Take Your Steps: Hierarchically Efficient Pulmonary Disease Screening via CT Volume Compression

2024-12-02

arXiv.org

AI Summary

To address the high computational cost and clinical deployment challenges of deep learning models in CT-based pulmonary disease screening, this paper proposes a three-stage progressive screening paradigm. First, a novel CT Volume Compression (CTVC) method selects the most discriminative axial slices, significantly reducing input dimensionality while better preserving lesion characteristics. Second, a lightweight classification model performs efficient coarse screening. Third, samples with high model uncertainty are escalated for physician review. This work innovatively integrates volumetric compression, lightweight inference, and uncertainty-driven human-AI collaboration. Evaluated on two public datasets, the proposed method achieves accuracy and recall comparable to full-convolutional baselines, accelerates inference by 50–70%, and demonstrates superior lesion preservation over existing CTVC approaches. The framework establishes a deployable, trustworthy paradigm for AI-assisted diagnosis in resource-constrained settings.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Deep learning models are widely used to process Computed Tomography (CT) data in the automated screening of pulmonary diseases, significantly reducing the workload of physicians. However, the three-dimensional nature of CT volumes involves an excessive number of voxels, which significantly increases the complexity of model processing. Previous screening approaches often overlook this issue, which undoubtedly reduces screening efficiency. Towards efficient and effective screening, we design a hierarchical approach to reduce the computational cost of pulmonary disease screening. The new approach re-organizes the screening workflows into three steps. First, we propose a Computed Tomography Volume Compression (CTVC) method to select a small slice subset that comprehensively represents the whole CT volume. Second, the selected CT slices are used to detect pulmonary diseases coarsely via a lightweight classification model. Third, an uncertainty measurement strategy is applied to identify samples with low diagnostic confidence, which are re-detected by radiologists. Experiments on two public pulmonary disease datasets demonstrate that our approach achieves comparable accuracy and recall while reducing the time by 50%-70% compared with the counterparts using full CT volumes. Besides, we also found that our approach outperforms previous cutting-edge CTVC methods in retaining important indications after compression.

Problem

• High computational cost hinders clinical adoption of CT-based pulmonary disease screening
• Current sub-sampling techniques compromise diagnostic integrity by losing critical information
• Need for efficient and reliable automated CT analysis in clinical practice

Innovation

• Cluster-based Sub-Sampling for efficient CT slice selection
• Hybrid Uncertainty Quantification with minimal overhead
• Lightweight framework reduces processing time by 60%