Abstract #0886

Personalized brain tumor radiation therapy planning pipeline based on spectroscopic MRI using the Brain Imaging Collaboration Suite (BrICS)

Anuradha Trivedi^1,2, Karthik Ramesh¹, Alexander Giuffrida^1,2, Sulaiman Sheriff³, Lee Cooper⁴, Brent Weinberg^5,6, Sinyeob Ahn⁷, Vahid Khalilzad Sharghi⁸, Andrew Maudsley⁹, Jeffry Alger^10,11,12,13, Brian Soher¹⁴, and Hyunsuk Shim^1,2,5,6

¹Department of Radiation Oncology, Emory University School of Medicine, Atlanta, GA, United States, ²Department of Biomedical Engineering, Georgia Tech and Emory University, Atlanta, GA, United States, ³Department of Radiation Oncology, University of Miami School of Medicine, Miami, FL, United States, ⁴Department of Pathology, Northwestern University, Chicago, IL, United States, ⁵Department of Radiology and Imaging Sciences, Emory University School of Medicine, Atlanta, GA, United States, ⁶Winship Cancer Institute, Emory University, Atlanta, GA, United States, ⁷Siemens Healthineers, San Francisco, CA, United States, ⁸Siemens Healthineers, Atlanta, GA, United States, ⁹Department of Radiology, University of Miami School of Medicine, Miami, FL, United States, ¹⁰Department of Neurology, University of California, Los Angeles Geffen School of Medicine, Los Angeles, CA, United States, ¹¹Advanced Imaging Research Center, University of Texas Southwestern Medical Center, Dallas, TX, United States, ¹²Hura Imaging Inc, Los Angeles, CA, United States, ¹³NeuroSpectroScopics, LLC, Sherman Oaks, CA, United States, ¹⁴Department of Radiology, Duke University School of Medicine, Durham, NC, United States

Synopsis

Keywords: Tumors (Pre-Treatment), Brain, Cancer, MR-Guided Radiotherapy, Data Processing, Image Reconstruction, Software Tools, Spectroscopy

Motivation: Current spectroscopic MRI (sMRI) workflows are challenging to integrate into clinical practice due to data size, processing complexity, and computational demands. An efficient sMRI pipeline could enhance brain tumor treatment planning, enabling personalized and data-driven therapeutic decisions.

Goal(s): To develop and validate PyMIDAS, a Python-based pipeline that improves the efficiency and accessibility of sMRI for brain tumor imaging, facilitating clinical workflow integration.

Approach: PyMIDAS was created by porting MIDAS (current solution) from IDL to Python, optimized with distributed processing and GPU computing. Validation included SSIM and cross-correlation comparisons across multi-site datasets.

Results: PyMIDAS demonstrated similar output to MIDAS while meeting validation criteria.

Impact: PyMIDAS, a Python version of the existing IDL-based pipeline, accelerates and simplifies spectroscopic MRI-based brain tumor treatment planning, enabling clinical workflow integration. Its improved computational efficiency and flexibility support broader adoption of advanced spectroscopic MRI for brain tumor imaging.

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.