Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans

TL;DR

This paper introduces a novel graph-based spectral domain convolution method for multi-label anomaly classification in 3D chest CT scans, addressing limitations of existing deep learning models and demonstrating strong generalization and robustness.

Contribution

It proposes a structured spectral graph learning approach that models 3D CT scans as graphs, improving anomaly classification and cross-dataset generalization over traditional CNNs and Transformers.

Findings

Achieves competitive classification performance.

Exhibits strong cross-dataset generalization.

Robust to z-axis translation.

Abstract

With the increasing number of CT scan examinations, there is a need for automated methods such as organ segmentation, anomaly detection and report generation to assist radiologists in managing their increasing workload. Multi-label classification of 3D CT scans remains a critical yet challenging task due to the complex spatial relationships within volumetric data and the variety of observed anomalies. Existing approaches based on 3D convolutional networks have limited abilities to model long-range dependencies while Vision Transformers suffer from high computational costs and often require extensive pre-training on large-scale datasets from the same domain to achieve competitive performance. In this work, we propose an alternative by introducing a new graph-based approach that models CT scans as structured graphs, leveraging axial slice triplets nodes processed through spectral domain convolution to enhance multi-label anomaly classification performance. Our method exhibits strong cross-dataset generalization, and competitive performance while achieving robustness to z-axis translation. An ablation study evaluates the contribution of each proposed component.