ECG Segmentation Task

Overview

The objective of ECG segmentation is to delineate key segments of the cardiac cycle, including the P-wave, QRS complex, and T-wave. These segments are used to compute a number of clinically relevant metrics, including heart rate, PR interval, QRS duration, QT interval, and QTc interval. They are also useful for a variety of downstream tasks, including rhythm classification and beat classification.

---

Characteristics

• P-Wave: Reflects atrial depolarization
• QRS Complex: Reflects ventricular depolarization
• T-Wave: Reflects ventricular repolarization
• U-Wave: Reflects papillary muscle repolarization

Annotated ECG Signal

---

Pre-Trained Models

The following table provides the latest performance and accuracy results for ECG segmentation models. Additional result details can be found in Model Zoo → Segmentation.

NAME	DATASET	FS	DURATION	# CLASSES	MODEL	PARAMS	FLOPS	METRIC
SEG-2-TCN-SM	Icentia11K, PTB-XL	100Hz	2.5s	2	TCN	4K	1.2M	96.9% IoU
SEG-4-TCN-SM	LUDB, Synthetic	100Hz	2.5s	4	TCN	7K	2.1M	78.7% IoU
SEG-4-TCN-LG	LUDB, Synthetic	100Hz	2.5s	4	TCN	10K	3.9M	80.2% IoU

---

Target Classes

Below outlines the classes available for ECG segmentation. When training a model, the number of classes, mapping, and names must be provided. This allows for the most flexibility in the segmentation task.

CLASS	LABELS
0	None
1	P-wave
2	QRS
3	T-wave
4	U-wave
5	Noise

Class Mapping Example

Below is an example of a class mapping for a 3-class segmentation model. The class map keys are the original class labels, and the values are the new class labels. Any class not included will be skipped.

{
    "num_classes": 3,
    "class_names": ["None", "QRS", "Noise"],
    "class_map": {
        "0": 0,  // Map None to None
        "1": 0,  // Map P-wave to None
        "2": 1,  // Map QRS to QRS
        "3": 0,  // Map T-wave to None
        "4": 0,  // Map U-wave to None
        "5": 2   // Map Noise to Noise
    }
}

---