Identification and classification of biological micro-organisms by holographic learning

The identification and classification of biological samples is high-demanded in biomedical imaging for diagnostic purposes. Among all imaging modalities, digital holography has gained credits as a powerful solutions, thanks to its ability to perform full-field and label-free quantitative phase imaging. On the other hand, machine learning is nowadays the most used approach for classification purposes. The robustness and the accuracy of the classification depend of the features used for the training step. Therefore, the identification of micro-organism becomes strictly related to the features that can be extracted from their images. In other word, the more the image contains information, the higher the possibility of extracting highly distinctive descriptors to differentiate biological phenotypes. Digital holography can be considered one of the richest in terms of information content due to the fact that a single digital hologram encode both amplitude and phase information about the imaged cells. This opens the way to improve the features extraction, thus making more accurate the classification step. In this paper we analyze a test case by using a holographic image dataset for classification, by extracting unique features that can be solely obtained by holographic images.