zea.models.echonetlvh

EchoNetLVH model for segmentation of PLAX view cardiac ultrasound.

To try this model, simply load one of the available presets:

>>> from zea.models.echonetlvh import EchoNetLVH

>>> model = EchoNetLVH.from_preset("echonetlvh")

Important

This is a zea implementation of the model. For the original code, see here.

Reference

G. Duffy, P. P. Cheng, N. Yuan, B. He, A. C. Kwan, M. J. Shun-Shin, et al., “High-Throughput Precision Phenotyping of Left Ventricular Hypertrophy with Cardiovascular Deep Learning,” JAMA Cardiology, vol. 7, no. 4, pp. 386–395, 2022. doi.org/10.1001/jamacardio.2021.6059

See also

A tutorial notebook where this model is used: Task-based transmit beamforming perception-action loop.

Classes

EchoNetLVH(*args, **kwargs)

EchoNet Left Ventricular Hypertrophy (LVH) model for echocardiogram analysis.

class zea.models.echonetlvh.EchoNetLVH(*args, **kwargs)

Bases: BaseModel

EchoNet Left Ventricular Hypertrophy (LVH) model for echocardiogram analysis.

This model performs semantic segmentation on echocardiogram images to identify key anatomical landmarks for measuring left ventricular wall thickness:

• LVPWd_1: Left Ventricular Posterior Wall point 1

• LVPWd_2: Left Ventricular Posterior Wall point 2

• IVSd_1: Interventricular Septum point 1

• IVSd_2: Interventricular Septum point 2

The model outputs 4-channel logits corresponding to heatmaps for each landmark.

For more information, see the original project page: https://echonet.github.io/lvh/

Initialize the EchoNetLVH model.

Parameters:

**kwargs – Additional keyword arguments passed to BaseModel

call(inputs)

Forward pass of the model.

Parameters:

inputs (Tensor) – Input images of shape [B, H, W, C]. They should be scan converted, with pixel values in range [0, 255].

Returns:

Logits of shape [B, H, W, 4] with 4 channels for each landmark

Return type:

Tensor

expected_coordinate(mask, coordinate_grid=None)

Compute the expected coordinate (center-of-mass) of a heatmap.

This implements a differentiable version of taking the max of a heatmap by computing the weighted average of coordinates.

Reference

A. Nibali, Z. He, S. Morgan, and L. Prendergast, “Numerical Coordinate Regression with Convolutional Neural Networks,” arXiv preprint, 2018. arXiv:1801.07372

Parameters:

• mask (Tensor) – Heatmap of shape [B, H, W]

• coordinate_grid (Tensor, optional) – Grid of coordinates. If None, uses coordinate_grid.

Returns:

Expected coordinates of shape [B, 2] in (x, y) format

Return type:

Tensor

extract_key_points_as_indices(logits)

Extract key point coordinates from logits using center-of-mass calculation.

Parameters:

logits (Tensor) – Model output logits of shape [B, H, W, 4]

Returns:

Key point coordinates of shape [B, 4, 2] where each point is a (row, col) index into the heatmap.

Return type:

Tensor

overlay_labels_on_image(image, label, alpha=0.5)

Overlay predicted heatmaps and connecting lines on the input image.

Parameters:

• image (Tensor) – Input image of shape [H, W] or [H, W, C]

• label (Tensor) – Predicted logits of shape [H, W, 4]

• alpha (float) – Blending factor for overlay (0=transparent, 1=opaque)

Returns:

Image with overlaid heatmaps and measurements of shape [H, W, 3]

Return type:

ndarray

visualize_logits(images, logits)

Create visualization of model predictions overlaid on input images.

Parameters:

• images (Tensor) – Input images of shape [B, H, W, C]

• logits (Tensor) – Model predictions of shape [B, H, W, 4]

Returns:

Images with overlaid predictions of shape [B, H, W, 3]

Return type:

Tensor