A research team led by Professor Moon In-kyu (Dean Kuk Yang) from the Department of Robotics and Mechatronics Engineering at DGIST has developed an AI holographic system that automatically extracts important information And check the quality of red blood cells. Accurate mass testing of red blood cells stored for a certain period of time for transfusion is expected to be a key technology, enabling patients to have cleaner, healthier red blood cell injections.
Red blood cells are the main components of the blood that carry oxygen. Red blood cells collected by donating blood are kept for a period of time until needed for a blood transfusion. This process is necessary because unhealthy red blood cells cannot function properly and can lead to fatal side effects such as acute lung injury.
Traditionally, image-based red blood cell analysis techniques are used, which is an invasive method that observes red blood cells by staining them, destroying them Three-dimensional structure of red blood cells. In addition, there are technical limitations in rapidly analyzing state changes such as red blood cell three-dimensional shape, density changes, and motion characteristics. To overcome this problem, Professor Moon In-kyu’s team previously developed a “holography-based red blood cell division and classification technique”. However, a large number of preprocessing algorithms are required before analysis, which is time-consuming and difficult to analyze and classify accurately.
In this regard, Professor Wen Renkui’s team has successfully developed an artificial intelligence holographic system, combining 3D structural images of red blood cells obtained with holographic technology Data, automatically detect the quality of red blood cells stored for a certain period of time. Generative Adversarial Neural Network Technology. If the developed technology is used, it will be possible to automatically extract important values of red blood cell judgment and check its quality by applying an automatic red blood cell 3D structure image analysis algorithm. In particular, the quality of red blood cells can be tested precisely and simply because no invasive methods or pretreatment procedures required by the prior art are required. It is expected to serve as a core technology to help reduce the side effects of blood transfusions by injecting clean, healthy red blood cells into patients who need blood transfusions.
“The technology developed through this research is the source technology that can automatically analyze how red blood cells are stored for transfusion, changing them according to the time of storage the three-dimensional shape and determine whether the stored red blood cells are healthy red blood cells that can be transfused,” said Professor Moon In-kyu from the Department of Robotics and Mechatronic Engineering. He added: “It is expected that in the future it will help to minimise the occurrence of post-transfusion side effects as it allows for a more meticulous examination of the status of stored red blood cells and to test whether the red blood cells are safe for the patient prior to transfusion.”
The results of this study were published in IEEE Biomedical and Health Information Journal of Science .
Further information: Eunji Kim et al., Deep learning-based phenotypic assessment of red blood cell storage injury for safe transfusion, IEEE Journal of Biomedical and Health Informatics (2021). DOI: 10.1109/JBHI.2021.3104650
Provided by DGIST (Daegu Gyeongbuk Institute of Science and Technology)
Citation : Is blood transfusion safe? AI holographic system checks blood quality without injection (12 Aug 2022), retrieved 18 Aug 2022 from https://medicalxpress.com/news/2022-08-transfusion-blood-safe-ai -holography.html
This document is copyrighted. Except for any fair dealing for private study or research purposes, no part may be reproduced without written permission. The content is for reference only.
