Patch-Based Sparse Representation For Bacterial Detection
This work addresses bacterial detection in medical imaging for clinicians, but it is incremental as it builds on existing sparse representation and ADMM techniques.
The paper tackles bacterial detection in optical endomicroscopy images by proposing an unsupervised patch-based sparse representation method, which models images as linear combinations of background structures and sparse outliers for anomalies, and reports good detection and correlation performance with clinician counts in simulations on two ex vivo lung datasets.
In this paper, we propose an unsupervised approach for bacterial detection in optical endomicroscopy images. This approach splits each image into a set of overlapping patches and assumes that observed intensities are linear combinations of the actual intensity values associated with background image structures, corrupted by additive Gaussian noise and potentially by a sparse outlier term modelling anomalies (which are considered to be candidate bacteria). The actual intensity term representing background structures is modelled as a linear combination of a few atoms drawn from a dictionary which is learned from bacteria-free data and then fixed while analyzing new images. The bacteria detection task is formulated as a minimization problem and an alternating direction method of multipliers (ADMM) is then used to estimate the unknown parameters. Simulations conducted using two ex vivo lung datasets show good detection and correlation performance between bacteria counts identified by a trained clinician and those of the proposed method.