Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- segmentation
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
## EchoNet-LVH
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
EchoNet Left Ventricular Hypertrophy (LVH) model for echocardiogram analysis.
|
| 10 |
+
|
| 11 |
+
This model performs semantic segmentation on echocardiogram images to identify
|
| 12 |
+
key anatomical landmarks for measuring left ventricular wall thickness:
|
| 13 |
+
- LVPWd_1: Left Ventricular Posterior Wall point 1
|
| 14 |
+
- LVPWd_2: Left Ventricular Posterior Wall point 2
|
| 15 |
+
- IVSd_1: Interventricular Septum point 1
|
| 16 |
+
- IVSd_2: Interventricular Septum point 2
|
| 17 |
+
|
| 18 |
+
The model outputs 4-channel logits corresponding to heatmaps for each landmark.
|
| 19 |
+
|
| 20 |
+
Original paper and code: https://echonet.github.io/lvh/index.html
|
| 21 |
+
|
| 22 |
+
🌽 This is a `zea` implementation of the model. For the source code check [here](https://zea.readthedocs.io/en/latest/_modules/zea/models/echonetlvh.html#EchoNetLVH).
|
| 23 |
+
|
| 24 |
+
📚 A tutorial notebook where this model is used: ["Task-based transmit beamforming perception-action loop"](https://zea.readthedocs.io/en/latest/notebooks/agent/task_based_perception_action_loop.html).
|