A Retrospective Systematic Study on Hierarchical Sparse Query Transformer-assisted Ultrasound Screening for Early Hepatocellular Carcinoma

2025-02-06

AI Summary

Early ultrasound screening for hepatocellular carcinoma (HCC) suffers from low sensitivity and heavy dependence on operator expertise. Method: We propose the Hierarchical Sparse Query Transformer (HSQformer), the first framework integrating hierarchical sparse query mechanisms with a CNN–ViT hybrid architecture: CNNs extract local texture features, ViTs capture long-range lesion contextual dependencies, and sparse queries adaptively focus on multi-scale suspicious regions without complex hyperparameter tuning. The modular design enables plug-and-play clinical deployment. Contribution/Results: Evaluated across single-center, multi-center, and high-risk population cohorts, HSQformer achieves diagnostic accuracy comparable to experienced radiologists—surpassing state-of-the-art models (e.g., ConvNeXt, Swin Transformer) and significantly outperforming junior clinicians. It delivers a robust, clinically deployable AI solution for HCC early detection in resource-limited settings.

Technology Category

• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Hepatocellular carcinoma (HCC) ranks as the third leading cause of cancer-related mortality worldwide, with early detection being crucial for improving patient survival rates. However, early screening for HCC using ultrasound suffers from insufficient sensitivity and is highly dependent on the expertise of radiologists for interpretation. Leveraging the latest advancements in artificial intelligence (AI) in medical imaging, this study proposes an innovative Hierarchical Sparse Query Transformer (HSQformer) model that combines the strengths of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) to enhance the accuracy of HCC diagnosis in ultrasound screening. The HSQformer leverages sparse latent space representations to capture hierarchical details at various granularities without the need for complex adjustments, and adopts a modular, plug-and-play design philosophy, ensuring the model's versatility and ease of use. The HSQformer's performance was rigorously tested across three distinct clinical scenarios: single-center, multi-center, and high-risk patient testing. In each of these settings, it consistently outperformed existing state-of-the-art models, such as ConvNext and SwinTransformer. Notably, the HSQformer even matched the diagnostic capabilities of senior radiologists and comprehensively surpassed those of junior radiologists. The experimental results from this study strongly demonstrate the effectiveness and clinical potential of AI-assisted tools in HCC screening. The full code is available at https://github.com/Asunatan/HSQformer.

Problem

• Improves HCC detection accuracy
• Reduces reliance on radiologist expertise
• Enhances ultrasound screening sensitivity

Innovation

• Hierarchical Sparse Query Transformer
• Combines CNNs and Vision Transformers
• Modular plug-and-play design