Machine learning in combination with microscopy is a well-established paradigm for the identification of cells target (e.g. sick cells) or for the statistical study of cells’ populations. In general, the accuracy in classifying single cells depends on the selected imaging modality, i.e., the more informative it is, the more performant the classifier is. Here we show that the combination of machine learning and holographic microscopy is an effective tool to achieve the above goal, thus allowing higher classification performances if compared to other standard microscopies. Moreover, by exploiting a priori information about the samples to identify, the classification performance can be further increased. We demonstrate this paradigm for the differential diagnosis of hereditary anemias, in which RBCs, imaged by holographic microscopy, are used to predict firstly if an anemia occurs, then which type of anemia among five phenotypes.
We propose a new diagnostic tool for anemias identification based on quantitative phase imaging. We introduce a panel of label-free optical markers to identify red blood cell (RBC) phenotypes, demonstrating that an optical fingerprint of RBC is related to erythrocyte disease through modeling RBC as biological lens.
Gold standard methods for anaemia diagnosis are the complete blood count and the peripheral smear observation. However, they do not allow for a complete differential diagnosis, which requires biochemical assays, thus being labeldependent techniques. On the other hand, recent studies focus on label-free quantitative phase imaging (QPI) of blood samples to investigate blood diseases by using video-based morphological methods. However, when sick cells are very similar to healthy ones in terms of morphometric features, identification of a blood disease becomes challenging even by morphometric analysis as well as QPI. Here we exploit in-flow tomographic phase microscopy to retrieve the exact 3D rendering of Red Blood Cells (RBCs) from anaemic patients and to identify the pathology, distinguishing it from healthy samples. Moreover, we introduce a Label-free Optical Marker (LOM) to detect RBC phenotypes demonstrating that a single set of all-optical parameters can clearly identify a signature directly related to the erythrocytes disease by modelling each RBC as a biolens. We tested this novel bio-photonic analysis by proofing that several inherited anaemias, specifically Iron-deficiency Anaemia, Thalassemia, Hereditary Spherocytosis and Congenital Dyserythropoietic Anaemia, can be identified and sorted thus opening a novel route for blood diagnosis on a completely different concept based on LOMs.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.