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 Debnath^5,6, 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