arXiv subjects

Ashkan Pakzad

Publications and source records attributed to Ashkan Pakzad.

9 recordsLinked to original sources

arXiv2026

Fast Patient-Specific Breast CT Dosimetry: 22-Fold Acceleration of Monte Carlo MGD Estimation

Accurate patient-specific mean glandular dose (MGD) estimation in breast computed tomography (BCT) requires anatomically realistic models, but high-resolution patient-derived phantoms impose high computational demands on Monte Carlo (MC) dosimetry. We previously developed and validated an EGSnrc-based framework for synchrotron propagation-based phase-contrast BCT (PB-PCT) for the first-in-human study at the Australian Synchrotron. With participant imaging commencing, this study aimed to optimize phantom spatial resolution and MC efficiency while maintaining MGD accuracy, for a rapid patient-specific dosimetry. Four patient-specific heterogeneous breast phantoms with varying volume and glandularity were generated from PB-PCT images of mastectomy specimens acquired at 35 keV. The highest-resolution phantom for each specimen served as the reference. Phantoms were downsampled by increasing in-plane voxel size and slice thickness, and MGD was recalculated using EGSnrc/DOSXYZnrc. A 4.5% difference from reference MGD was adopted as the accuracy criterion. Primary photon histories were then reduced to determine the minimum required for acceptable MC precision. A common voxel size of 0.30 x 0.30 x 3.00 mm3 maintained MGD within 4.5% of reference for all four phantoms while reducing voxel number by approximately 20-31-fold. MGD was more sensitive to in-plane voxel size than slice thickness, supporting anisotropic downsampling. Reduced-resolution phantoms enabled a 15-fold reduction in photon histories to 2 x 10^8 while maintaining acceptable statistical uncertainty. Combined optimization reduced computation time from approximately 1600 to 72 min, a 22-fold acceleration. Patient-specific phantoms can be substantially downsampled while maintaining MGD accuracy and markedly reducing computational burden. This optimization provides a foundation for future real-time patient-specific BCT dosimetry.

physics.med-ph↗

arXiv2026

Development and Validation of Patient-Specific Monte Carlo Dosimetry for Synchrotron Breast Phase-Contrast CT

This study develops and validates a patient-specific Monte Carlo (MC) dosimetry framework for propagation-based phase-contrast breast CT (BCT) at the Imaging and Medical Beamline (IMBL), ANSTO Australian Synchrotron, for accurate mean glandular dose (MGD) estimation. BCT provides 3D imaging without breast compression, improving comfort and visualization of internal structures for cancer detection. Propagation-based phase contrast improves soft-tissue contrast at equal or lower dose than conventional systems. Accurate dosimetry remains essential for safety and optimisation. Most MC-based MGD studies use non-patient-specific phantoms that ignore anatomical variability, while existing patient-specific methods lack a unified framework. Here, a voxel-based MC framework using EGSnrc was implemented to compute MGD in realistic anthropomorphic breast phantoms derived from synchrotron BCT images. IMBL beam characteristics were used as source inputs. Homogeneous phantoms were also generated to compute air Kerma to MGD conversion coefficients (DgN) for comparison with heterogeneous models. Simulations covered breast height, skin thickness, and photon energies (28 to 38 keV). Results show MGD depends strongly on anatomy and energy. Higher glandular density reduces MGD, while larger breast volume increases dose. A 2 mm increase in skin thickness reduces MGD by 10%. Differences between heterogeneous and homogeneous phantoms show variations in DgN, highlighting the need for anatomical realism. The framework provides a robust basis for patient-specific dosimetry in synchrotron phase-contrast BCT, enabling precise MGD estimation and supporting safe, optimised clinical imaging. This supports improved protocol design and contributes to standardised patient-specific dosimetry for clinical translation across varying breast anatomies and imaging conditions within synchrotron BCT applications.

physics.med-ph↗

arXiv2026

On optimization of Paganin's method for propagation-based X-ray phase-contrast imaging and tomography

Paganin's method for image reconstruction in propagation-based phase-contrast X-ray imaging and tomography has enjoyed broad acceptance in recent years, with over one thousand publications citing its use. The present paper discusses approaches to optimization of the method with respect to simple image quality metrics, such as signal-to-noise ratio and spatial resolution, as well as a reference-based metric corresponding to the relative mean squared difference between the reconstructed image and the "ground truth" image that would be obtained in a setup with perfect spatial resolution and no noise. The problem of optimization of the intrinsic regularization parameter of Paganin's method with respect to spatial resolution in the reconstructed image is studied in detail. It is also demonstrated that a combination of Paganin's method with a Tikhonov-regularized deconvolution of the point-spread function of the imaging system can provide significantly higher image quality compared to the standard version of the method. Analytical expressions for some relevant image quality metrics are obtained and compared with results of numerical simulations. Advantages and shortcomings of optimization approaches using a number of different image quality metrics are discussed. The results of this study are expected to be useful in practical X-ray imaging and training of deep machine learning models for image denoising and segmentation.

physics.med-ph↗

arXiv2025

Towards order of magnitude X-ray dose reduction in breast cancer imaging using phase contrast and deep denoising

Breast cancer is the most frequently diagnosed human cancer in the United States at present. Early detection is crucial for its successful treatment. X-ray mammography and digital breast tomosynthesis are currently the main methods for breast cancer screening. However, both have known limitations in terms of their sensitivity and specificity to breast cancers, while also frequently causing patient discomfort due to the requirement for breast compression. Breast computed tomography is a promising alternative, however, to obtain high-quality images, the X-ray dose needs to be sufficiently high. As the breast is highly radiosensitive, dose reduction is particularly important. Phase-contrast computed tomography (PCT) has been shown to produce higher-quality images at lower doses and has no need for breast compression. It is demonstrated in the present study that, when imaging full fresh mastectomy samples with PCT, deep learning-based image denoising can further reduce the radiation dose by a factor of 16 or more, without any loss of image quality. The image quality has been assessed both in terms of objective metrics, such as spatial resolution and contrast-to-noise ratio, as well as in an observer study by experienced medical imaging specialists and radiologists. This work was carried out in preparation for live patient PCT breast cancer imaging, initially at specialized synchrotron facilities.

physics.med-ph↗

arXiv2024

Efficient automatic segmentation for multi-level pulmonary arteries: The PARSE challenge

Efficient automatic segmentation of multi-level (i.e. main and branch) pulmonary arteries (PA) in CTPA images plays a significant role in clinical applications. However, most existing methods concentrate only on main PA or branch PA segmentation separately and ignore segmentation efficiency. Besides, there is no public large-scale dataset focused on PA segmentation, which makes it highly challenging to compare the different methods. To benchmark multi-level PA segmentation algorithms, we organized the first \textbf{P}ulmonary \textbf{AR}tery \textbf{SE}gmentation (PARSE) challenge. On the one hand, we focus on both the main PA and the branch PA segmentation. On the other hand, for better clinical application, we assign the same score weight to segmentation efficiency (mainly running time and GPU memory consumption during inference) while ensuring PA segmentation accuracy. We present a summary of the top algorithms and offer some suggestions for efficient and accurate multi-level PA automatic segmentation. We provide the PARSE challenge as open-access for the community to benchmark future algorithm developments at \url{https://parse2022.grand-challenge.org/Parse2022/}.

eess.IV↗

arXiv2024

Interpolation-Split: a data-centric deep learning approach with big interpolated data to boost airway segmentation performance

The morphology and distribution of airway tree abnormalities enables diagnosis and disease characterisation across a variety of chronic respiratory conditions. In this regard, airway segmentation plays a critical role in the production of the outline of the entire airway tree to enable estimation of disease extent and severity. In this study, we propose a data-centric deep learning technique to segment the airway tree. The proposed technique utilises interpolation and image split to improve data usefulness and quality. Then, an ensemble learning strategy is implemented to aggregate the segmented airway trees at different scales. In terms of segmentation performance (dice similarity coefficient), our method outperforms the baseline model by 2.5% on average when a combined loss is used. Further, our proposed technique has a low GPU usage and high flexibility enabling it to be deployed on any 2D deep learning model.

eess.IV↗

arXiv2023

Multi-site, Multi-domain Airway Tree Modeling (ATM'22): A Public Benchmark for Pulmonary Airway Segmentation

Open international challenges are becoming the de facto standard for assessing computer vision and image analysis algorithms. In recent years, new methods have extended the reach of pulmonary airway segmentation that is closer to the limit of image resolution. Since EXACT'09 pulmonary airway segmentation, limited effort has been directed to quantitative comparison of newly emerged algorithms driven by the maturity of deep learning based approaches and clinical drive for resolving finer details of distal airways for early intervention of pulmonary diseases. Thus far, public annotated datasets are extremely limited, hindering the development of data-driven methods and detailed performance evaluation of new algorithms. To provide a benchmark for the medical imaging community, we organized the Multi-site, Multi-domain Airway Tree Modeling (ATM'22), which was held as an official challenge event during the MICCAI 2022 conference. ATM'22 provides large-scale CT scans with detailed pulmonary airway annotation, including 500 CT scans (300 for training, 50 for validation, and 150 for testing). The dataset was collected from different sites and it further included a portion of noisy COVID-19 CTs with ground-glass opacity and consolidation. Twenty-three teams participated in the entire phase of the challenge and the algorithms for the top ten teams are reviewed in this paper. Quantitative and qualitative results revealed that deep learning models embedded with the topological continuity enhancement achieved superior performance in general. ATM'22 challenge holds as an open-call design, the training data and the gold standard evaluation are available upon successful registration via its homepage.

eess.IV↗

arXiv2022

Airway measurement by refinement of synthetic images improves mortality prediction in idiopathic pulmonary fibrosis

Several chronic lung diseases, like idiopathic pulmonary fibrosis (IPF) are characterised by abnormal dilatation of the airways. Quantification of airway features on computed tomography (CT) can help characterise disease progression. Physics based airway measurement algorithms have been developed, but have met with limited success in part due to the sheer diversity of airway morphology seen in clinical practice. Supervised learning methods are also not feasible due to the high cost of obtaining precise airway annotations. We propose synthesising airways by style transfer using perceptual losses to train our model, Airway Transfer Network (ATN). We compare our ATN model with a state-of-the-art GAN-based network (simGAN) using a) qualitative assessment; b) assessment of the ability of ATN and simGAN based CT airway metrics to predict mortality in a population of 113 patients with IPF. ATN was shown to be quicker and easier to train than simGAN. ATN-based airway measurements were also found to be consistently stronger predictors of mortality than simGAN-derived airway metrics on IPF CTs. Airway synthesis by a transformation network that refines synthetic data using perceptual losses is a realistic alternative to GAN-based methods for clinical CT analyses of idiopathic pulmonary fibrosis. Our source code can be found at https://github.com/ashkanpakzad/ATN that is compatible with the existing open-source airway analysis framework, AirQuant.

eess.IV↗

arXiv2021

Evaluation of automated airway morphological quantification for assessing fibrosing lung disease

Abnormal airway dilatation, termed traction bronchiectasis, is a typical feature of idiopathic pulmonary fibrosis (IPF). Volumetric computed tomography (CT) imaging captures the loss of normal airway tapering in IPF. We postulated that automated quantification of airway abnormalities could provide estimates of IPF disease extent and severity. We propose AirQuant, an automated computational pipeline that systematically parcellates the airway tree into its lobes and generational branches from a deep learning based airway segmentation, deriving airway structural measures from chest CT. Importantly, AirQuant prevents the occurrence of spurious airway branches by thick wave propagation and removes loops in the airway-tree by graph search, overcoming limitations of existing airway skeletonisation algorithms. Tapering between airway segments (intertapering) and airway tortuosity computed by AirQuant were compared between 14 healthy participants and 14 IPF patients. Airway intertapering was significantly reduced in IPF patients, and airway tortuosity was significantly increased when compared to healthy controls. Differences were most marked in the lower lobes, conforming to the typical distribution of IPF-related damage. AirQuant is an open-source pipeline that avoids limitations of existing airway quantification algorithms and has clinical interpretability. Automated airway measurements may have potential as novel imaging biomarkers of IPF severity and disease extent.

physics.med-ph↗