A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision
Providing reliable detection of QRS complexes is key in automated analyses of electrocardiograms (ECG). Accurate and timely R-peak detections provide a basis for ECG-based diagnoses and to synchronize radiologic, electrophysiologic, or other medical devices. Compared with classical algorithms, deep...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/4/2288 |
| _version_ | 1797618192076505088 |
|---|---|
| author | Maroua Mehri Guillaume Calmon Freddy Odille Julien Oster |
| author_facet | Maroua Mehri Guillaume Calmon Freddy Odille Julien Oster |
| author_sort | Maroua Mehri |
| collection | DOAJ |
| description | Providing reliable detection of QRS complexes is key in automated analyses of electrocardiograms (ECG). Accurate and timely R-peak detections provide a basis for ECG-based diagnoses and to synchronize radiologic, electrophysiologic, or other medical devices. Compared with classical algorithms, deep learning (DL) architectures have demonstrated superior accuracy and high generalization capacity. Furthermore, they can be embedded on edge devices for real-time inference. 3D vectorcardiograms (VCG) provide a unifying framework for detecting R-peaks regardless of the acquisition strategy or number of ECG leads. In this article, a DL architecture was demonstrated to provide enhanced precision when trained and applied on 3D VCG, with no pre-processing nor post-processing steps. Experiments were conducted on four different public databases. Using the proposed approach, high F1-scores of 99.80% and 99.64% were achieved in leave-one-out cross-validation and cross-database validation protocols, respectively. False detections, measured by a precision of 99.88% or more, were significantly reduced compared with recent state-of-the-art methods tested on the same databases, without penalty in the number of missed peaks, measured by a recall of 99.39% or more. This approach can provide new applications for devices where precision, or positive predictive value, is essential, for instance cardiac magnetic resonance imaging. |
| first_indexed | 2024-03-11T08:09:40Z |
| format | Article |
| id | doaj.art-3542ab624250485996ff7e9ae9ac6026 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T08:09:40Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3542ab624250485996ff7e9ae9ac60262023-11-16T23:12:52ZengMDPI AGSensors1424-82202023-02-01234228810.3390/s23042288A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced PrecisionMaroua Mehri0Guillaume Calmon1Freddy Odille2Julien Oster3Epsidy, 54000 Nancy, FranceEpsidy, 54000 Nancy, FranceEpsidy, 54000 Nancy, FranceIADI-Imagerie Adaptative Diagnostique et Interventionnelle, Inserm U1254, Université de Lorraine, 54000 Nancy, FranceProviding reliable detection of QRS complexes is key in automated analyses of electrocardiograms (ECG). Accurate and timely R-peak detections provide a basis for ECG-based diagnoses and to synchronize radiologic, electrophysiologic, or other medical devices. Compared with classical algorithms, deep learning (DL) architectures have demonstrated superior accuracy and high generalization capacity. Furthermore, they can be embedded on edge devices for real-time inference. 3D vectorcardiograms (VCG) provide a unifying framework for detecting R-peaks regardless of the acquisition strategy or number of ECG leads. In this article, a DL architecture was demonstrated to provide enhanced precision when trained and applied on 3D VCG, with no pre-processing nor post-processing steps. Experiments were conducted on four different public databases. Using the proposed approach, high F1-scores of 99.80% and 99.64% were achieved in leave-one-out cross-validation and cross-database validation protocols, respectively. False detections, measured by a precision of 99.88% or more, were significantly reduced compared with recent state-of-the-art methods tested on the same databases, without penalty in the number of missed peaks, measured by a recall of 99.39% or more. This approach can provide new applications for devices where precision, or positive predictive value, is essential, for instance cardiac magnetic resonance imaging.https://www.mdpi.com/1424-8220/23/4/228812-lead ECGvectorcardiogramR-peak detectionsegmentationdeep learningU-Net architecture |
| spellingShingle | Maroua Mehri Guillaume Calmon Freddy Odille Julien Oster A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision Sensors 12-lead ECG vectorcardiogram R-peak detection segmentation deep learning U-Net architecture |
| title | A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision |
| title_full | A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision |
| title_fullStr | A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision |
| title_full_unstemmed | A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision |
| title_short | A Deep Learning Architecture Using 3D Vectorcardiogram to Detect R-Peaks in ECG with Enhanced Precision |
| title_sort | deep learning architecture using 3d vectorcardiogram to detect r peaks in ecg with enhanced precision |
| topic | 12-lead ECG vectorcardiogram R-peak detection segmentation deep learning U-Net architecture |
| url | https://www.mdpi.com/1424-8220/23/4/2288 |
| work_keys_str_mv | AT marouamehri adeeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision AT guillaumecalmon adeeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision AT freddyodille adeeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision AT julienoster adeeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision AT marouamehri deeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision AT guillaumecalmon deeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision AT freddyodille deeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision AT julienoster deeplearningarchitectureusing3dvectorcardiogramtodetectrpeaksinecgwithenhancedprecision |