Kelley Marie Swanberg

Om mig

Kelley M. Swanberg, Ph.D. is a biomedical engineer who specializes in the methods and applications of ultra-high-field (7+ tesla) clinical and preclinical in vivo proton magnetic resonance spectroscopy (1H MRS) and imaging (MRI). She received her BA in Neurobiology from Harvard University in Cambridge, MA, USA; her MSc in East-West Medicine, Korean Medicine from Kyung Hee University in Seoul, South Korea; and her MSc and PhD in Biomedical Engineering from Columbia University in New York, NY, USA.

Since beginning her career in magnetic resonance (MR) at the Yale School of Medicine Magnetic Resonance Research Center (MRRC) in 2015, Dr. Swanberg has been methodologically interested in pushing the limits of synthetic data and multivariate analysis thereof, like machine learning and its generative cousins, to understand and control the errors inherent in MR data acquisitions. She is topically interested in employing these acquisitions, together with experts in non-MR methods like immunohistochemistry (IHC), ultra-high performance liquid chromatography with tandem mass spectrometry (UPLC-MS/MS), and more, to better understand, as noninvasively and equivalently as possible in both preclinical models and human patients, the multitudinous faces and fundamental mechanisms of neurodegeneration.

Within EISLAB (Embedded Intelligent Systems) in Institutionen för system- och rymdteknik at Luleå tekniska universitet, Dr. Swanberg teaches classes in best practices within the application of artificial intelligence to complex problems in clinical medicine and biomedical research, especially image analysis.

In her research at the Lund University Faculty of Medicine, Dr. Swanberg is also driving the development of a novel MR-based method to noninvasively track potentially clinically significant cerebrospinal fluid (CSF)-mediated brain solute clearance in both mouse models and humans. She is additionally leading efforts to characterize the vascular, metabolic and anatomic signatures of early neurodegeneration in mouse models of Alzheimer's-like beta-amyloid aggregation, as well as to rigorously validate the potential of language-model (LM) artificial intelligence (AI) to streamline the comprehensive literature review of noninvasive magnetic-resonance research on neurofluid dynamics and Alzheimer's disease.