Meeting Banner
Abstract #3070

Differentiation of Non-enhancing tumor region from Vasogenic edema in high-grade glioma using a machine learning framework based upon conventional MRI feature

Anirban Sengupta1, Neha Vats2, Sumeet Agarwal3, Rakesh Kumar Gupta4, Dinil Sasi5, Ayan Debnath5,6, and Anup Singh5

1Centre for Biomedical Engineering, IIT Delhi, New Delhi, India, 2NIT kurukshetra, Kurukshetra, India, 3Electrical Engineering, IIT Delhi, Hauz Khas, New Delhi, India, 4Fortis Memorial Research Institute, New Delhi, India, 5IIT Delhi, New Delhi, India, 6University of Pennysylvania, Philadelphia, PA, United States

Differentiation between non-enhancing tumor (NET) from vasogenic edema (VE) in glioma patients is difficult using conventional MRI parameters (CMP) such as FLAIR, T2-W, T1-W and PD-W as they appear similar in intensity in both the regions. T1 perfusion MRI parameters (T1-PMP) have been found useful in differentiating between NET and VE previously. The work in this study shows that combining different CMP using a machine learning algorithm improves differentiation between NET and VE substantially over using any individual CMP. However, combination of T1-PMP still performs slightly better than combination of CMP in differentiating NET from VE.

This abstract and the presentation materials are available to members only; a login is required.

Join Here