Many methods have been developed for estimating the parameters of biexponential decay signals, which arise throughout magnetic resonance relaxometry (MRR) and the physical sciences. This is an intrinsically ill-posed problem so that estimates can depend strongly on noise and underlying parameter values. Regularization has proven to be a remarkably efficient procedure for providing more reliable solutions to ill-posed problems, while, more recently, neural networks have been used for parameter estimation. We re-address the problem of parameter estimation in biexponential models by introducing a novel form of neural network regularization which we call input layer regularization (ILR). Here, inputs to the neural network are composed of a biexponential decay signal augmented by signals constructed from parameters obtained from a regularized nonlinear least-squares estimate of the two decay time constants. We find that ILR results in a reduction in the error of time constant estimates on the order of 15%-50% or more, depending on the metric used and signal-to-noise level, with greater improvement seen for the time constant of the more rapidly decaying component. ILR is compatible with existing regularization techniques and should be applicable to a wide range of parameter estimation problems.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10185331PMC
http://dx.doi.org/10.1002/mrc.5289DOI Listing

Publication Analysis

Top Keywords

parameter estimation
16
input layer
8
layer regularization
8
magnetic resonance
8
resonance relaxometry
8
biexponential decay
8
neural network
8
time constant
8
regularization
5
parameter
5

Similar Publications

The assessment of humans indirectly exposed to chemicals via the environment (HvE) is an assessment element of the Registration, Evaluation, Authorisation, and Restriction of Chemicals (REACH) regulation. The European Union System for the Evaluation of Substances (EUSES) is the default screening tool, aimed at prioritizing chemicals for further refinement/higher tier assessment. This review summarizes the approach used in EUSES, evaluates the state of the science in human exposure modeling via the environment, and identifies areas for further research to strengthen the confidence and applicability of EUSES for assessing HvE.

View Article and Find Full Text PDF

Causal associations between immune cells and psychiatric disorders: a bidirectional mendelian randomization analysis.

Naunyn Schmiedebergs Arch Pharmacol

January 2025

Graduate School of PLA Medical College, Chinese PLA General Hospital and PLA Medical College, 28 Fu Xing Road, Beijing, 100083, China.

Extensive researches illuminate a potential interplay between immune traits and psychiatric disorders. However, whether there is the causal relationship between the two remains an unresolved question. We conducted a two-sample bidirectional mendelian randomization by utilizing summary data of 731 immune cell traits from genome-wide association studies (GCST90001391-GCST90002121)) and 11 psychiatric disorders including attention deficit/hyperactivity disorder (ADHD), anxiety disorder, autism spectrum disorder (ASD), bipolar disorder (BIP), anorexia nervosa (AN), major depressive disorder (MDD), obsessive-compulsive disorder (OCD), Tourette syndrome (TS), post-traumatic stress disorder (PTSD), schizophrenia (SCZ), and substance use disorders (cannabis) (SUD) from the Psychiatric Genomics Consortium (PGC).

View Article and Find Full Text PDF

Implicit solvation models permit the approximate description of solute-solvent interactions, where water is the most often considered solvent due to its relevance in biological systems. The use of other solvents is less common but is relevant for applications such as in nuclear magnetic resonance (NMR) or chromatography. As an example, chloroform is commonly used in anisotropic NMR to measure residual dipolar couplings (RDCs) of chiral analytes weakly aligned by an alignment medium.

View Article and Find Full Text PDF

Rapid validation of newly predicted materials through autonomous synthesis requires real-time adaptive control methods that exploit physics knowledge, a capability that is lacking in most systems. Here, we demonstrate an approach to enable real-time control of thin film synthesis by combining optical diagnostics with a Bayesian state estimation method. We developed a physical model for film growth and applied the direct filter (DF) method for real-time estimation of nucleation and growth rates during pulsed laser deposition (PLD).

View Article and Find Full Text PDF

Fire safety in healthcare facilities is extremely important due to limited evacuation capacity of occupants. Therefore, poor fire safety precautions lead to more fatalities and financial losses. This study introduces an effective fire risk management approach for healthcare buildings utilizing an interval valued neutrosophic-fuzzy framework.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!