Detection of Emerging Infectious Diseases in Lung CT based on Spatial Anomaly Patterns
This work addresses the challenge of early disease detection for public health and medical professionals, but it appears incremental as it builds on existing anomaly detection methods with a focus on spatial patterns.
The paper tackles the problem of detecting emerging infectious diseases in lung CT scans by identifying novel spatial distributions of lesions, and it evaluates the approach's ability to detect disease onset using accumulated evidence from patient cohorts.
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.