arXiv subjects

Amirkoushyar Ziabari

Publications and source records attributed to Amirkoushyar Ziabari.

15 recordsLinked to original sources

arXiv2026

Toward a Foundation Plug-and-Play Prior for Computed Tomography Reconstruction via a Multimodal Diffusion Model

Computed tomography (CT) throughput is limited by scan time, which grows with both the number of projections acquired and the detector integration time for each projection. Reconstructing high-quality volumes from sparse-view or low-dose measurements therefore depends on using an informative prior, typically a neural network trained for one specific scan setting and retrained whenever the modality, geometry, or material changes. We investigate whether a single diffusion model trained across several imaging domains can instead serve as a reusable prior for heterogeneous CT reconstruction problems. We evaluate the proposed method using the same diffusion visual transformer model and normalized denoising strength on three datasets that differ in modality, beam geometry, material, and degradation type, spanning additively manufactured metal parts and concrete microstructure imaged with cone-bean X-ray CT and parallel-beam neutron CT respectively. The proposed method improves upon analytic reconstructions in all three cases, demonstrating transferability across the evaluated problems and providing a step toward a reusable foundation prior for heterogeneous CT reconstruction.

cs.CV↗

arXiv2026

Regularizing INR with diffusion prior self-supervised 3D reconstruction of neutron computed tomography data

Recently, generative diffusion priors have made huge strides as inverse problem solvers, including the ability to be adapted for inference on out-of-distribution data. Concurrently, implicit neural representations (INRs) have emerged as fast and lightweight inverse imaging solvers that are amenable to hybrid approaches that combine learned priors with traditional inverse problem formulations. In this paper, we present a diffusive computed tomography (CT) inversion framework for regularizing INRs called Diffusive INR (DINR), designed to enable high-quality reconstruction from sparse-view neutron CT. Pretrained purely on synthetic data, DINR is evaluated on simulated and experimentally obtained observations of concrete microstructures, where traditional reconstruction methods suffer substantial degradation when the number of views is reduced. Our approach delivers superior performance, reduces reconstruction artifacts, and achieves gains in PSNR and SSIM, enabling accurate micro-structural characterization even under extreme data limitations compared to state-of-the-art sparse-view reconstruction techniques.

eess.IV↗

arXiv2026

Cross-Modal Guidance for Fast Diffusion-Based Computed Tomography

Diffusion models have emerged as powerful priors for solving inverse problems in computed tomography (CT). In certain applications, such as neutron CT, it can be expensive to collect large amounts of measurements even for a single scan, leading to sparse data sets from which it is challenging to obtain high quality reconstructions even with diffusion models. One strategy to mitigate this challenge is to leverage a complementary, easily available imaging modality; however, such approaches typically require retraining the diffusion model with large datasets. In this work, we propose incorporating an additional modality without retraining the diffusion prior, enabling accelerated imaging of costly modalities. We further examine the impact of imperfect side modalities on cross-modal guidance. Our method is evaluated on sparse-view neutron computed tomography, where reconstruction quality is substantially improved by incorporating X-ray computed tomography of the same samples.

cs.CV↗

arXiv2025

Plug-and-Play with 2.5D Artifact Reduction Prior for Fast and Accurate Industrial Computed Tomography Reconstruction

Cone-beam X-ray computed tomography (XCT) is an essential imaging technique for generating 3D reconstructions of internal structures, with applications ranging from medical to industrial imaging. Producing high-quality reconstructions typically requires many X-ray measurements; this process can be slow and expensive, especially for dense materials. Recent work incorporating artifact reduction priors within a plug-and-play (PnP) reconstruction framework has shown promising results in improving image quality from sparse-view XCT scans while enhancing the generalizability of deep learning-based solutions. However, this method uses a 2D convolutional neural network (CNN) for artifact reduction, which captures only slice-independent information from the 3D reconstruction, limiting performance. In this paper, we propose a PnP reconstruction method that uses a 2.5D artifact reduction CNN as the prior. This approach leverages inter-slice information from adjacent slices, capturing richer spatial context while remaining computationally efficient. We show that this 2.5D prior not only improves the quality of reconstructions but also enables the model to directly suppress commonly occurring XCT artifacts (such as beam hardening), eliminating the need for artifact correction pre-processing. Experiments on both experimental and synthetic cone-beam XCT data demonstrate that the proposed method better preserves fine structural details, such as pore size and shape, leading to more accurate defect detection compared to 2D priors. In particular, we demonstrate strong performance on experimental XCT data using a 2.5D artifact reduction prior trained entirely on simulated scans, highlighting the proposed method's ability to generalize across domains.

eess.IV↗

arXiv2025

A Learnt Half-Quadratic Splitting-Based Algorithm for Fast and High-Quality Industrial Cone-beam CT Reconstruction

Industrial X-ray cone-beam CT (XCT) scanners are widely used for scientific imaging and non-destructive characterization. Industrial CBCT scanners use large detectors containing millions of pixels and the subsequent 3D reconstructions can be of the order of billions of voxels. In order to obtain high-quality reconstruction when using typical analytic algorithms, the scan involves collecting a large number of projections/views which results in large measurement times - limiting the utility of the technique. Model-based iterative reconstruction (MBIR) algorithms can produce high-quality reconstructions from fast sparse-view CT scans, but are computationally expensive and hence are avoided in practice. Single-step deep-learning (DL) based methods have demonstrated that it is possible to obtain fast and high-quality reconstructions from sparse-view data but they do not generalize well to out-of-distribution scenarios. In this work, we propose a half-quadratic splitting-based algorithm that uses convolutional neural networks (CNN) in order to obtain high-quality reconstructions from large sparse-view cone-beam CT (CBCT) measurements while overcoming the challenges with typical approaches. The algorithm alternates between the application of a CNN and a conjugate gradient (CG) step enforcing data-consistency (DC). The proposed method outperforms other methods on the publicly available Walnuts data-set.

eess.IV↗

arXiv2025

A Fast, Scalable, and Robust Deep Learning-based Iterative Reconstruction Framework for Accelerated Industrial Cone-beam X-ray Computed Tomography

Cone-beam X-ray Computed Tomography (XCT) with large detectors and corresponding large-scale 3D reconstruction plays a pivotal role in micron-scale characterization of materials and parts across various industries. In this work, we present a novel deep neural network-based iterative algorithm that integrates an artifact reduction-trained CNN as a prior model with automated regularization parameter selection, tailored for large-scale industrial cone-beam XCT data. Our method achieves high-quality 3D reconstructions even for extremely dense thick metal parts - which traditionally pose challenges to industrial CT images - in just a few iterations. Furthermore, we show the generalizability of our approach to out-of-distribution scans obtained under diverse scanning conditions. Our method effectively handles significant noise and streak artifacts, surpassing state-of-the-art supervised learning methods trained on the same data.

cs.CV↗

arXiv2024

Adapting Segment Anything Model (SAM) to Experimental Datasets via Fine-Tuning on GAN-based Simulation: A Case Study in Additive Manufacturing

Industrial X-ray computed tomography (XCT) is a powerful tool for non-destructive characterization of materials and manufactured components. XCT commonly accompanied by advanced image analysis and computer vision algorithms to extract relevant information from the images. Traditional computer vision models often struggle due to noise, resolution variability, and complex internal structures, particularly in scientific imaging applications. State-of-the-art foundational models, like the Segment Anything Model (SAM)-designed for general-purpose image segmentation-have revolutionized image segmentation across various domains, yet their application in specialized fields like materials science remains under-explored. In this work, we explore the application and limitations of SAM for industrial X-ray CT inspection of additive manufacturing components. We demonstrate that while SAM shows promise, it struggles with out-of-distribution data, multiclass segmentation, and computational efficiency during fine-tuning. To address these issues, we propose a fine-tuning strategy utilizing parameter-efficient techniques, specifically Conv-LoRa, to adapt SAM for material-specific datasets. Additionally, we leverage generative adversarial network (GAN)-generated data to enhance the training process and improve the model's segmentation performance on complex X-ray CT data. Our experimental results highlight the importance of tailored segmentation models for accurate inspection, showing that fine-tuning SAM on domain-specific scientific imaging data significantly improves performance. However, despite improvements, the model's ability to generalize across diverse datasets remains limited, highlighting the need for further research into robust, scalable solutions for domain-specific segmentation tasks.

cs.CV↗

arXiv2024

2.5D Super-Resolution Approaches for X-ray Computed Tomography-based Inspection of Additively Manufactured Parts

X-ray computed tomography (XCT) is a key tool in non-destructive evaluation of additively manufactured (AM) parts, allowing for internal inspection and defect detection. Despite its widespread use, obtaining high-resolution CT scans can be extremely time consuming. This issue can be mitigated by performing scans at lower resolutions; however, reducing the resolution compromises spatial detail, limiting the accuracy of defect detection. Super-resolution algorithms offer a promising solution for overcoming resolution limitations in XCT reconstructions of AM parts, enabling more accurate detection of defects. While 2D super-resolution methods have demonstrated state-of-the-art performance on natural images, they tend to under-perform when directly applied to XCT slices. On the other hand, 3D super-resolution methods are computationally expensive, making them infeasible for large-scale applications. To address these challenges, we propose a 2.5D super-resolution approach tailored for XCT of AM parts. Our method enhances the resolution of individual slices by leveraging multi-slice information from neighboring 2D slices without the significant computational overhead of full 3D methods. Specifically, we use neighboring low-resolution slices to super-resolve the center slice, exploiting inter-slice spatial context while maintaining computational efficiency. This approach bridges the gap between 2D and 3D methods, offering a practical solution for high-throughput defect detection in AM parts.

eess.IV↗

arXiv2023

Deep learning based workflow for accelerated industrial X-ray Computed Tomography

X-ray computed tomography (XCT) is an important tool for high-resolution non-destructive characterization of additively-manufactured metal components. XCT reconstructions of metal components may have beam hardening artifacts such as cupping and streaking which makes reliable detection of flaws and defects challenging. Furthermore, traditional workflows based on using analytic reconstruction algorithms require a large number of projections for accurate characterization - leading to longer measurement times and hindering the adoption of XCT for in-line inspections. In this paper, we introduce a new workflow based on the use of two neural networks to obtain high-quality accelerated reconstructions from sparse-view XCT scans of single material metal parts. The first network, implemented using fully-connected layers, helps reduce the impact of BH in the projection data without the need of any calibration or knowledge of the component material. The second network, a convolutional neural network, maps a low-quality analytic 3D reconstruction to a high-quality reconstruction. Using experimental data, we demonstrate that our method robustly generalizes across several alloys, and for a range of sparsity levels without any need for retraining the networks thereby enabling accurate and fast industrial XCT inspections.

eess.IV↗

arXiv2022

YOLO2U-Net: Detection-Guided 3D Instance Segmentation for Microscopy

Microscopy imaging techniques are instrumental for characterization and analysis of biological structures. As these techniques typically render 3D visualization of cells by stacking 2D projections, issues such as out-of-plane excitation and low resolution in the $z$-axis may pose challenges (even for human experts) to detect individual cells in 3D volumes as these non-overlapping cells may appear as overlapping. In this work, we introduce a comprehensive method for accurate 3D instance segmentation of cells in the brain tissue. The proposed method combines the 2D YOLO detection method with a multi-view fusion algorithm to construct a 3D localization of the cells. Next, the 3D bounding boxes along with the data volume are input to a 3D U-Net network that is designed to segment the primary cell in each 3D bounding box, and in turn, to carry out instance segmentation of cells in the entire volume. The promising performance of the proposed method is shown in comparison with some current deep learning-based 3D instance segmentation methods.

eess.IV↗

arXiv2021

Model-based Reconstruction for Enhanced X-ray CT of Tri-structural Isotropic (TRISO) Particles

Tri-Structural Isotropic (TRISO) fuel particles are a key component of next generation nuclear fuels. Using X-ray computed tomography (CT) to characterize TRISO particles is challenging because of the strong attenuation of the X-ray beam by the uranium core leading to severe photon starvation in a substantial fraction of the measurements. Furthermore, the overall acquisition time for a high-resolution CT scan can be very long when using conventional lab-based X-ray systems and reconstruction algorithms. Specifically, when analytic methods like the Feldkamp-Davis-Kress (FDK) algorithm is used for reconstruction, it results in severe streaks artifacts and noise in the corresponding 3D volume which make subsequent analysis of the particles challenging. In this article, we develop and apply model-based image reconstruction (MBIR) algorithms for improving the quality of CT reconstructions for TRISO particles in order to facilitate better characterization. We demonstrate that the proposed MBIR algorithms can significantly suppress artifacts with minimal pre-processing compared to the conventional approaches. Furthermore, we demonstrate the proposed MBIR approach can obtain high-quality reconstruction compared to the FDK approach even when using a fraction of the typically acquired measurements, thereby enabling dramatically faster measurement times for TRISO particles.

eess.IV↗

arXiv2019

PABO: Pseudo Agent-Based Multi-Objective Bayesian Hyperparameter Optimization for Efficient Neural Accelerator Design

The ever increasing computational cost of Deep Neural Networks (DNN) and the demand for energy efficient hardware for DNN acceleration has made accuracy and hardware cost co-optimization for DNNs tremendously important, especially for edge devices. Owing to the large parameter space and cost of evaluating each parameter in the search space, manually tuning of DNN hyperparameters is impractical. Automatic joint DNN and hardware hyperparameter optimization is indispensable for such problems. Bayesian optimization-based approaches have shown promising results for hyperparameter optimization of DNNs. However, most of these techniques have been developed without considering the underlying hardware, thereby leading to inefficient designs. Further, the few works that perform joint optimization are not generalizable and mainly focus on CMOS-based architectures. In this work, we present a novel pseudo agent-based multi-objective hyperparameter optimization (PABO) for maximizing the DNN performance while obtaining low hardware cost. Compared to the existing methods, our work poses a theoretically different approach for joint optimization of accuracy and hardware cost and focuses on memristive crossbar-based accelerators. PABO uses a supervisor agent to establish connections between the posterior Gaussian distribution models of network accuracy and hardware cost requirements. The agent reduces the mathematical complexity of the co-optimization problem by removing unnecessary computations and updates of acquisition functions, thereby achieving significant speed-ups for the optimization procedure. PABO outputs a Pareto frontier that underscores the trade-offs between designing high-accuracy and hardware efficiency. Our results demonstrate a superior performance compared to the state-of-the-art methods both in terms of accuracy and computational speed (~100x speed up).

cs.LG↗

arXiv2019

X-Ray CT Reconstruction of Additively Manufactured Parts using 2.5D Deep Learning MBIR

In this paper, we present a deep learning algorithm to rapidly obtain high quality CT reconstructions for AM parts. In particular, we propose to use CAD models of the parts that are to be manufactured, introduce typical defects and simulate XCT measurements. These simulated measurements were processed using FBP (computationally simple but result in noisy images) and the MBIR technique. We then train a 2.5D deep convolutional neural network [4], deemed 2.5D Deep Learning MBIR (2.5D DL-MBIR), on these pairs of noisy and high-quality 3D volumes to learn a fast, non-linear mapping function. The 2.5D DL-MBIR reconstructs a 3D volume in a 2.5D scheme where each slice is reconstructed from multiple inputs slices of the FBP input. Given this trained system, we can take a small set of measurements on an actual part, process it using a combination of FBP followed by 2.5D DL-MBIR. Both steps can be rapidly performed using GPUs, resulting in a real-time algorithm that achieves the high-quality of MBIR as fast as standard techniques. Intuitively, since CAD models are typically available for parts to be manufactured, this provides a strong constraint "prior" which can be leveraged to improve the reconstruction.

cs.CV↗

arXiv2018

Model Based Iterative Reconstruction With Spatially Adaptive Sinogram Weights for Wide-Cone Cardiac CT

With the recent introduction of CT scanners with large cone angles, wide coverage detectors now provide a desirable scanning platform for cardiac CT that allows whole heart imaging in a single rotation. On these scanners, while half-scan data is strictly sufficient to produce images with the best temporal resolution, acquiring a full 360 degree rotation worth of data is beneficial for wide-cone image reconstruction at negligible additional radiation dose. Applying Model-Based Iterative Reconstruction (MBIR) algorithm to the heart has shown to yield significant enhancement in image quality for cardiac CT. But imaging the heart in large cone angle geometry leads to apparently conflicting data usage considerations. On the one hand, in addition to using the fastest available scanner rotation speed, a minimal complete data set of 180 degrees plus the fan angle is typically used to minimize both cardiac and respiratory motion. On the other hand, a full 360 degree acquisition helps better handle the challenges of missing frequencies and incomplete projections associated with wide-cone half-scan data acquisition. In this paper, we develop a Spatially Adaptive sinogram Weights MBIR algorithm (SAW-MBIR) that is designed to achieve the benefits of both half and full-scan reconstructions in order to maximize temporal resolution over the heart region while providing stable results over the whole volume covered with the wide-area detector. Spatially-adaptive sinogram weights applied to each projection measurement in SAW-MBIR are designed to selectively perform backprojection from the full and half-scan portion of the sinogram based on both projection angle and reconstructed voxel location. We demonstrate with experimental results of SAW-MBIR applied to whole-heart cardiac CT clinical data that overall temporal resolution matches half-scan while full volume image quality is on par with full-scan MBIR.

eess.IV↗

arXiv2018

2.5D Deep Learning for CT Image Reconstruction using a Multi-GPU implementation

While Model Based Iterative Reconstruction (MBIR) of CT scans has been shown to have better image quality than Filtered Back Projection (FBP), its use has been limited by its high computational cost. More recently, deep convolutional neural networks (CNN) have shown great promise in both denoising and reconstruction applications. In this research, we propose a fast reconstruction algorithm, which we call Deep Learning MBIR (DL-MBIR), for approximating MBIR using a deep residual neural network. The DL-MBIR method is trained to produce reconstructions that approximate true MBIR images using a 16 layer residual convolutional neural network implemented on multiple GPUs using Google Tensorflow. In addition, we propose 2D, 2.5D and 3D variations on the DL-MBIR method and show that the 2.5D method achieves similar quality to the fully 3D method, but with reduced computational cost.

eess.IV↗