Abstract #2837

Identification of S100 Immunopositivity on T2-weighted MRI Using Deep Learning

Abdullah Baş¹, Kübra Tan², Ayça Ersen Danyeli^3,4, M.Necmettin Pamir^5,6, Alp Dincer^4,7, Koray Ozduman^5,6, Ozge Can⁸, and Esin Ozturk-Isik¹

¹Institute of Biomedical Engineering, Bogazici University, İstanbul, Turkey, ²Health Institutes of Turkey, Istanbul, Turkey, ³Department of Medical Pathology, Acibadem Mehmet Ali Aydinlar University, İstanbul, Turkey, ⁴Center for Neuroradiological Applications and Reseach, Acibadem Mehmet Ali Aydinlar University, İstanbul, Turkey, ⁵Center for Neuroradiological Applications and Reseach, Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey, ⁶Department of Neurosurgery, Acibadem Mehmet Ali Aydinlar University, İstanbul, Turkey, ⁷Department of Radiology, Acibadem Mehmet Ali Aydinlar University, İstanbul, Turkey, ⁸Center for Neuroradiological Applications and Reseach Acibadem Mehmet Ali Aydinlar University, Istanbul, Turkey

Synopsis

S100 protein expression is a relevant indicator of prognosis in meningiomas and it is more common in benign meningiomas. To our knowledge, a clinically feasible non-invasive method that preoperatively identifies S100 protein expression is not available. In this study, we proposed registration-free deep learning models to predict S100 expression non-invasively using T2-w MRI. The proposed hybrid deep learning model could predict S100 protein expression in meningiomas using T2-w MRI, with 91% accuracy on the validation set, and 83% accuracy on the test set.

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.