CT) scans. We tested the approach on 22,206 pairs of 2D slices with varyinglevels of intensity, affine, and elastic transformations. The proposed approachfinds an average of 639, 466, and 370 landmark matches per image pair forintensity, affine, and elastic transformations, respectively, with spatialmatching errors of at most 1 mm. Further, more than 99% of the landmark pairsare within a spatial matching error of 2 mm, 4 mm, and 8 mm for image pairswith intensity, affine, and elastic transformations, respectively. Toinvestigate the utility of our developed approach in a clinical setting, wealso tested our approach on pairs of transverse slices selected from follow-upCT scans of three patients. Visual inspection of the results revealed landmarkmatches in both bony anatomical regions as well as in soft tissues lackingprominent intensity gradients.

An End-to-end Deep Learning Approach for Landmark Detection and Matching in Medical Images