ML로 blood quality test 하기

Each year, nearly 120 million units of donated blood flow from donor veins into storage bags at collection centers around the world. The fluid is packed, processed and reserved for later use. But once outside the body, stored red blood cells (RBCs) undergo continuous deterioration. By day 42 in most countries, the products are no longer usable.

For years, labs have used expert microscopic examinations to assess the quality of stored blood. How viable is a unit by day 24? How about day 37? Depending on what technicians' eyes perceive, answers may vary. This manual process is laborious, complex and subjective.

"With this technique, RBCs are suspended and flowed through the cytometer, an instrument that takes thousands of images of individual blood cells per second. We can then examine each RBC without handling or inadvertently damaging them, which sometimes happens during microscopic examinations."

In the study's second part, the researchers avoided human input altogether and devised an alternative, "weakly-supervised" deep learning model in which neural networks learned about RBC degradation on their own.

Instead of being taught the six visual categories used by experts, the machines learned solely by analyzing over one million images of RBCs, unclassed and ordered only by blood storage duration time. Eventually, the machines correctly discerned features in single RBCs that correspond to the descent from healthy to unhealthy cells.

 

cytometry image로 blood quality를 판단한다는 내용이다. 이미지에 expert들이 판단한 내용을 가지고 training을 시켰다면 별 임팩트가 없었겠지만, weakly supervised DML이라고 한다. 그냥 시간이 경과한 데이터들을 feeding했다고 한다. expert들은 모양을 가지고 하는데, 모양이 아닌 시간이 얼마나 경과했는가를 두고 training하였다.

 

reference

Minh Doan et al, Objective assessment of stored blood quality by deep learning, PNAS August 24, 2020 doi.org/10.1073/pnas.2001227117