Image analysis framework for infection monitoring

We present a novel framework for automatic extraction of the progress of an infection from time-series medical images, with application to pneumonia monitoring. In each image of a series, the lungs, which are the body components of interest in our study, are detected and delineated by a modified active shape model-based algorithm that is constrained by binary approximation masks. This algorithm offers resistance in the presence of infection manifestations that may distort the typical appearance of the body components of interest. The relative extent of the infection manifestations is assessed by supervised classification of samples acquired from the respective image regions. The samples are represented by multiple dissimilarity features fused according to a novel entropy-based weighted voting scheme offering nonparametric operation and robustness to outliers. The output of the proposed framework is a time series of structured data quantifying the relative extent of infection manifestations at the body components of interest over time. The results obtained indicate an improved performance over relevant state-of-the-art methods. The overall accuracy quantified by the area under receiver operating characteristic reaches 90.0 ± 2.1%. The effectiveness of the proposed framework to pneumonia monitoring, the generality, and the adaptivity of its methods open perspectives for application to other medical imaging domains.