Meeting Banner
Abstract #3379

An Open-source, Flexible, Plug-and-Play Inline CMR Image Segmentation Platform

Salah Assana1, Manuel A. Morales1, Jonah Castiglione1, Scott Johnson1, Patrick Pierce1, Jennifer Rodriguez1, Kelvin Chow2, Tess Wallace1,3, Pieter Kitslaar4, Warren J. Manning1,5, and Reza Nezafat1
1Cardiology, Beth Israel Deaconess Medical Center, Boston, MA, United States, 2Cardiovascular MR R&D, Siemens Healthcare Ltd, Calgary, AB, Canada, 3Siemens Medical Solutions, Boston, MA, United States, 4Medis Medical Imaging Systems, Leiden, Netherlands, 5Radiology, Beth Israel Deaconess Medical Center, Boston, MA, United States

Synopsis

Keywords: Heart Failure, Segmentation, Open-Source

Motivation: Cardiac magnetic resonance (CMR) image segmentation remains a time-consuming task. Deep learning (DL) segmentation models have advanced considerably in recent years, but they lack flexibility for manual adjustments.

Goal(s): We sought to develop an open-source, flexible plug-and-play inline CMR image segmentation platform.

Approach: We implemented in-house algorithms in a clinical scanner as separate Python modules, allowing new and existing DL models to be integrated into clinical workflow.

Results: We assessed the feasibility of the automated plug-and-play platform for inline cine segmentation in 308 patients referred for clinical CMR.

Impact: This platform facilitates the rapid development and evaluation of any segmentation algorithm in a transparent and reproducible fashion. An open-source, flexible, plug-and-play inline CMR segmentation platform will enable rapid testing and evaluation of new segmentation and analysis algorithms.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords