Enhancing Consistency in Neuroimaging With AI and Image Harmonization: Lianrui Zuo, MSE

In the advancing field of medical research and diagnostics, neuroimaging plays an important role in understanding complex neurological disorders such as multiple sclerosis (MS); however, it is not a process without challenges. Neuroimaging data collected from different clinic centers, hospitals, and even manufacturers, often exhibit variations in image contrast, which may lead to some difficulties comparing the data and final analysis.

Recently, Lianrui Zuo, MSE, a PhD student in the Department of Electrical and Computer Engineering at Johns Hopkins University, presented on impacts and solutions of inconsistent imaging data acquisition in a platform session focused on imaging topics at the 2023 Consortium of Multiple Sclerosis Centers (CMSC) Annual Meeting, May 31 to June 3, in Aurora, Colorado.¹ The rest of the speakers in the session discussed topics such as progressive steps towards a standardized MRI protocol, spinal cord measurement in clinical MRI, and the relationship between baseline cognitive performance and brain volume outcomes in patients with MS.

Zuo sat down in an interview with NeurologyLive® at the meeting to provide an overview of his research based on the presentation. He discussed how image harmonization using artificial intelligence (AI) can help to alleviate the challenges caused by multisite effects in neuroimaging. He also talked about the importance of prioritizing consistent data acquisition in studies involving gray matter volume and patient age relationships among patients with MS. Furthermore, Zuo spoke about the role of AI tools in standardizing image data acquired from different centers and manufacturers in the field of neuroimaging.