Checkout upcoming CONFERENCES and EVENTS

CEI 2022 Seminar Series

We are very excited to announce the first presentation in the new Consortium for ECGI 2022 Seminar Series. With this seminar series, we hope to organize presentations from leaders in the field of cardiac electrophysiological modeling.

Seminar Info:

March 15th 3:00 pm - 4:00 pm GMT -- Artificial Intelligence in Electrophysiology

Registration Link: https://utah.zoom.us/meeting/register/tJUvceyqrD4oHdRDzH9uNZf-x3wsYfaruhFz

Moderator: Dr. Linwei Wang, Rochester Institute of Technology

Presenters:

Rutger van de Leur, University Medical Center Utrecht -- Explainable AI for the ECG
Deep neural networks (DNNs) show excellent performance in interpreting electrocardiograms (ECGs), both for conventional ECG interpretation and for novel applications such as detection of reduced ejection fraction. Despite these promising developments, clinical implementation is severely hampered by the lack of trustworthy techniques to explain the decisions of the deep learning algorithm to clinicians. Especially, currently employed heatmap-based methods have shown to be inaccurate. We will discuss a novel approach that is inherently explainable and uses an unsupervised variational auto-encoder (VAE) to learn the underlying factors of variation of the ECG (the FactorECG) in a database with 1.1 million ECG recordings.

Dr. Maxime Sermesant, Inria IHU Liryc Université Côte d’Azur -- Learning to improve cardiac models

Physics-based and data-driven approaches both progressed tremendously during the last decade. There is now increasing research activity at the interface between these two scientific areas. In particular, deep learning can be used to efficiently predict the solution to a given PDE. However, in most of these approaches, the learned model can at best achieve similar accuracy as the physics-based model used to train it. Therefore, the benefit can be reduced to a better computational efficiency, with the risk of a loss of realism for conditions far from the training data. I will present an approach to learn cardiac electrophysiology models and recent results on a new framework to learn model error from data. This has the potential to produce a final dynamical model combining simulation and learning that is closer to the reality than the original biophysical model.




May TBD

Moderator:

Presenters:

Dr. Natalia Trayanova, Johns Hopkins University

TBD


CEI Satellite Symposium 2021

The 6th edition was a success. More information can be found HERE. See you all at the 2022 event!

Dec 7, 2021

"Lecture notes on Electric Volume Conduction in Biomedicine" by A. van Oosterom and T. F. Oostendorp, Laboratory of Medical Physics and Biophysics, Catholic University Nijmegen, Nijmegen, The Netherlands, is now available for download on the CEI publications page.


Jan 13, 2021

Do you also wonder what the effect is of differences in segmentations and segmentation programs on the inverse problem of electrocardiography? Within the Model Building working group of the Consortium for ECG imaging, we try to answer this question and with that we need your help!

Four imaging datasets were selected and thereof already several people segmented the heart (endocardium and epicardium), lungs and thorax, wherefore we are very grateful! However, more segmentations are required and therefore we want to ask for your help.

Each dataset contains its own challenge, like imaging artifacts or segmentation without contrast. On the Google Drive, the four datasets are uploaded as nrrd and DICOM files:

1. Dalhousie: segmentation of blood pools, epicardium/endocardium, lungs and thorax.

2. P43: segmentation of blood pools, epicardium/endocardium, lungs and thorax, challenge with imaging artifacts.

3. Nijmegen: segmentation of blood pools, epicardium/endocardium, lungs and thorax

4. Auckland: segmentation of epicardium, lungs and thorax, challenge with imaging artifacts and without blood pool contrast.

If you are in the opportunity to segment one or more of these datasets using the images uploaded at the drive with your own segmentation tools before the 10th of February, it would really help us making another step forward in the analysis towards answering our question! Thanks in advance for your help and for the segmentations, we really appreciate it! If you have any questions, don’t hesitate to ask me (Machteld, m.j.boo...@umcutrecht.nl)!

Dec 16, 2020

We have a new EDGAR dataset for you all to use! RV and LV pacing, sinus rhythm, induced LBBB, all recorded using a torso tank and epicardial sock array. Thanks to Laura Bear, and IHU LIRYC for providing this dataset. Go check it out here: http://edgar.sci.utah.edu/torso-tank/25-bdx-160620-exp16.html

Oct 21, 2020

CEI Satellite Symposium (2020) recorded material has been released. Below is a link to our YouTube channel where the videos from our amazing presenters have been posted. Please let us know if you have any questions, comments, or concerns. Thank you to our speakers for taking time to have an excellent discussion.

https://www.youtube.com/channel/UCW6ub_Rg8w3P4EN4u0pPXYA?view_as=subscriber