Performance Evaluation of Big Data Processing Strategies for Neuroimaging
share
Neuroimaging datasets are rapidly growing in size as a result of advancements in image acquisition methods, open-science and data sharing. However, it remains that current neuroimaging data processing engines do not employ strategies adopted by Big Data processing engines to improve processing time. Here, we evaluate three Big Data processing strategies (in-memory computing, data-locality and lazy-evaluation) on typical neuroimaging use cases, represented by the BigBrain dataset. We contrast the various processing strategies by using Apache Spark and Nipype as our representative Big Data and neuroimaging processing engines on Dell EMC's Top-500 cluster. Big Data thresholds were modeled by comparing the data/compute ratio of the application to the filesystem/concurrent processes ratio. This model acknowledges the fact that page caching provided by the Linux kernel is critical to the performance of Big Data applications. Results show that in-memory computing alone speeds-up executions by a factor of up to 1.6, whereas when combined with data locality, this factor reaches 5.3. Lazy evaluation strategies were found to increase the likelihood of cache hits, further improving processing time. Such important speed-up values are likely to be observed on typical image processing operations performed on images of size larger than 75GB. A ballpark speculation from our model showed that in-memory computing alone will not speed-up current functional MRI analyses unless coupled with data locality and processing around 280 subjects concurrently. In addition, we observe that emulating in-memory computing using in-memory file systems (tmpfs) does not reach the performance of an in-memory engine, presumably due to swapping to disk and the lack of data cleanup. We conclude that Big Data processing strategies are worth developing for neuroimaging applications.
READ FULL TEXT