3D unsupervised anomaly detection and localization through virtual multi-view projection and reconstruction: Clinical validation on low-dose chest computed tomography

TL;DR

This paper introduces an unsupervised deep learning method for 3D anomaly detection and localization in low-dose chest CT scans, using virtual multi-view projection and reconstruction, validated with high accuracy on clinical data.

Contribution

It presents a novel unsupervised approach that only requires healthy data for training, improving detection accuracy and enabling 3D localization without disease annotations.

Findings

Achieved 10% higher patient-level detection accuracy (AUC 0.959) compared to supervised methods.

Localized anomalies with 93% accuracy in clinical validation.

Utilized multi-view 2D projections for enhanced 3D recognition and localization.

Abstract

Computer-aided diagnosis for low-dose computed tomography (CT) based on deep learning has recently attracted attention as a first-line automatic testing tool because of its high accuracy and low radiation exposure. However, existing methods rely on supervised learning, imposing an additional burden to doctors for collecting disease data or annotating spatial labels for network training, consequently hindering their implementation. We propose a method based on a deep neural network for computer-aided diagnosis called virtual multi-view projection and reconstruction for unsupervised anomaly detection. Presumably, this is the first method that only requires data from healthy patients for training to identify three-dimensional (3D) regions containing any anomalies. The method has three key components. Unlike existing computer-aided diagnosis tools that use conventional CT slices as the network input, our method 1) improves the recognition of 3D lung structures by virtually projecting an extracted 3D lung region to obtain two-dimensional (2D) images from diverse views to serve as network inputs, 2) accommodates the input diversity gain for accurate anomaly detection, and 3) achieves 3D anomaly/disease localization through a novel 3D map restoration method using multiple 2D anomaly maps. The proposed method based on unsupervised learning improves the patient-level anomaly detection by 10% (area under the curve, 0.959) compared with a gold standard based on supervised learning (area under the curve, 0.848), and it localizes the anomaly region with 93% accuracy, demonstrating its high performance.