Publications by authors named "M A Anastasio"
Medical imaging systems are commonly assessed and optimized by the use of objective measures of image quality (IQ). The performance of the ideal observer (IO) acting on imaging measurements has long been advocated as a figure-of-merit to guide the optimization of imaging systems. For computed imaging systems, the performance of the IO acting on imaging measurements also sets an upper bound on task-performance that no image reconstruction method can transcend.
View Article and Find Full Text PDFIn certain three-dimensional (3D) applications of photoacoustic computed tomography (PACT), including \textit{in vivo} breast imaging, hemispherical measurement apertures that enclose the object within their convex hull are employed for data acquisition. Data acquired with such measurement geometries are referred to as \textit{half-scan} data, as only half of a complete spherical measurement aperture is employed. Although previous studies have demonstrated that half-scan data can uniquely and stably reconstruct the sought-after object, no closed-form reconstruction formula for use with half-scan data has been reported.
View Article and Find Full Text PDFArticle Synopsis
- qPACT is an advanced medical imaging technique that aims to provide detailed images of important physiological metrics like hemoglobin levels and oxygen saturation, but its image reconstruction involves complex, non-linear mathematical challenges.
- There is currently no standardized design for qPACT systems, leading to uncertainty about which system designs are optimal for different medical applications.
- This research introduces a new computational method for optimizing the design of qPACT systems using the Bayesian Cramér-Rao bound, demonstrating its effectiveness through numerical simulations, marking a significant advancement in the field of imaging governed by partial differential equations.
Background: The findings of the 2023 AAPM Grand Challenge on Deep Generative Modeling for Learning Medical Image Statistics are reported in this Special Report.
Purpose: The goal of this challenge was to promote the development of deep generative models for medical imaging and to emphasize the need for their domain-relevant assessments via the analysis of relevant image statistics.
Methods: As part of this Grand Challenge, a common training dataset and an evaluation procedure was developed for benchmarking deep generative models for medical image synthesis.
Article Synopsis
- Traditional metrics for measuring digital mammography and tomosynthesis image quality often fail to predict clinical performance, leading to the use of a more realistic breast phantom with randomized microcalcifications and deep learning for evaluation.
- The research focused on developing a methodology that combines an anthropomorphic breast phantom, a specific microcalcification detection task, and a convolutional neural network for automated performance assessment.
- Results showed that the ability to detect microcalcifications varied with the amount of radiation exposure, indicating that the new method is effective for evaluating different mammography technologies.