From 270100b6e43beb8f7231a91765ab858a8be23368 Mon Sep 17 00:00:00 2001 From: Mikel Landajuela Date: Tue, 14 Jan 2025 09:32:35 -0800 Subject: [PATCH] Show the figure on top --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index 1cc6b6d..33eabe9 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,10 @@ **If you find this repository useful, we ask that you cite our works in section [Citations](#citations). Also, don't forget to ⭐ this repository if you find it useful!** +

+ +

+ This repository contains the code for the [Data Science Challenge](https://data-science.llnl.gov/dsc) problem on machine learning for cardiac electrophysiology. It contains tutorials on machine learning, as well as notebooks to get you started with the challenge. These notebooks are meant to be a starting point for the challenge, and you are encouraged to modify them as you see fit. In particular, you are encouraged to use any machine learning framework of your choice (e.g. PyTorch, TensorFlow, JAX, etc.) and any machine learning model of your choice (e.g. neural networks, random forests, etc.). @@ -25,10 +29,6 @@ Resources ## Description The electrocardiogram (ECG) provides a non-invasive and cost-effective tool for the diagnosis of heart conditions. However, the standard 12-lead ECG is inadequate for mapping out the electrical activity of the heart in sufficient detail for many clinical applications (e.g., identifying the origins of an arrhythmia). In order to construct a more detailed map of the heart, current techniques require not only ECG readings from dozens of locations on a patient’s body, but also patient-specific anatomical models built from expensive medical imaging procedures. For this Data Science Challenge problem, we consider an alternative data-driven approach to reconstructing electroanatomical maps of the heart at clinically relevant resolutions, which combines input from the standard 12-lead electrocardiogram (ECG) with advanced machine learning techniques. We begin with the clearly-defined task of identifying heart conditions from ECG profiles and then consider a range of more open-ended challenges, including the reconstruction of a complete spatio-temporal activation map of the human heart. -

- -

- ## Contents - [tutorials](./tutorials/) - [tutorials/image_classifier_tutorial_v1.2](./tutorials/image_classifier_tutorial_v1.2.ipynb) : Tutorial on image classification @@ -189,4 +189,4 @@ and SPDX-License-Identifier: MIT -LLNL-CODE-849487 \ No newline at end of file +LLNL-CODE-849487