Overview diagram of deep learning algorithm with proposed two-step structure for erythrocyte holography picture segmentation and computerized classification. Credit: DGIST (Daegu Gyeongbuk Institute of Science and Technology)
A compare crew led by Professor Moon In-kyu of the Department of Robotics and Mechatronics Engineering at DGIST (President Kuk Yang) developed an AI holography machine that robotically extracts crucial files and inspects the quality of red blood cells. It’s anticipated to change into a key technology that permits cleaner and more healthy red blood cell injections to patients thru precise quality inspection of red blood cells stored for a tear timeframe for blood transfusion.
Red blood cells are a significant ingredient of blood that carries oxygen. Red blood cells unruffled thru blood donation are stored for a tear timeframe till they are old for transfusion when wished. This course of is foremost because of the unhealthy red blood cells create now not characteristic nicely and can simply lead to lethal facet effects a lot like acute lung concern.
Conventionally, picture-essentially based mostly red blood cell analysis technology used to be old, which is an invasive formulation that destroys the three-d structure of red blood cells as red blood cells are seen after staining. To boot, there are technical limitations in immediate analyzing pronounce adjustments a lot like three-d shape, density switch, and motility characteristics of red blood cells. To beat this device back, Professor Moon In-kyu’s crew previously developed “holography-essentially based mostly red blood cell division and classification technology.” Nonetheless it completely required a replacement of pre-processing algorithms before analysis, which takes a lengthy time, and alive to difficulties in performing precise analysis and classification.
In response, Prof. Moon In-kyu’s crew successfully developed an AI holography machine that robotically inspects the quality of red blood cells stored for a tear time by combining the 3D structure picture files of red blood cells obtained with holography technology and generative adversarial neural community technology. If the developed technology is old, this might possibly presumably additionally additionally be doable to robotically extract crucial values of judgment for red blood cells by applying the automated red blood cell 3D structural picture analysis algorithm and also compare its quality. In explicit, it is miles doable to test the quality of red blood cells exactly and simply as there’s not any need for invasive concepts or pre-treatment procedures required by present technologies. It’s anticipated to be old as a core technology to reduction lower facet effects of transfusion by injecting spruce and healthy red blood cells to patients wanting blood transfusions.
“The technology developed thru this compare is the source technology that might possibly presumably robotically analyze how red blood cells, stored for transfusion for transfusion, switch their three-d shape reckoning on the storage period and identify whether stored red blood cells are healthy red blood cells that might possibly presumably additionally additionally be transfused,” said Professor Moon In-kyu of the Department of Robotics and Mechatronics Engineering. He added, “It’s anticipated that this might possibly presumably help lower the incidence of facet effects after transfusion in the extinguish as it is going to compare the pronounce of stored red blood cells more minutely and test whether the red blood cells are safe for the patient before transfusion.”
The outcomes of this compare were published in the IEEE Journal of Biomedical and Health Informatics.
More files:
Eunji Kim et al, Deep Discovering out-Primarily based completely completely Phenotypic Evaluation of Red Cell Storage Lesions for Safe Transfusions, IEEE Journal of Biomedical and Health Informatics (2021). DOI: 10.1109/JBHI.2021.3104650
Equipped by
DGIST (Daegu Gyeongbuk Institute of Science and Technology)
Quotation:
Is transfusion blood safe? AI holography machine tests blood quality without injections (2022, August 12)
retrieved 13 August 2022
from https://medicalxpress.com/news/2022-08-transfusion-blood-safe-ai-holography.html
This document is field to copyright. Other than any handsome dealing for the cause of internal most witness or compare, no
fragment is seemingly to be reproduced without the written permission. The command material is supplied for files purposes most efficient.