AI Article Synopsis
- A new method for creating high-quality attenuation maps improves the accuracy of myocardial perfusion imaging, addressing shortcomings of traditional methods like filtered backprojection (FBP).
- This Bayesian iterative algorithm uses a smart prior to enhance accuracy in soft-tissue areas while adapting to lung and bone regions, leading to more uniform attenuation estimates across diverse body mass indices (BMIs).
- The results show significant improvements in image quality and accuracy, with less variability in myocardial wall measurements across different BMI groups compared to traditional methods.
Article Abstract
Background: High-quality attenuation maps are critical for attenuation correction of myocardial perfusion single photon emission computed tomography studies. The filtered backprojection (FBP) approach can introduce errors, especially with low-count transmission data. We present a new method for attenuation map reconstruction and examine its performance in phantom and patient data.
Methods And Results: The Bayesian iterative transmission gradient algorithm incorporates a spatially varying gamma prior function that preferentially weights estimated attenuation coefficients toward the soft-tissue value while allowing data-driven solutions for lung and bone regions. The performance with attenuation-corrected technetium 99m sestamibi clinical images was evaluated in phantom studies and in 50 low-likelihood patients grouped by body mass index (BMI). The algorithm converged in 15 iterations in the phantom studies. For the clinical studies, soft-tissue estimates had significantly greater uniformity of mediastinal coefficients (mean SD, 0.005 cm(-1) vs 0.011 cm(-1); P < .0001). The accuracy and uniformity of the Bayesian iterative transmission gradient algorithm were independent of BMI, whereas both declined at higher BMI values with FBP. Attenuation-corrected perfusion images showed improvement in myocardial wall variability (4.8% to 4.1%, P = .02) for all BMI groups with the new method compared with FBP.
Conclusion: This new method for attenuation map reconstruction provides rapidly converging and accurate attenuation maps over a wide spectrum of patient BMI values and significantly improves attenuation-corrected perfusion images.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.nuclcard.2007.02.004 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Bayesian Analysis of Exponential Random Graph Models Using Stochastic Gradient Markov Chain Monte Carlo.
Bayesian Anal
June 2024
Department of Statistics, Purdue University, West Lafayette, IN 47907, USA.
The exponential random graph model (ERGM) is a popular model for social networks, which is known to have an intractable likelihood function. Sampling from the posterior for such a model is a long-standing problem in statistical research. We analyze the performance of the stochastic gradient Langevin dynamics (SGLD) algorithm (also known as noisy Longevin Monte Carlo) in tackling this problem, where the stochastic gradient is calculated via running a short Markov chain (the so-called inner Markov chain in this paper) at each iteration.
View Article and Find Full Text PDFZero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems.
Comput Vis ECCV
November 2024
University of Minnesota, Minneapolis.
Diffusion models have emerged as powerful generative techniques for solving inverse problems. Despite their success in a variety of inverse problems in imaging, these models require many steps to converge, leading to slow inference time. Recently, there has been a trend in diffusion models for employing sophisticated noise schedules that involve more frequent iterations of timesteps at lower noise levels, thereby improving image generation and convergence speed.
View Article and Find Full Text PDFBayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing.
Light Sci Appl
January 2025
School of Mechanical Engineering, Purdue University, 585 Purdue Mall, West Lafayette, IN, 47907, USA.
Multi-photon polymerization is a well-established, yet actively developing, additive manufacturing technique for 3D printing on the micro/nanoscale. Like all additive manufacturing techniques, determining the process parameters necessary to achieve dimensional accuracy for a structure 3D printed using this method is not always straightforward and can require time-consuming experimentation. In this work, an active machine learning based framework is presented for determining optimal process parameters for the recently developed, high-speed, layer-by-layer continuous projection 3D printing process.
View Article and Find Full Text PDFRobust estimation of skin physiological parameters from hyperspectral images using Bayesian neural networks.
J Biomed Opt
January 2025
University of Ljubljana, Faculty of Mathematics and Physics, Ljubljana, Slovenia.
Significance: Machine learning models for the direct extraction of tissue parameters from hyperspectral images have been extensively researched recently, as they represent a faster alternative to the well-known iterative methods such as inverse Monte Carlo and inverse adding-doubling (IAD).
Aim: We aim to develop a Bayesian neural network model for robust prediction of physiological parameters from hyperspectral images.
Approach: We propose a two-component system for extracting physiological parameters from hyperspectral images.
Human-in-the-loop optimization of wearable device parameters using an EMG-based objective function.
Wearable Technol
November 2024
BruBotics, Vrije Universiteit Brussel, Brussels, 1050, Belgium.
Advancements in wearable robots aim to improve user motion, motor control, and overall experience by minimizing energetic cost (EC). However, EC is challenging to measure and it is typically indirectly estimated through respiratory gas analysis. This study introduces a novel EMG-based objective function that captures individuals' natural energetic expenditure during walking.
View Article and Find Full Text PDFWant 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!