ISLE: An Intelligent Streaming Framework for High-Throughput AI Inference in Medical Imaging
This addresses bandwidth and compute limitations for healthcare providers and AI vendors in medical imaging, offering a domain-specific solution that is incremental in optimizing existing streaming methods.
The paper tackled the problem of communication bottlenecks in streaming medical imaging data for AI inference, which cause delays and high costs in clinical settings, by developing ISLE, an intelligent streaming framework that reduced data transmission by 98.02%, decoding time by 98.09%, and increased throughput by 2,730%.
As the adoption of Artificial Intelligence (AI) systems within the clinical environment grows, limitations in bandwidth and compute can create communication bottlenecks when streaming imaging data, leading to delays in patient care and increased cost. As such, healthcare providers and AI vendors will require greater computational infrastructure, therefore dramatically increasing costs. To that end, we developed ISLE, an intelligent streaming framework for high-throughput, compute- and bandwidth- optimized, and cost effective AI inference for clinical decision making at scale. In our experiments, ISLE on average reduced data transmission by 98.02% and decoding time by 98.09%, while increasing throughput by 2,730%. We show that ISLE results in faster turnaround times, and reduced overall cost of data, transmission, and compute, without negatively impacting clinical decision making using AI systems.