Year: 2024
Type: conference-paper
Abstract: As part of the PhysioNet/Computing in Cardiology Challenge 2024, our team, Inventec AIC, developed a dual deep-learning system to digitize and classify 12-lead electrocardiograms (ECG) from scanned images.Our approach comprises a computer vision (CV) algorithm and two deep-learning models based on Convolutional Neural Networks (CNN).Our preprocessing algorithm uses contour detection to capture the ECG grid, cropping out nonrelevant information and fixing rotations.Our digitization approach leverages a fine-tuned object detection algorithm -YOLOv7 to detect and crop ECG sequences.Then, our digitization model based on CNNs with self-attention outputs the digital ECG signals.Besides, we developed an EfficientNet-B0 model with sample weighting to classify ECG images into 11 labels.We trained our models with 336K synthetic images with different formats and distortions from three datasets.In our internal evaluation, our approaches achieved an SNR of 1.479 and a macro Fmeasure of 0.728.For the digitization task, our model received an SNR of 0.397 (ranked 5th out of 16 eligible teams) on the hidden set.For the classification task, our model received a macro F -measure of 0.742 (awarded 2nd prize among 16 eligible teams).
Source: Computing in cardiology
Authors: ChunTi Chou, Sergio González Vázquez
Institution: Inventec (Taiwan)
Language: English
Topic: ECG Monitoring and Analysis
Subfield: Cardiology and Cardiovascular Medicine
Field: Medicine
Domain: Health Sciences
Open Access status: bronze
OpenAlex ID: W4405435308