K-Means for Noise-Insensitive Multi-Dimensional Feature Learning
This addresses the challenge of analyzing complex signals in imaging modalities like Photoacoustic Microscopy, offering a method to uncover hidden information beyond simple brightness, though it appears incremental as it builds on clustering concepts.
The paper tackles the problem of extracting multi-modal information from multi-dimensional signals in pixel-by-pixel imaging by proposing a novel clustering method that groups signals based on shape rather than amplitude, resulting in a scalable and noise-robust algorithm for learning signal shapes related to underlying target characteristics.
Many measurement modalities which perform imaging by probing an object pixel-by-pixel, such as via Photoacoustic Microscopy, produce a multi-dimensional feature (typically a time-domain signal) at each pixel. In principle, the many degrees of freedom in the time-domain signal would admit the possibility of significant multi-modal information being implicitly present, much more than a single scalar "brightness", regarding the underlying targets being observed. However, the measured signal is neither a weighted-sum of basis functions (such as principal components) nor one of a set of prototypes (K-means), which has motivated the novel clustering method proposed here. Signals are clustered based on their shape, but not amplitude, via angular distance and centroids are calculated as the direction of maximal intra-cluster variance, resulting in a clustering algorithm capable of learning centroids (signal shapes) that are related to the underlying, albeit unknown, target characteristics in a scalable and noise-robust manner.