Faster R-CNN approach for estimating global QRS duration in electrocardiograms with a limited quantity of annotated data

In electrocardiography (ECG), measurement of QRS duration (QRSd) is crucial for diagnosing conditions such as left bundle branch block. To address the limited availability of ECG databases with QRS delineation labels, we present a method to use small databases to train deep learning object detection models for global QRSd estimation that involves minimal manual labeling of median beats. In our method, an ECG record is segmented into individual heartbeats, transformed into artificial images, and a Faster R-CNN model is utilized to estimate the global QRSd. Faster R-CNN models were tested with three different backbone configurations (VGG-16, VGG-19, and RESNET-18) and two ECG image formats: binary images in which each beat in each lead was represented by a separate image and RGB images in which the same beat from a trio of leads was superimposed by mapping each lead to a different color channel. Using 258 twelve-lead, 10-s digital ECG records acquired from 140 unique heart failure outpatients, the best-performing backbone, VGG-19 with RGB images, achieved root-mean-square and mean absolute errors for QRSd of 10.4 ± 0.8 ms and 8.2 ± 1.0 ms, respectively, during five-fold cross-validation. Testing with an independent, publicly available dataset yielded root-mean-square and mean absolute errors for QRSd of 7.0 ± 1.1 ms and 5.3 ± 0.9 ms, respectively. Therefore, our method provides high QRSd estimation accuracy while reducing the need for manual labeling and shows promise for generalization to independent databases, demonstrating potential for efficient training of deep learning models on small ECG databases. • A Faster R-CNN model estimates global QRSd using artificial ECG images. • VGG-19 with RGB images achieved the best QRSd estimation accuracy. • The method reduces manual labeling by using small ECG databases for training. • Strong performance was observed in both cross-validation and independent testing. • The approach shows potential for generalizing to new ECG datasets.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.