Detection of Emerging Infectious Diseases in Lung CT based on Spatial Anomaly Patterns

TL;DR

This paper introduces a novel method for detecting emerging infectious diseases in lung CT scans by analyzing spatial anomaly patterns and their distribution over time using deep learning representations.

Contribution

It proposes a new approach that combines anomaly detection with spatial distribution analysis to identify novel disease phenotypes in lung CT data.

Findings

Successfully detects emerging disease patterns in CT data

Utilizes deep neural network features for anomaly clustering

Demonstrates effectiveness in longitudinal patient cohorts

Abstract

Fast detection of emerging diseases is important for containing their spread and treating patients effectively. Local anomalies are relevant, but often novel diseases involve familiar disease patterns in new spatial distributions. Therefore, established local anomaly detection approaches may fail to identify them as new. Here, we present a novel approach to detect the emergence of new disease phenotypes exhibiting distinct patterns of the spatial distribution of lesions. We first identify anomalies in lung CT data, and then compare their distribution in a continually acquired new patient cohorts with historic patient population observed over a long prior period. We evaluate how accumulated evidence collected in the stream of patients is able to detect the onset of an emerging disease. In a gram-matrix based representation derived from the intermediate layers of a three-dimensional convolutional neural network, newly emerging clusters indicate emerging diseases.