A Causality-Inspired Model for Intima-Media Thickening Assessment in Ultrasound Videos

2025-03-16

AI Summary

Variations in scanning视角 across carotid ultrasound videos induce image style shifts, causing models to erroneously associate non-causal visual artifacts—such as lumen deformation—with intima-media thickness (IMT) progression, thereby undermining robustness in early assessment. To address this, we propose the first causal modeling framework for longitudinal IMT evaluation. Our approach comprises three novel modules: (1) Spurious Correlation Elimination (SCE), which disentangles style-related confounders; (2) Causal Equivalence Consolidation (CEC), which strengthens content-based causal relationships; and (3) Causal Transition Augmentation (CTA), which enforces temporal causal consistency. We integrate style-invariant learning, content-randomized adversarial optimization, text-guided contrastive learning, and auxiliary path modeling. Evaluated on a newly curated carotid ultrasound video dataset, our method achieves 86.93% accuracy—significantly surpassing state-of-the-art methods. The source code is publicly available.

Technology Category

• Machine Learning: Causal Learning
• Reasoning under Uncertainty: Causality
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Carotid atherosclerosis represents a significant health risk, with its early diagnosis primarily dependent on ultrasound-based assessments of carotid intima-media thickening. However, during carotid ultrasound screening, significant view variations cause style shifts, impairing content cues related to thickening, such as lumen anatomy, which introduces spurious correlations that hinder assessment. Therefore, we propose a novel causal-inspired method for assessing carotid intima-media thickening in frame-wise ultrasound videos, which focuses on two aspects: eliminating spurious correlations caused by style and enhancing causal content correlations. Specifically, we introduce a novel Spurious Correlation Elimination (SCE) module to remove non-causal style effects by enforcing prediction invariance with style perturbations. Simultaneously, we propose a Causal Equivalence Consolidation (CEC) module to strengthen causal content correlation through adversarial optimization during content randomization. Simultaneously, we design a Causal Transition Augmentation (CTA) module to ensure smooth causal flow by integrating an auxiliary pathway with text prompts and connecting it through contrastive learning. The experimental results on our in-house carotid ultrasound video dataset achieved an accuracy of 86.93%, demonstrating the superior performance of the proposed method. Code is available at href{https://github.com/xielaobanyy/causal-imt}{https://github.com/xielaobanyy/causal-imt}.

Problem

• Assesses carotid intima-media thickening in ultrasound videos
• Eliminates spurious correlations caused by style variations
• Enhances causal content correlations for accurate diagnosis

Innovation

• Spurious Correlation Elimination module removes style effects
• Causal Equivalence Consolidation strengthens content correlation
• Causal Transition Augmentation ensures smooth causal flow