EcoScaleNet: A Lightweight Multi Kernel Network for Long Sequence 12 lead ECG Classification

TL;DR

EcoScaleNet is a lightweight, hierarchical multi-scale CNN that efficiently classifies long sequence 12-lead ECGs, achieving state-of-the-art accuracy with significantly reduced computational cost.

Contribution

It introduces EcoScaleNet, a novel hierarchical multi-scale CNN that retains full receptive field coverage while drastically reducing parameters and FLOPs for ECG classification.

Findings

Reduces parameters by 90% compared to OS CNN.

Decreases FLOPs by 99%, enabling real-time deployment.

Improves macro F1 score by 2.4% on CODE 15% ECG dataset.

Abstract

Accurate interpretation of 12 lead electrocardiograms (ECGs) is critical for early detection of cardiac abnormalities, yet manual reading is error prone and existing CNN based classifiers struggle to choose receptive field sizes that generalize to the long sequences typical of ECGs. Omni Scale CNN (OS CNN) addresses this by enumerating prime sized kernels inspired by Goldbach conjecture to cover every scale, but its exhaustive design explodes computational cost and blocks deeper, wider models. We present Efficient Convolutional Omni Scale Network (EcoScale-Net), a hierarchical variant that retains full receptive field coverage while eliminating redundancy. At each stage, the maximum kernel length is capped to the scale still required after down sampling, and bottleneck convolutions inserted before and after every Omni Scale block curtail channel growth and fuse multi scale features. On the large scale CODE 15% ECG dataset, EcoScaleNet reduces parameters by 90% and FLOPs by 99% compared with OS CNN, while raising macro averaged F1 score by 2.4%. These results demonstrate that EcoScaleNet delivers SOTA accuracy for long sequence ECG classification at a fraction of the computational cost, enabling real time deployment on commodity hardware. Our EcoScaleNet code is available in GitHub Link.