arXiv subjects

Amirreza Hashemi

Publications and source records attributed to Amirreza Hashemi.

8 recordsLinked to original sources

arXiv2025

Application of Spherical Convolutional Neural Networks to Image Reconstruction and Denoising in Nuclear Medicine

This work investigates use of equivariant neural networks as efficient and high-performance frameworks for image reconstruction and denoising in nuclear medicine. Our work aims to tackle limitations of conventional Convolutional Neural Networks (CNNs), which require significant training. We investigated equivariant networks, aiming to reduce CNN's dependency on specific training sets. Specifically, we implemented and evaluated equivariant spherical CNNs (SCNNs) for 2- and 3-dimensional medical imaging problems. Our results demonstrate superior quality and computational efficiency of SCNNs in both image reconstruction and denoising benchmark problems. Furthermore, we propose a novel approach to employ SCNNs as a complement to conventional image reconstruction tools, enhancing the outcomes while reducing reliance on the training set. Across all cases, we observed significant decrease in computational cost by leveraging the inherent inclusion of equivariant representatives while achieving the same or higher quality of image processing using SCNNs compared to CNNs. Additionally, we explore the potential of SCNNs for broader tomography applications, particularly those requiring rotationally variant representation.

eess.IV↗

arXiv2025

A novel perspective on denoising using quantum localization with application to medical imaging

Background noise in many fields such as medical imaging poses significant challenges for accurate diagnosis, prompting the development of denoising algorithms. Traditional methodologies, however, often struggle to address the complexities of noisy environments in high dimensional imaging systems. This paper introduces a novel quantum-inspired approach for image denoising, drawing upon principles of quantum and condensed matter physics. Our approach views medical images as amorphous structures akin to those found in condensed matter physics and we propose an algorithm that incorporates the concept of mode resolved localization directly into the denoising process. Notably, unlike previous studies that considered localization as a hindrance, our approach considers quantum localization as a fundamental component of image reconstruction which is used to differentiate between noisy and non-noisy modes based on diffusivity and localization measurements. This perspective eliminates the need for hyperparameter tuning, making the proposed method a standalone algorithm which can be implemented with minimal manual intervention and can perform automatic filtering of noise regardless of noise level. Through numerical validation, we showcase the effectiveness of our approach in addressing noise-related challenges in imaging and especially medical imaging, underscoring its relevance for possible quantum computing applications.

eess.IV↗

arXiv2024

Flexible and Generic Framework for Complex Nuclear Medicine Scanners using FreeCAD/GDML Workbench

The design of nuclear imaging scanners is crucial for optimizing detection and imaging processes. While advancements have been made in simplistic, symmetrical modalities, current research is progressing towards more intricate structures, however, the widespread adoption of computer-aided design (CAD) tools for modeling and simulation is still limited. This paper introduces FreeCAD and the GDML Workbench as essential tools for designing and testing complex geometries in nuclear imaging modalities. FreeCAD is a parametric 3D CAD modeler, and GDML is an XML-based language for describing complex geometries in simulations. Their integration streamlines the design and simulation of nuclear medicine scanners, including PET and SPECT scanners. The paper demonstrates their application in creating calibration phantoms and conducting simulations with Geant4, showcasing their precision and versatility in generating sophisticated components for nuclear imaging. The integration of these tools is expected to streamline design processes, enhance efficiency, and facilitate widespread application in the nuclear imaging field.

physics.med-ph↗

arXiv2024

AutoVisual Fusion Suite: A Comprehensive Evaluation of Image Segmentation and Voice Conversion Tools on HuggingFace Platform

This study presents a comprehensive evaluation of tools available on the HuggingFace platform for two pivotal applications in artificial intelligence: image segmentation and voice conversion. The primary objective was to identify the top three tools within each category and subsequently install and configure these tools on Linux systems. We leveraged the power of pre-trained segmentation models such as SAM and DETR Model with ResNet-50 backbone for image segmentation, and the so-vits-svc-fork model for voice conversion. This paper delves into the methodologies and challenges encountered during the implementation process, and showcases the successful combination of video segmentation and voice conversion in a unified project named AutoVisual Fusion Suite.

cs.CV↗

arXiv2021

Ab initio phonon transport across grain boundaries in graphene using machine learning based on small dataset

Establishing the structure-property relationship for grain boundaries (GBs) is critical for developing next generation functional materials, but has been severely hampered due to its extremely large configurational space. Atomistic simulations with low computational cost and high predictive power are strongly desirable, but the conventional simulations using empirical interatomic potentials and density functional theory suffer from the lack of predictive power and high computational cost, respectively. A machine learning interatomic potential (MLIP) recently emerged but often requires an extensive size of the training dataset, making it a less feasible approach. Here we demonstrate that an MLIP trained with a rationally designed small training dataset can predict thermal transport across GBs in graphene with ab initio accuracy at an affordable computational cost. In particular, we employed a rational approach based on the structural unit model to find a small set of GBs that can represent the entire configurational space and thus can serve as a cost-effective training dataset for the MLIP. Only 5 GBs were found to be enough to represent the entire configurational space of graphene GBs. Using the atomistic Green's function approach and the MLIP, we revealed that the structure-thermal resistance relation in graphene does not follow the common understanding that large dislocation density causes larger thermal resistance. In fact, thermal resistance is nearly independent of dislocation density at room temperature and is higher when the dislocation density is small at sub-room temperature. We explain this intriguing behavior with the buckling near a GB causing a strong scattering of flexural phonon modes.

cond-mat.mtrl-sci↗

arXiv2020

Graph Convolutional Neural Networks for Body Force Prediction

Many scientific and engineering processes produce spatially unstructured data. However, most data-driven models require a feature matrix that enforces both a set number and order of features for each sample. They thus cannot be easily constructed for an unstructured dataset. Therefore, a graph based data-driven model to perform inference on fields defined on an unstructured mesh, using a Graph Convolutional Neural Network (GCNN) is presented. The ability of the method to predict global properties from spatially irregular measurements with high accuracy is demonstrated by predicting the drag force associated with laminar flow around airfoils from scattered velocity measurements. The network can infer from field samples at different resolutions, and is invariant to the order in which the measurements within each sample are presented. The GCNN method, using inductive convolutional layers and adaptive pooling, is able to predict this quantity with a validation $R^{2}$ above 0.98, and a Normalized Mean Squared Error below 0.01, without relying on spatial structure.

cs.LG↗

arXiv2019

Equal bi-Vectorized (EBV) method to high performance on GPU

Due to importance of reducing of time solution in numerical codes, we propose an algorithm for parallel LU decomposition solver for dense and sparse matrices on GPU. This algorithm is based on first bi-vectorizing a triangular matrices of decomposed coefficient matrix and then equalizing vectors. So we improve performance of LU decomposition on equal contributed scheme on threads. This algorithm also is convenient for other parallelism method and multi devices. Several test cases show advantage of this method over other familiar method.

cs.DC↗

arXiv2019

Machine-learning based interatomic potential for phonon transport in perfect crystalline Si and crystalline Si with vacancies

We report that single interatomic potential, developed using Gaussian regression of density functional theory calculation data, has high accuracy and flexibility to describe phonon transport with ab initio accuracy in two different atomistic configurations: perfect crystalline Si and crystalline Si with vacancies. The high accuracy of second- and third-order force constants from the Gaussian approximation potential (GAP) are demonstrated with phonon dispersion, Grüneisen parameter, three-phonon scattering rate, phonon-vacancy scattering rate, and thermal conductivity, all of which are very close to the results from density functional theory calculation. We also show that the widely used empirical potentials (Stillinger-Weber and Tersoff) produce much larger errors compared to the GAP. The computational cost of GAP is higher than the two empirical potentials, but five orders of magnitude lower than the density functional theory calculation. Our work shows that GAP can provide a new opportunity for studying phonon transport in partially disordered crystalline phases with the high predictive power of ab initio calculation but at a feasible computational cost.

cond-mat.mtrl-sci↗