Meeting Banner
Abstract #2047

AI-driven Multi-Feature based Blood Hematocrit Prediction for Myocardial Extracellular Volume Quantification

Young-Jung Yang1, Pan Ki Kim1, Jinho Park1, Yoo Jin Hong1, Chul Hwan Park2, and Byoung Wook Choi1
1Department of Radiology and Research Institute of Radiological Science, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea, Republic of, 2Department of Radiology and Research Institute of Radiological Science, Gangnam Severance Hospital, Yonsei University College of Medicine, Seoul, Korea, Republic of

Blood hematocrit is needed for myocardial ECV. To determine the hematocrit, blood sampling is the standard way, but it is invasive and time-consuming. To avoid the inconvenience of blood sampling, synthetic derivation of hematocrit was suggested in recent studies. In here, we derived the Hct using three prediction methods with multi-features of patient. Investigated methods include the linear regression and AI apporaches. We hypothesized that AI driven multi-feature based synthetic Hct would be more precise than the linear regression. The results of synthetic methods were compared with the laboratory Hct (Lab-Hct) and conventional ECV (Conv-ECV) as the reference.

This abstract and the presentation materials are available to 2020 meeting attendees and eLibrary customers only; a login is required.

Join Here