4.2 Use Case Discussion

2.2 Use Case Methods
3.2 Use Case Results

The occasional outlying sample that is poorly prepared is crucially important to include in training data sets, but yet edited out by the well intentioned operator who recognizes the problem. Therefore as we continue our efforts, we will be working to obtain use case data and create synthetic data that represent outliers/rejected samples of the quality checking process in our collaborators labs.

Quest Diagnostics, which had provided leukemia/lymphoma data, has encountered regulatory constraints on the release of information. Tree Star has terminated this collaboration and is pursuing additional opportunities with other organizations. Richard Konz from University of Massachusetts is in contact with an clinical investigator that may be interested in this project and Bill Hyun of UCSF also has interest in this project and has available data to share.

Discussions with Dr. Joern Schmitz on Nov. 20, 2009 suggest that we may be able to receive these outlier or rejected samples from a study his lab will be conducting on a large automated incubator for cell treatment and processing.