Alibakhshi, Alireza ORCID: https://orcid.org/0009-0008-7729-7320, Fernandes, Patricia, Serej, Nasim Dadashi, Francis, Darrel P. and Zolgharni, Massoud ORCID: https://orcid.org/0000-0003-0904-2904 (2026) From relative annotation to pairwise learning for assessing Echocardiographic Rotational Alignment. Ultrasound in Medicine & Biology. ISSN 03015629 (In Press)

Preview

PDF 1-s2.0-S030156292600356X-main.pdf - Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

Objective
To evaluate whether preserving relative expert-derived structure during model training improves the automated assessment of rotational misalignment in apical four-chamber echocardiographic images.

Methods
A multi-expert dataset of apical four-chamber images was annotated using multiple-image ranking to derive consensus rotational orderings along a clockwise–to–anti-clockwise continuum. Conventional pointwise regression models were compared with shared-weight pairwise models that received two images and predicted the signed difference between their consensus rotational scores. Performance was evaluated across three independent expert-ranked test sets using pairwise agreement and Spearman correlation. Robustness was further assessed using leave-one-expert-out and cycle-consistency analyses, with saliency-based visualization used to examine the image regions influencing predictions.

Results
Pairwise learning increased the mean pairwise agreement from 74.86% to 84.29% and the mean Spearman correlation from 67.74% to 85.43% compared with pointwise regression. The best pairwise model achieved a pairwise agreement of up to 87.81% and a Spearman correlation of up to 91.23%. The performance remained stable when individual annotators were excluded, and a cycle-consistency analysis demonstrated few cyclic preferences on independent test data. Visual explanation maps indicated model attention to clinically relevant cardiac anatomy.

Conclusion
Training directly on relative expert-derived structure improved agreement with multi-expert consensus compared with conventional pointwise regression. Pairwise learning therefore provides a robust framework for assessing qualitative, continuous echocardiographic image-quality attributes such as rotational alignment.

Item Type:	Article
Identifier:	10.1016/j.ultrasmedbio.2026.09.003
Keywords:	Echocardiography ; Qualitative image quality assessment ; Rotational misalignment ; Pairwise learning ; Relative annotation ; Expert consensus
Subjects:	Computing > Intelligent systems Medicine and health
Date Deposited:	24 Oct 2026
Dates:	Date Publication status 2 September 2026 Accepted 10 September 2026 Published Online
School, department or research centre:	THRIVE (The Centre for Translational Healthcare Research, Innovation, Vision, and Excellence) School of Computing and Engineering
Keywords:	Echocardiography ; Qualitative image quality assessment ; Rotational misalignment ; Pairwise learning ; Relative annotation ; Expert consensus
URI:	https://repository.uwl.ac.uk/id/eprint/15541

Downloads

Actions (admin access)