Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scans
This addresses the need for automated anomaly classification to assist radiologists, though it is incremental as it builds on graph-based methods for medical imaging.
The paper tackles multi-label classification of anomalies in 3D chest CT scans by proposing a graph-based approach that models scans as structured graphs with spectral domain convolution, achieving competitive performance and strong cross-dataset generalization.
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.