Search for: All records

We propose an innovative machine learning paradigm enabling precision medicine for AD biomarker discovery. The paradigm tailors the imaging biomarker discovery process to individual characteristics of a given patient. We implement this paradigm using a newly developed learning-to-rank method 𝙿𝙻𝚃𝚁 . The 𝙿𝙻𝚃𝚁 model seamlessly integrates two objectives for joint optimization: pushing up relevant biomarkers and ranking among relevant biomarkers. The empirical study of 𝙿𝙻𝚃𝚁 conducted on the ADNI data yields promising results to identify and prioritize individual-specific amyloid imaging biomarkers based on the individual’s structural MRI data. The resulting top ranked imaging biomarker has the potential to aid personalizedmore »diagnosis and disease subtyping.« less

Brain imaging genetics is an important research topic in brain science, which combines genetic variations and brain structures or functions to uncover the genetic basis of brain disorders. Imaging data collected by different technologies, measuring the same brain distinctly, might carry complementary but different information. Unfortunately, we do not know the extent to which phenotypic variance is shared among multiple imaging modalities, which might trace back to the complex genetic mechanism. In this study, we propose a novel dirty multi-task SCCA to analyze imaging genetics problems with multiple modalities of brain imaging quantitative traits (QTs) involved. The proposed method canmore »not only identify the shared SNPs and QTs across multiple modalities, but also identify the modality-specific SNPs and QTs, showing a flexible capability of discovering the complex multi-SNP-multi-QT associations. Compared with the multi-view SCCA and multi-task SCCA, our method shows better canonical correlation coefficients and canonical weights on both synthetic and real neuroimaging genetic data. This demonstrates that the proposed dirty multi-task SCCA could be a meaningful and powerful alternative method in multi-modal brain imaging genetics.« less

Dynamic nuclear polarization (DNP) has enabled enormous gains in magnetic resonance signals and led to vastly accelerated NMR/MRI imaging and spectroscopy. Unlike conventionalcw-techniques, DNP methods that exploit the full electron spectrum are appealing since they allow direct participation of all electrons in the hyperpolarization process. Such methods typically entail sweeps of microwave radiation over the broad electron linewidth to excite DNP but are often inefficient because the sweeps, constrained by adiabaticity requirements, are slow. In this paper, we develop a technique to overcome the DNP bottlenecks set by the slow sweeps, using a swept microwave frequency comb that increases themore »effective number of polarization transfer events while respecting adiabaticity constraints. This allows a multiplicative gain in DNP enhancement, scaling with the number of comb frequencies and limited only by the hyperfine-mediated electron linewidth. We demonstrate the technique for the optical hyperpolarization of¹³C nuclei in powdered microdiamonds at low fields, increasing the DNP enhancement from 30 to 100 measured with respect to the thermal signal at 7T. For low concentrations of broad linewidth electron radicals [e.g., TEMPO ((2,2,6,6-tetramethylpiperidin-1-yl)oxyl)], these multiplicative gains could exceed an order of magnitude.

« less