Subspace-Guided Semantic and Topological Invariant Registration for Annotation-Free Ultrasound Plane Quality Control

2026-05-24

AI Summary

This work addresses the challenges in ultrasound image quality control, where pseudo-labels are often compromised by reliance on manual annotations or spatial deformations. To overcome these limitations, the authors propose STRIQ, a framework that reframes unsupervised quality assessment as a subspace-guided consistency measurement task. STRIQ employs a latent registration aligner to establish hierarchical feature correspondences between query images and self-distilled anchors, and introduces a novel variance-spectrum criterion to automatically distill anatomically stable prototypes. Furthermore, it incorporates Orthogonal Knowledge Subspace (OKS) decomposition to disentangle representations across anatomical planes, enabling fine-grained expert collaboration and suppressing cross-plane interference. Evaluated on the US4QA and CAMUS datasets, STRIQ significantly outperforms existing unsupervised methods and achieves the highest correlation with clinical quality ratings.

Abstract

Reliable quality control (QC) of ultrasound images is essential for both real-time acquisition guidance and retrospective clinical audit, yet existing approaches rely heavily on per-plane annotations, or employ pseudo-labeling prone to systematic bias under spatial deformations inherent in clinical acquisition. We present STRIQ, a registration-driven framework that recasts annotation-free US plane quality control as a subspace-guided consistency measurement problem. Specifically, STRIQ introduces a Latent Registration Aligner (LRA) to establish hierarchical feature space correspondences between query images and variance-driven anchors, which are autonomously distilled from unlabeled data via a variance spectrum criterion to serve as structurally stable prototypes. To further disambiguate anatomical planes and mitigate negative knowledge transfer, we propose an Orthogonal Knowledge Subspace (OKS) module. The OKS decomposes plane-specific representations into mutually orthogonal subspaces, enabling fine-grained expert collaboration while preventing inter-plane interference, ensuring that the quality metric is grounded in principled subspace proximity. Extensive experiments on the in-house US4QA and public CAMUS datasets demonstrate that STRIQ achieves state-of-the-art correlation with clinical quality scores, establishing a new paradigm for annotation-free, real-time reliable ultrasound quality control. Our code is available at https://github.com/zhcz328/STRIQ.

Problem

• ultrasound quality control
• annotation-free
• image registration
• subspace learning
• clinical audit

Innovation

• annotation-free
• subspace-guided registration
• orthogonal knowledge subspace
• ultrasound quality control
• latent registration aligner