etc. Given a low resolution image, it aims to reconstruct a high resolution
image. The problem is ill-posed since there can be more than one high resolution
image corresponding to the same low-resolution image. To address this problem, a
number of machine learning-based approaches have been proposed.
In this dissertation, I present my works on single image super-resolution (SISR)
and accelerated magnetic resonance imaging (MRI) (a.k.a. super-resolution on MR
images), followed by the investigation on transfer learning for accelerated MRI reconstruction.
For the SISR, a dictionary-based approach and two reconstruction based
approaches are presented. To be precise, a convex dictionary learning (CDL)
algorithm is proposed by constraining the dictionary atoms to be formed by nonnegative
linear combination of the training data, which is a natural, desired property.
Also, two reconstruction-based single methods are presented, which make use
of (i)the joint regularization, where a group-residual-based regularization (GRR) and
a ridge-regression-based regularization (3R) are combined; (ii)the collaborative representation
and non-local self-similarity. After that, two deep learning approaches
are proposed, aiming at reconstructing high-quality images from accelerated MRI
acquisition. Residual Dense Block (RDB) and feedback connection are introduced
in the proposed models. In the last chapter, the feasibility of transfer learning for
accelerated MRI reconstruction is discussed.
To overcome the above data scarcity and generalization issues, in my dissertation, I first propose two unsupervised conventional machine learning algorithms, hyperbolic stochastic coding, and multi-resemble multi-target low-rank coding, to solve the incomplete data and missing label problem. I further introduce a deep multi-domain adaptation network to leverage the power of deep learning by transferring the rich knowledge from a large-amount labeled source dataset. I also invent a novel time-sequence dynamically hierarchical network that adaptively simplifies the network to cope with the scarce data.
To learn a large number of unseen concepts, lifelong machine learning enjoys many advantages, including abstracting knowledge from prior learning and using the experience to help future learning, regardless of how much data is currently available. Incorporating this capability and making it versatile, I propose deep multi-task weight consolidation to accumulate knowledge continuously and significantly reduce data requirements in a variety of domains. Inspired by the recent breakthroughs in automatically learning suitable neural network architectures (AutoML), I develop a nonexpansive AutoML framework to train an online model without the abundance of labeled data. This work automatically expands the network to increase model capability when necessary, then compresses the model to maintain the model efficiency.
In my current ongoing work, I propose an alternative method of supervised learning that does not require direct labels. This could utilize various supervision from an image/object as a target value for supervising the target tasks without labels, and it turns out to be surprisingly effective. The proposed method only requires few-shot labeled data to train, and can self-supervised learn the information it needs and generalize to datasets not seen during training.
Human protein diversity arises as a result of alternative splicing, single nucleotide polymorphisms (SNPs) and posttranslational modifications. Because of these processes, each protein can exists as multiple variants in vivo. Tailored strategies are needed to study these protein variants and understand their role in health and disease. In this work we utilized quantitative mass spectrometric immunoassays to determine the protein variants concentration of beta-2-microglobulin, cystatin C, retinol binding protein, and transthyretin, in a population of 500 healthy individuals. Additionally, we determined the longitudinal concentration changes for the protein variants from four individuals over a 6 month period. Along with the native forms of the four proteins, 13 posttranslationally modified variants and 7 SNP-derived variants were detected and their concentration determined. Correlations of the variants concentration with geographical origin, gender, and age of the individuals were also examined. This work represents an important step toward building a catalog of protein variants concentrations and examining their longitudinal changes.
A globally integrated carbon observation and analysis system is needed to improve the fundamental understanding of the global carbon cycle, to improve our ability to project future changes, and to verify the effectiveness of policies aiming to reduce greenhouse gas emissions and increase carbon sequestration. Building an integrated carbon observation system requires transformational advances from the existing sparse, exploratory framework towards a dense, robust, and sustained system in all components: anthropogenic emissions, the atmosphere, the ocean, and the terrestrial biosphere. The paper is addressed to scientists, policymakers, and funding agencies who need to have a global picture of the current state of the (diverse) carbon observations.
We identify the current state of carbon observations, and the needs and notional requirements for a global integrated carbon observation system that can be built in the next decade. A key conclusion is the substantial expansion of the ground-based observation networks required to reach the high spatial resolution for CO2 and CH4 fluxes, and for carbon stocks for addressing policy-relevant objectives, and attributing flux changes to underlying processes in each region. In order to establish flux and stock diagnostics over areas such as the southern oceans, tropical forests, and the Arctic, in situ observations will have to be complemented with remote-sensing measurements. Remote sensing offers the advantage of dense spatial coverage and frequent revisit. A key challenge is to bring remote-sensing measurements to a level of long-term consistency and accuracy so that they can be efficiently combined in models to reduce uncertainties, in synergy with ground-based data.
Bringing tight observational constraints on fossil fuel and land use change emissions will be the biggest challenge for deployment of a policy-relevant integrated carbon observation system. This will require in situ and remotely sensed data at much higher resolution and density than currently achieved for natural fluxes, although over a small land area (cities, industrial sites, power plants), as well as the inclusion of fossil fuel CO2 proxy measurements such as radiocarbon in CO2 and carbon-fuel combustion tracers. Additionally, a policy-relevant carbon monitoring system should also provide mechanisms for reconciling regional top-down (atmosphere-based) and bottom-up (surface-based) flux estimates across the range of spatial and temporal scales relevant to mitigation policies. In addition, uncertainties for each observation data-stream should be assessed. The success of the system will rely on long-term commitments to monitoring, on improved international collaboration to fill gaps in the current observations, on sustained efforts to improve access to the different data streams and make databases interoperable, and on the calibration of each component of the system to agreed-upon international scales.
The apolipoprotein E (APOE) e4 allele is the most prevalent genetic risk factor for Alzheimer's disease (AD). Hippocampal volumes are generally smaller in AD patients carrying the e4 allele compared to e4 noncarriers. Here we examined the effect of APOE e4 on hippocampal morphometry in a large imaging database—the Alzheimer's Disease Neuroimaging Initiative (ADNI). We automatically segmented and constructed hippocampal surfaces from the baseline MR images of 725 subjects with known APOE genotype information including 167 with AD, 354 with mild cognitive impairment (MCI), and 204 normal controls. High-order correspondences between hippocampal surfaces were enforced across subjects with a novel inverse consistent surface fluid registration method. Multivariate statistics consisting of multivariate tensor-based morphometry (mTBM) and radial distance were computed for surface deformation analysis. Using Hotelling's T2 test, we found significant morphological deformation in APOE e4 carriers relative to noncarriers in the entire cohort as well as in the nondemented (pooled MCI and control) subjects, affecting the left hippocampus more than the right, and this effect was more pronounced in e4 homozygotes than heterozygotes. Our findings are consistent with previous studies that showed e4 carriers exhibit accelerated hippocampal atrophy; we extend these findings to a novel measure of hippocampal morphometry. Hippocampal morphometry has significant potential as an imaging biomarker of early stage AD.
Mild Cognitive Impairment (MCI) is a transitional stage between normal aging and dementia and people with MCI are at high risk of progression to dementia. MCI is attracting increasing attention, as it offers an opportunity to target the disease process during an early symptomatic stage. Structural magnetic resonance imaging (MRI) measures have been the mainstay of Alzheimer's disease (AD) imaging research, however, ventricular morphometry analysis remains challenging because of its complicated topological structure. Here we describe a novel ventricular morphometry system based on the hyperbolic Ricci flow method and tensor-based morphometry (TBM) statistics. Unlike prior ventricular surface parameterization methods, hyperbolic conformal parameterization is angle-preserving and does not have any singularities. Our system generates a one-to-one diffeomorphic mapping between ventricular surfaces with consistent boundary matching conditions. The TBM statistics encode a great deal of surface deformation information that could be inaccessible or overlooked by other methods. We applied our system to the baseline MRI scans of a set of MCI subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI: 71 MCI converters vs. 62 MCI stable). Although the combined ventricular area and volume features did not differ between the two groups, our fine-grained surface analysis revealed significant differences in the ventricular regions close to the temporal lobe and posterior cingulate, structures that are affected early in AD. Significant correlations were also detected between ventricular morphometry, neuropsychological measures, and a previously described imaging index based on fluorodeoxyglucose positron emission tomography (FDG-PET) scans. This novel ventricular morphometry method may offer a new and more sensitive approach to study preclinical and early symptomatic stage AD.
Errors in the specification or utilization of fossil fuel CO2 emissions within carbon budget or atmospheric CO2 inverse studies can alias the estimation of biospheric and oceanic carbon exchange. A key component in the simulation of CO2 concentrations arising from fossil fuel emissions is the spatial distribution of the emission near coastlines. Regridding of fossil fuel CO2 emissions (FFCO2) from fine to coarse grids to enable atmospheric transport simulations can give rise to mismatches between the emissions and simulated atmospheric dynamics which differ over land or water. For example, emissions originally emanating from the land are emitted from a grid cell for which the vertical mixing reflects the roughness and/or surface energy exchange of an ocean surface. We test this potential "dynamical inconsistency" by examining simulated global atmospheric CO2 concentration driven by two different approaches to regridding fossil fuel CO2 emissions. The two approaches are as follows: (1) a commonly used method that allocates emissions to grid cells with no attempt to ensure dynamical consistency with atmospheric transport and (2) an improved method that reallocates emissions to grid cells to ensure dynamically consistent results. Results show large spatial and temporal differences in the simulated CO2 concentration when comparing these two approaches. The emissions difference ranges from −30.3 TgC grid cell-1 yr-1 (−3.39 kgC m-2 yr-1) to +30.0 TgC grid cell-1 yr-1 (+2.6 kgC m-2 yr-1) along coastal margins. Maximum simulated annual mean CO2 concentration differences at the surface exceed ±6 ppm at various locations and times. Examination of the current CO2 monitoring locations during the local afternoon, consistent with inversion modeling system sampling and measurement protocols, finds maximum hourly differences at 38 stations exceed ±0.10 ppm with individual station differences exceeding −32 ppm. The differences implied by not accounting for this dynamical consistency problem are largest at monitoring sites proximal to large coastal urban areas and point sources. These results suggest that studies comparing simulated to observed atmospheric CO2 concentration, such as atmospheric CO2 inversions, must take measures to correct for this potential problem and ensure flux and dynamical consistency.
High-resolution, global quantification of fossil fuel CO[subscript 2] emissions is emerging as a critical need in carbon cycle science and climate policy. We build upon a previously developed fossil fuel data assimilation system (FFDAS) for estimating global high-resolution fossil fuel CO[subscript 2] emissions. We have improved the underlying observationally based data sources, expanded the approach through treatment of separate emitting sectors including a new pointwise database of global power plants, and extended the results to cover a 1997 to 2010 time series at a spatial resolution of 0.1°. Long-term trend analysis of the resulting global emissions shows subnational spatial structure in large active economies such as the United States, China, and India. These three countries, in particular, show different long-term trends and exploration of the trends in nighttime lights, and population reveal a decoupling of population and emissions at the subnational level. Analysis of shorter-term variations reveals the impact of the 2008–2009 global financial crisis with widespread negative emission anomalies across the U.S. and Europe. We have used a center of mass (CM) calculation as a compact metric to express the time evolution of spatial patterns in fossil fuel CO[subscript 2] emissions. The global emission CM has moved toward the east and somewhat south between 1997 and 2010, driven by the increase in emissions in China and South Asia over this time period. Analysis at the level of individual countries reveals per capita CO[subscript 2] emission migration in both Russia and India. The per capita emission CM holds potential as a way to succinctly analyze subnational shifts in carbon intensity over time. Uncertainties are generally lower than the previous version of FFDAS due mainly to an improved nightlight data set.
Proteins can exist as multiple proteoforms in vivo, as a result of alternative splicing and single-nucleotide polymorphisms (SNPs), as well as posttranslational processing. To address their clinical significance in a context of diagnostic information, proteoforms require a more in-depth analysis. Mass spectrometric immunoassays (MSIA) have been devised for studying structural diversity in human proteins. MSIA enables protein profiling in a simple and high-throughput manner, by combining the selectivity of targeted immunoassays, with the specificity of mass spectrometric detection. MSIA has been used for qualitative and quantitative analysis of single and multiple proteoforms, distinguishing between normal fluctuations and changes related to clinical conditions. This mini review offers an overview of the development and application of mass spectrometric immunoassays for clinical and population proteomics studies. Provided are examples of some recent developments, and also discussed are the trends and challenges in mass spectrometry-based immunoassays for the next-phase of clinical applications.
Introduction: Apolipoprotein C-III (apoC-III) regulates triglyceride (TG) metabolism. In plasma, apoC-III exists in non-sialylated (apoC-III0a without glycosylation and apoC-III[subscript 0b] with glycosylation), monosialylated (apoC-III1) or disialylated (apoC-III2) proteoforms. Our aim was to clarify the relationship between apoC-III sialylation proteoforms with fasting plasma TG concentrations.
Methods: In 204 non-diabetic adolescent participants, the relative abundance of apoC-III plasma proteoforms was measured using mass spectrometric immunoassay.
Results: Compared with the healthy weight subgroup (n = 16), the ratios of apoC-III0a, apoC-III0b, and apoC-III1 to apoC-III2 were significantly greater in overweight (n = 33) and obese participants (n = 155). These ratios were positively correlated with BMI z-scores and negatively correlated with measures of insulin sensitivity (S[subscript i]). The relationship of apoC-III1 / apoC-III2 with Si persisted after adjusting for BMI (p = 0.02). Fasting TG was correlated with the ratio of apoC-III0a / apoC-III2 (r = 0.47, p<0.001), apoC-III0b / apoC-III2 (r = 0.41, p<0.001), apoC-III1 / apoC-III2 (r = 0.43, p<0.001). By examining apoC-III concentrations, the association of apoC-III proteoforms with TG was driven by apoC-III0a (r = 0.57, p<0.001), apoC-III0b (r = 0.56. p<0.001) and apoC-III1 (r = 0.67, p<0.001), but not apoC-III2 (r = 0.006, p = 0.9) concentrations, indicating that apoC-III relationship with plasma TG differed in apoC-III2 compared with the other proteoforms.
Conclusion: We conclude that apoC-III0a, apoC-III0b, and apoC-III1, but not apoC-III2 appear to be under metabolic control and associate with fasting plasma TG. Measurement of apoC-III proteoforms can offer insights into the biology of TG metabolism in obesity.