Deploying a quantized LiteRT DNN on an ARM Cortex-M7 microcontroller reduced computation latency from 4.8 s to 0.6 s and energy consumption by 7.85 times with <0.4% rhythm accuracy deviation.
Does deploying a quantized pre-trained deep neural network on ARM-based microcontrollers maintain accuracy while reducing computational complexity for ventricular fibrillation detection?
Quantized deep neural networks can be effectively deployed on low-resource ARM-based microcontrollers for real-time ventricular fibrillation detection with minimal loss of accuracy and significant reductions in latency and energy consumption.
GPU-based deep neural networks (DNNs) are powerful for electrocardiogram (ECG) processing and rhythm classification. Although questions often arise about their practical application in embedded systems with low computational resources, few studies have investigated the associated challenges. This study aims to show a useful workflow for deploying a pre-trained DNN model from a GPU-based development platform to two popular ARM-based microcontrollers: Raspberry Pi 4 and ARM Cortex-M7. Specifically, a five-layer convolutional neural network pre-trained in TensorFlow (TF) for the detection of ventricular fibrillation is converted to Lite Runtime (LiteRT) format and subjected to post-training quantization to reduce model size and computational complexity. Using a test dataset of 7482 10 s cardiac arrest ECGs, the inference of LiteRT DNN in Raspberry Pi 4 takes about 1 ms with a sensitivity of 98.6% and specificity of 99.5%, reproducing the TF DNN performance. An optimization study with 1300 representative datasets (RDSs), including 10 to 4000 calibration ECG signals selected by random, rhythm, or amplitude-based criteria, showed that choosing a random RDS with a relatively small size of 80 resulted in a quantized integer LiteRT DNN with minimal quantization error. The inference of both non-quantized and quantized LiteRT DNNs on a low-resource ARM Cortex-M7 microcontroller (STM32F7) shows rhythm accuracy deviation of <0.4%. Quantization reduces internal computation latency from 4.8 s to 0.6 s, flash memory usage from 40 kB to 20 kB, and energy consumption by 7.85 times. This study ensures that DNN models retain their functionality while being optimized for real-time execution on resource-constrained hardware, demonstrating application in automated external defibrillators.
Krasteva et al. (Thu,) conducted a other in Ventricular fibrillation (n=7,482). Quantized LiteRT DNN on ARM-based microcontrollers vs. Non-quantized LiteRT DNN / TF DNN was evaluated on Rhythm accuracy deviation, computation latency, memory usage, and energy consumption. Deploying a quantized LiteRT DNN on an ARM Cortex-M7 microcontroller reduced computation latency from 4.8 s to 0.6 s and energy consumption by 7.85 times with <0.4% rhythm accuracy deviation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: