arXiv subjects

Adam S. Wang

Publications and source records attributed to Adam S. Wang.

12 recordsLinked to original sources

arXiv2026

ENCORE: Efficient Noise Context-Aware Representation for Low-Dose CT Denoising

While deep learning-based denoising has become widely adopted in low-dose CT, conventional models use generic architectures designed for natural images, failing to account for non-stationary and spatially correlated CT noise characteristics. To address this, we propose an Efficient Noise COntext-aware REpresentation (ENCORE) framework that explicitly leverages CT noise characteristics and anatomical features. First, we reformulate the noise synthesis procedure based on a realistic noise distribution beyond the conventional Gaussian approximation, establishing a rigorous foundation for training pair generation. Next, we extract local noise power and correlation contexts to guide the denoising process. To fully leverage the potential of noise context, we propose a FlyingConv module, which adaptively changes convolution weights for each local image region. Notably, our approach demonstrates substantial gains in both denoising quality and computational efficiency. Furthermore, manipulating the intensity of the noise context maps at inference time enables zero-shot conditional denoising, allowing for dynamic control over the output image texture. The entire pipeline is available at https://github.com/minwoo-yu/ENCORE.git

cs.CV↗

arXiv2026

Evaluation of Silicon-Based Photon-Counting CT for Coronary Stenosis Quantification with Realistic Coronary Artery Phantoms

Objective: To quantify the impact of high-resolution deep silicon photon-counting CT (dSi-PCCT) on coronary stenosis quantification in anatomically realistic calcified coronary artery phantoms using Micro-CT as ground truth. Methods: Twelve vessel sections representing four calcification geometries (Type I-IV) and three luminal iodine concentrations (10, 15, and 20 mg/mL) were scanned under static conditions using energy-integrating detector CT (EID-CT), dSi-PCCT, and Micro-CT. Images were registered to Micro-CT and segmented using an automated threshold-based pipeline. The primary analysis compared longitudinal profiles of Micro-CT-referenced percent area stenosis and segmented vessel area. A secondary analysis evaluated ellipse-derived percent area stenosis and percent vessel-area deviation at the maximum-calcification cross-section. Results: dSi-PCCT reduced whole-profile mean absolute error in Micro-CT-referenced percent area stenosis from 3.10% with EID-CT to 1.62% (p=0.027) and reduced segmented vessel-area error from 0.55 to 0.31 mm2 (p=0.001). In the secondary analysis, absolute deviations in ellipse-derived percent area stenosis ranged from 0.1% to 6.5% for dSi-PCCT and from 0.8% to 24.2% for EID-CT (p<0.001). Mean absolute differences in percent vessel-area deviation from Micro-CT were also lower with dSi-PCCT than with EID-CT (15.0% vs 26.6%, p<0.001). Conclusion: Under static, resolution-optimized conditions, dSi-PCCT improved task-based coronary stenosis quantification and vessel delineation relative to EID-CT, supporting further evaluation in dynamic phantoms and clinical CCTA.

physics.med-ph↗

arXiv2026

Liver Metastasis Detection at Reduced Radiation Dose: Diagnostic Evaluation of a Novel Organ-Level Tube Current Modulation Method

Objective: To evaluate retroOpt, a novel organ-level tube current modulation (TCM) method that minimizes effective radiation dose while preserving diagnostic image quality for liver metastasis detection. Methods: In this retrospective, IRB-approved study, 22 patients with 68 liver lesions (38 malignant, 30 benign) underwent portal venous phase contrast-enhanced chest-abdomen-pelvis CT. Using projection-domain noise emulation, five series were generated per patient: original full dose (Orig-100), uniform dose reduction to 40% (UD-40) and 60% (UD-60) of the original effective dose, and organ-level TCM at the same levels (Opt-40, Opt-60). Three abdominal radiologists independently detected and classified lesions and rated image quality (5-point Likert). Per-lesion sensitivity was compared by McNemar test. Malignant lesion-size thresholds for 50% and 90% sensitivity (x50, x90) were estimated by logistic regression. Image quality was compared by Wilcoxon signed-rank test. Results: At the 60% level, Opt-60 achieved mean malignant lesion sensitivity comparable to full-dose CT (82% vs 80%) and exceeded uniform reduction (67%). At the 40% level, Opt-40 improved mean sensitivity over UD-40 from 52% to 68%. Mean all-lesion sensitivity rose from 54% (UD-40) to 64% (Opt-40) and from 65% (UD-60) to 77% (Opt-60), remaining comparable to full dose (76%). All optimized-versus-uniform differences were significant (p <= 0.003). Opt-60 lesion-size thresholds closely matched Orig-100 (x50 3.3 vs 3.7 mm; x90 15.7 vs 16.8 mm). Median Opt-60 image quality ranged from 3 to 4.5 across readers. Conclusions: Organ-level TCM preserved liver metastasis detection at 60% of the original effective dose, outperforming uniform dose reduction. Task-specific organ-level dose optimization may enable greater CT dose reduction than uniform strategies for patients requiring repeated metastasis surveillance.

physics.med-ph↗

arXiv2026

Characterizing the Radiation Dose to Measurement Accuracy Relationship across Multiple Metrics in Opportunistic Chest CT

Objectives: This study aims to characterize the dose-performance relationship for opportunistic CT and disentangle the contributions of segmentation failure and dose-dependent HU bias to performance degradation. Methods: Simulated low-dose CT images at 1-75% of full dose were generated from 50 paired full- and low-dose chest CT scans. An independent dataset of 22 paired PCCT acquisitions at lung cancer screening (LCS) and chest x-ray-equivalent (CXR) dose levels provided parallel real-world evaluation. Multiple quantitative disease metrics were obtained using deep learning-based segmentation followed by quantitative metric extraction. Classification performance was evaluated against full-dose reference standards, with additional analyses isolating the contributions of segmentation error and HU bias. Agreement between dose levels was assessed using Bland-Altman and correlation analyses. Results: Mean HU metrics maintained classification accuracy to CXR-equivalent dose (3%); bias correction improved accuracy from 88% to 96% for hepatic steatosis and from 84% to 90% for sarcopenia. Trabecular bone attenuation maintained 98% accuracy at LCS dose. Volume metrics (cardiomegaly) achieved 94% accuracy at CXR-equivalent dose. Threshold-based metrics required LCS dose for reliable classification; bias correction improved accuracy from 58% to 92%. Coronary artery calcification scoring reached 96% accuracy at LCS dose. In both Mayo and PCCT datasets, agreement analyses demonstrated strong correlation for all metrics except coronary artery calcification. Conclusions: Opportunistic CT is feasible at reduced dose levels though it becomes less robust at ultra-low doses. Distinct failure modes are caused by HU bias or segmentation failure and depend on the clinical task. Providers should be aware of these task-specific limitations when designing opportunistic screening programs.

physics.med-ph↗

arXiv2026

End-to-End Differentiable Photon Counting CT

Quantitative imaging is an important feature of spectral X-ray and CT systems, especially photon-counting CT (PCCT) imaging systems, which is achieved through material decomposition (MD) using spectral measurements. In this work, we present a novel framework that makes the PCCT imaging chain end-to-end differentiable (differentiable PCCT), with which we can leverage quantitative information in the image domain to enable cross-domain learning and optimization for upstream models. Specifically, the material decomposition from maximum-likelihood estimation (MLE) was made differentiable based on the Implicit Function Theorem and inserted as a layer into the imaging chain for end-to-end optimization. This framework allows for an automatic and adaptive solution of a wide range of imaging tasks, ultimately achieving quantitative imaging through computation rather than manual intervention. The end-to-end training mechanism effectively avoids the need for direct-domain training or supervision from intermediate references as models are trained using quantitative images. We demonstrate its applicability in two representative tasks: correcting detector energy bin drift and training an object scatter correction network using cross-domain reference from quantitative material images.

physics.med-ph↗

arXiv2025

Scout-Dose-TCM: Direct and Prospective Scout-Based Estimation of Personalized Organ Doses from Tube Current Modulated CT Exams

This study proposes Scout-Dose-TCM for direct, prospective estimation of organ-level doses under tube current modulation (TCM) and compares its performance to two established methods. We analyzed contrast-enhanced chest-abdomen-pelvis CT scans from 130 adults (120 kVp, TCM). Reference doses for six organs (lungs, kidneys, liver, pancreas, bladder, spleen) were calculated using MC-GPU and TotalSegmentator. Based on these, we trained Scout-Dose-TCM, a deep learning model that predicts organ doses corresponding to discrete cosine transform (DCT) basis functions, enabling real-time estimates for any TCM profile. The model combines a feature learning module that extracts contextual information from lateral and frontal scouts and scan range with a dose learning module that output DCT-based dose estimates. A customized loss function incorporated the DCT formulation during training. For comparison, we implemented size-specific dose estimation per AAPM TG 204 (Global CTDIvol) and its organ-level TCM-adapted version (Organ CTDIvol). A 5-fold cross-validation assessed generalizability by comparing mean absolute percentage dose errors and r-squared correlations with benchmark doses. Average absolute percentage errors were 13% (Global CTDIvol), 9% (Organ CTDIvol), and 7% (Scout-Dose-TCM), with bladder showing the largest discrepancies (15%, 13%, and 9%). Statistical tests confirmed Scout-Dose-TCM significantly reduced errors vs. Global CTDIvol across most organs and improved over Organ CTDIvol for the liver, bladder, and pancreas. It also achieved higher r-squared values, indicating stronger agreement with Monte Carlo benchmarks. Scout-Dose-TCM outperformed Global CTDIvol and was comparable to or better than Organ CTDIvol, without requiring organ segmentations at inference, demonstrating its promise as a tool for prospective organ-level dose estimation in CT.

physics.med-ph↗

arXiv2024

Unsupervised Training of a Dynamic Context-Aware Deep Denoising Framework for Low-Dose Fluoroscopic Imaging

Fluoroscopy is critical for real-time X-ray visualization in medical imaging. However, low-dose images are compromised by noise, potentially affecting diagnostic accuracy. Noise reduction is crucial for maintaining image quality, especially given such challenges as motion artifacts and the limited availability of clean data in medical imaging. To address these issues, we propose an unsupervised training framework for dynamic context-aware denoising of fluoroscopy image sequences. First, we train the multi-scale recurrent attention U-Net (MSR2AU-Net) without requiring clean data to address the initial noise. Second, we incorporate a knowledge distillation-based uncorrelated noise suppression module and a recursive filtering-based correlated noise suppression module enhanced with motion compensation to further improve motion compensation and achieve superior denoising performance. Finally, we introduce a novel approach by combining these modules with a pixel-wise dynamic object motion cross-fusion matrix, designed to adapt to motion, and an edge-preserving loss for precise detail retention. To validate the proposed method, we conducted extensive numerical experiments on medical image datasets, including 3500 fluoroscopy images from dynamic phantoms (2,400 images for training, 1,100 for testing) and 350 clinical images from a spinal surgery patient. Moreover, we demonstrated the robustness of our approach across different imaging modalities by testing it on the publicly available 2016 Low Dose CT Grand Challenge dataset, using 4,800 images for training and 1,136 for testing. The results demonstrate that the proposed approach outperforms state-of-the-art unsupervised algorithms in both visual quality and quantitative evaluation while achieving comparable performance to well-established supervised learning methods across low-dose fluoroscopy and CT imaging.

eess.IV↗

arXiv2024

OpenDosimeter: Open Hardware Personal X-ray Dosimeter

We present OpenDosimeter (www.opendosimeter.org), an open hardware solution for real-time personal X-ray dose monitoring based on a scintillation counter. Using an X-ray sensor assembly (LYSO + SiPM) on a custom board powered by a Raspberry Pi Pico, OpenDosimeter provides real-time feedback (1 Hz), data logging (10 hours), and battery-powered operation. One of the core innovations is that we calibrate the device using $^{241}$Am found in ionization smoke detectors. Specifically, we use the $\gamma$-emissions to spectrally calibrate the dosimeter, then calculate the effective dose from X-ray exposure by compensating for the scintillator absorption efficiency and applying energy-to-dose coefficients derived from tabulated data in the ICRP 116 publication. We demonstrate that this transparent approach enables real-time dose rate readings with a linear response between 0.1-1000 $\mu$Sv/h at $\pm$25% accuracy, tested for energies up to 120 keV. The maximum dose rate readings are limited by pile-up effects when approaching count rate saturation ($\sim$77 kcps at $\sim$13 $\mu$s average pulse processing time). The total component cost for making an OpenDosimeter is <\$100, which, combined with its open design (both hardware and software), enables cost-effective local reproducibility on a global scale. Through a student workshop, we also demonstrate its effectiveness as an educational and capacity-building tool. This paper complements the open-source documentation by explaining the underlying technology, the algorithm for dose calculation, and areas for future improvement.

physics.ins-det↗

arXiv2022

Multi-Energy Blended CBCT Spectral Imaging Using a Spectral Modulator with Flying Focal Spot (SMFFS)

Conventional cone-beam CT (CBCT) can be easily compromised by scatter and beam hardening artifacts, and the entanglement of scatter and spectral effects introduces additional complexity. In this work, we present the first attempt to develop a stationary spectral modulator with flying focal spot (SMFFS) technology as a promising, low-cost approach to accurately solving the X-ray scattering problem and physically enabling spectral imaging in a unified framework. To deal with the intertwined scatter-spectral challenge, we propose a novel scatter-decoupled material decomposition (SDMD) method for SMFFS based on a hypothesis of scatter similarity. Monte Carlo simulations of a pure-water cylinder phantom with different focal spot deflections show that focal spot deflections within a range of ~2 mm share quite similar scatter distributions overall. Numerical simulations using a clinical abdominal CT dataset demonstrate that SMFFS with SDMD method can achieve better material decomposition and CT number accuracy with less artifacts. Physics experiments on a tabletop CBCT system using a Gammex multi-energy CT phantom an anthropomorphic chest phantom, are carried out to demonstrate the feasibility of CBCT spectral imaging with SMFFS. For the chest phantom, the root mean square error (RMSE) in selected regions of interest (ROIs) of virtual monochromatic image (VMI) at 70 keV is 11.8 HU for SMFFS CB scan, and 14.5 and 437.6 HU for sequential 80/140 kVp (DKV) CB scan with and without scatter correction, respectively. Also, the non-uniformity among selected regions is 14.1 HU for SMFFS CB scan, and 59.4 and 184.0 HU for the DKV CB scan with and without a traditional scatter correction method, respectively. Our preliminary results show that SMFFS can enable spectral imaging with simultaneous scatter correction for CBCT and effectively improve its quantitative imaging performance.

physics.med-ph↗

arXiv2020

An Analysis of Scatter Characteristics in X-ray CT Spectral Correction

X-ray scatter remains a major physics challenge in volumetric computed tomography (CT), whose physical and statistical behaviors have been commonly leveraged in order to eliminate its impact on CT image quality. In this work, we conduct an in-depth derivation of how the scatter distribution and scatter to primary ratio (SPR) will change during the spectral correction, leading to an interesting finding on the property of scatter: when applying the spectral correction before scatter is removed, the impact of SPR on a CT projection will be scaled by the first derivative of the mapping function; while the scatter distribution in the transmission domain will be scaled by the product of the first derivative of the mapping function and a natural exponential of the projection difference before and after the mapping. Such a characterization of scatter's behavior provides an analytic approach of compensating for the SPR as well as approximating the change of scatter distribution after spectral correction, even though both of them might be significantly distorted as the linearization mapping function in spectral correction could vary a lot from one detector pixel to another. We conduct an evaluation of SPR compensations on a Catphan phantom and an anthropomorphic chest phantom to validate the characteristics of scatter. In addition, this scatter property is also directly adopted into CT imaging using a spectral modulator with flying focal spot technology (SMFFS) as an example to demonstrate its potential in practical applications.

physics.med-ph↗

arXiv2020

Deep Learning-Based Reconstruction of Interventional Tools from Four X-Ray Projections for Tomographic Interventional Guidance

Image guidance for minimally invasive interventions is usually performed by acquiring fluoroscopic images using a C-arm system. However, the projective data provide only limited information about the spatial structure and position of interventional tools such as stents, guide wires or coils. In this work we propose a deep learning-based pipeline for real-time tomographic (four-dimensional) interventional guidance at acceptable dose levels. In the first step, interventional tools are extracted from four cone-beam CT projections using a deep convolutional neural network (CNN). These projections are then reconstructed and fed into a second CNN, which maps this highly undersampled reconstruction to a segmentation of the interventional tools. Our pipeline is capable of reconstructing interventional tools from only four x-ray projections without the need for a patient prior with very high accuracy. Therefore, the proposed approach is capable of overcoming the drawbacks of today's interventional guidance and could enable the development of new minimally invasive radiological interventions by providing full spatiotemporal information about the interventional tools.

physics.med-ph↗

arXiv2020

Assessing Robustness to Noise: Low-Cost Head CT Triage

Automated medical image classification with convolutional neural networks (CNNs) has great potential to impact healthcare, particularly in resource-constrained healthcare systems where fewer trained radiologists are available. However, little is known about how well a trained CNN can perform on images with the increased noise levels, different acquisition protocols, or additional artifacts that may arise when using low-cost scanners, which can be underrepresented in datasets collected from well-funded hospitals. In this work, we investigate how a model trained to triage head computed tomography (CT) scans performs on images acquired with reduced x-ray tube current, fewer projections per gantry rotation, and limited angle scans. These changes can reduce the cost of the scanner and demands on electrical power but come at the expense of increased image noise and artifacts. We first develop a model to triage head CTs and report an area under the receiver operating characteristic curve (AUROC) of 0.77. We then show that the trained model is robust to reduced tube current and fewer projections, with the AUROC dropping only 0.65% for images acquired with a 16x reduction in tube current and 0.22% for images acquired with 8x fewer projections. Finally, for significantly degraded images acquired by a limited angle scan, we show that a model trained specifically to classify such images can overcome the technological limitations to reconstruction and maintain an AUROC within 0.09% of the original model.

eess.IV↗