Significance

For the Needs of :

Level 1: Patients

Our long-term beneficiaries are CLL/ALL patients. Currently, most of them need to wait for a week or so to get a diagnosis. Also, it is hard for hospitals to identify their conditions if they have early and subtle cancer cell build-up. Our automated method can significantly improve the processing time of Flow Cytometry data, therefore promote a quicker diagnosis. Also, the automated method can avoid the high false positive and false negative rate because its clustering is based on more precise biological features instead of arbitrary boundaries drawn by hands. Patients also need to understand their conditions. The visualization via machine learning algorithm is easier to understand so they can have a better sense of their conditions while hearing doctors explaining to them.

Level 2: Researchers working on Flow Cytometry data

In the short term, our project will benefit researchers working on Flow Cytometry data in cancer research institutes. Because our goal is to develop and improve the automated method in Flow Cytometry data clustering, it can be widely applied to other diseases that utilize Flow Cytometry results in the process of diagnosis. Instead of using manual gating, they can use the automated method to speed up the processing time and improve the accuracy of the result. This will save them money and time, and will probably yield better results.

Level 3: Physicians

One of our most important beneficiaries will be physicians working with Leukemia diagnosis. Doctors need easy-to-interpret data for diagnosis, and also a quicker diagnosis process for making decisions in early treatment. Our project will provide a clear visualization for the cancer cell population, which is similar to the final result of manual gating but more biologically explainable. This can better assist physicians to make decisions based on the result.