Deep-Learning Model for Central Nervous System Infection Diagnosis and Prognosis Using Label-Free 3D Immune-Cell Morphology in the Cerebrospinal Fluid

Abstract

Deep-Learning Model for Central Nervous SystemInfection Diagnosis

In article number 2401145, Kyung Min Kim, Yu Rang Park, and co-workers describe their study on central nervous system (CNS) infection diagnosis and prognosis prediction using a deep-learning model and label-free 3D holotomography. It combines a conceptual CNS infection visualization, a holotomography device, and immune cell images from cerebrospinal fluid (CSF). Their model analyzes CSF immune cell morphology to differentiate infection etiology and predict outcomes. This rapid, non-invasive approach enhances CNS infection diagnostics, improving patient care.