Using Radiomics-Based MR Fingerprinting to Detect Focal Cortical Dysplasia: Irene Wang, PhD

WATCH TIME: 4 minutes

"We are now combining this quantitative-MRI with quantitative post-processing. I think of this as quantitative based on quantitative, so it’s essentially quantitative squared.”

Focal cortical dysplasia (FCD) is one of the most common pathologies for medically intractable focal epilepsy; however, using conventional weighted MRI may be limited in detecting or characterizing FCD. MR fingerprinting, a novel technique developed in the past decade, may provide the quantitative look that clinicians need to better understand the presentation of the disease. A study presented at the 2021 American Epilepsy Society (AES) Annual Meeting, December 3-7, adopted a MR fingerprinting-based radiomics feature extraction approach to characterize FCD lesions.

At the end of the analysis, the MF fingerprinting radiomics model with the optimal 30 features showed high area under the curve, accuracy, sensitivity, and specificity of 0.86 (±0.02), 84% (±1), 87% (±1) and 80% (±2), respectively. Senior author Irene Wang, PhD, has been at the forefront of developing and expanding the use of MR fingerprinting. She and her colleagues have worked on several other research papers using this technique, including 2 others at AES 2021.

Wang, the research director and staff scientist at the Comprehensive Epilepsy Center of Cleveland Clinic, noted that the decision to use a radiomics-based approach was because its radar independent. In an interview with NeurologyLive®, she provided background on the results observed, the most notable take-home points, and the advantages of adjusting MR fingerprinting. She also discussed whether her approach could be replicated for further use in other epilepsy-related areas.

REFERENCE

Choi JY, Su T, Hu S, et al. MR Fingerprinting radiomics for characterization of focal cortical dysplasia. Presented at AES Annual Meeting; December 3-7, 2021; Chicago, IL. Poster 3.235