Abstract
Application of synthetic datasets in training and validation of analysis tools have led to improvements in many decision-making tasks in a range of domains from computer vision to digital pathology. Synthetic datasets overcome the constraints of real-world datasets, namely difficulties in collection and labelling, expense, time and privacy concerns. In flow cytometry, real cell-based datasets are limited by properties such as size, number of parameters, distance between cell populations and distributions, and are often focused on a narrow range of disease or cell types. Researchers in some cases have designed these desired properties into synthetic datasets, however operators have implemented them in inconsistent approaches and there is a scarcity of publicly available, high-quality synthetic datasets. In this research, we propose a method to systematically design and generate flow cytometry synthetic datasets with highly controlled characteristics. We demonstrate the generation of two-cluster synthetic datasets with specific degrees of separation between cell populations, and of non-normal distributions with increasing levels of skewness and orientations of skew pairs. We apply our synthetic datasets to test the performance of a popular automated cell populations identification software, SPADE3, and define the region where the software performance decreases as the clusters get closer together. Application of the synthetic skewed dataset suggests the software is capable of processing non-normal data. We calculate the classification accuracy of SPADE3 with robustness not achievable with real-world datasets. Our approach aims to advance research towards generation of high-quality synthetic flow cytometry datasets, and to increase their awareness among the community. The synthetic datasets can be utilised in benchmarking studies that critically evaluate cell population identification tools and help illustrate potential digital platform inconsistencies. These datasets have the potential to improve cell characterisation workflows that integrate automated analysis in clinical diagnostics and cell therapy manufacturing.
- Received May 25, 2021.
- Accepted December 7, 2021.
- Copyright © 2022, Parenteral Drug Association
PDA members receive access to all articles published in the current year and previous volume year. Institutional subscribers received access to all content. Log in below to receive access to this article if you are either of these.
If you are neither or you are a PDA member trying to access an article outside of your membership license, then you must purchase access to this article (below). If you do not have a username or password for JPST, you will be required to create an account prior to purchasing.
Full issue PDFs are for PDA members only.
Note to pda.org users
The PDA and PDA bookstore websites (www.pda.org and www.pda.org/bookstore) are separate websites from the PDA JPST website. When you first join PDA, your initial UserID and Password are sent to HighWirePress to create your PDA JPST account. Subsequent UserrID and Password changes required at the PDA websites will not pass on to PDA JPST and vice versa. If you forget your PDA JPST UserID and/or Password, you can request help to retrieve UserID and reset Password below.