PandeMIC: Early detection and classification of CoViD-19 pneumonia using computed tomography and machine learning
Abstract
The goal of this project is to apply machine learning methods to low-dose chest CTs and additional meta-information from CoViD-19 patients to perform individualized automated detection, quantification and risk assessment. Our research includes automatic quantification of infected lung regions, longitudinal analysis of patient progression and utilization of Graph Convolutional Networks for patient triage combining imaging and meta-information.
SAT.1 Bayern featured a reportage in December 2020 on the efforts of the CAMP Chair in collaboration with the Radiology of Klinikum Rechts der Isar to fight CoViD-19 and equip physicians with solutions that could further be useful for future pandemics. You can watch it here: https://www.sat1.de/regional/bayern/nachrichten/die-sendung-vom-28-12-2020-ganze-folge
Keywords: Medical Imaging, Machine Learning, CoViD-19, Segmentation, Classification
This project is funded by the Bavarian Research Foundation (BFS) under grant agreement AZ-1429-20C.
The company ImFusion GmbH contribute with a free version of their segmentation software ImFusion Labels to this project, what we thank and acknowledge here.