@article{Alibakhshi:2026:10.1016/j.ultrasmedbio.2026.09.003,
author = {Alibakhshi, A and Fernandes, P and Serej, ND and Francis, DP and Zolgharni, M},
doi = {10.1016/j.ultrasmedbio.2026.09.003},
journal = {Ultrasound Med Biol},
title = {From Relative Annotation to Pairwise Learning for Assessing Echocardiographic Rotational Alignment.},
url = {http://dx.doi.org/10.1016/j.ultrasmedbio.2026.09.003},
year = {2026}
}

Download

TY  - JOUR
AB  - 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.
AU  - Alibakhshi,A
AU  - Fernandes,P
AU  - Serej,ND
AU  - Francis,DP
AU  - Zolgharni,M
DO  - 10.1016/j.ultrasmedbio.2026.09.003
PY  - 2026///
TI  - From Relative Annotation to Pairwise Learning for Assessing Echocardiographic Rotational Alignment.
T2  - Ultrasound Med Biol
UR  - http://dx.doi.org/10.1016/j.ultrasmedbio.2026.09.003
UR  - https://www.ncbi.nlm.nih.gov/pubmed/42855400
ER  - 

Download