arXiv subjects

Richard Qiu

Publications and source records attributed to Richard Qiu.

13 recordsLinked to original sources

arXiv2025

An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generation

Objective: Gadolinium-based contrast agents (GBCAs) are commonly employed with T1w MRI to enhance lesion visualization but are restricted in patients at risk of nephrogenic systemic fibrosis and variations in GBCA administration can introduce imaging inconsistencies. This study develops an efficient 3D deep-learning framework to generate T1-contrast enhanced images (T1C) from pre-contrast multiparametric MRI. Approach: We propose the 3D latent rectified flow (T1C-RFlow) model for generating high-quality T1C images. First, T1w and T2-FLAIR images are input into a pretrained autoencoder to acquire an efficient latent space representation. A rectified flow diffusion model is then trained in this latent space representation. The T1C-RFlow model was trained on a curated dataset comprised of the BraTS 2024 glioma (GLI; 1480 patients), meningioma (MEN; 1141 patients), and metastases (MET; 1475 patients) datasets. Selected patients were split into train (N=2860), validation (N=612), and test (N=614) sets. Results: Both qualitative and quantitative results demonstrate that the T1C-RFlow model outperforms benchmark 3D models (pix2pix, DDPM, Diffusion Transformers (DiT-3D)) trained in the same latent space. T1C-RFlow achieved the following metrics - GLI: NMSE 0.044 +/- 0.047, SSIM 0.935 +/- 0.025; MEN: NMSE 0.046 +/- 0.029, SSIM 0.937 +/- 0.021; MET: NMSE 0.098 +/- 0.088, SSIM 0.905 +/- 0.082. T1C-RFlow had the best tumor reconstruction performance and significantly faster denoising times (6.9 s/volume, 200 steps) than conventional DDPM models in both latent space (37.7s, 1000 steps) and patch-based in image space (4.3 hr/volume). Significance: Our proposed method generates synthetic T1C images that closely resemble ground truth T1C in much less time than previous diffusion models. Further development may permit a practical method for contrast-agent-free MRI for brain tumors.

cs.CV↗

arXiv2025

Clinically Interpretable Survival Risk Stratification in Head and Neck Cancer Using Bayesian Networks and Markov Blankets

Purpose: To identify a clinically interpretable subset of survival-relevant features in HN cancer using Bayesian Network (BN) and evaluate its prognostic and causal utility. Methods and Materials: We used the RADCURE dataset, consisting of 3,346 patients with H&N cancer treated with definitive (chemo)radiotherapy. A probabilistic BN was constructed to model dependencies among clinical, anatomical, and treatment variables. The Markov Blanket (MB) of two-year survival (SVy2) was extracted and used to train a logistic regression model. After excluding incomplete cases, a temporal split yielded a train/test (2,174/820) dataset using 2007 as the cutoff year. Model performance was assessed using area under the ROC curve (AUC), C-index, and Kaplan-Meier (KM) survival stratification. Model fit was further evaluated using a log-likelihood ratio (LLR) test. Causal inference was performed using do-calculus interventions on MB variables. Results: The MB of SVy2 included 6 clinically relevant features: ECOG performance status, T-stage, HPV status, disease site, the primary gross tumor volume (GTVp), and treatment modality. The model achieved an AUC of 0.65 and C-index of 0.78 on the test dataset, significantly stratifying patients into high- and low-risk groups (log-rank p < 0.01). Model fit was further supported by a log-likelihood ratio of 70.32 (p < 0.01). Subgroup analyses revealed strong performance in HPV-negative (AUC = 0.69, C-index = 0.76), T4 (AUC = 0.69, C-index = 0.80), and large-GTV (AUC = 0.67, C-index = 0.75) cohorts, each showing significant KM separation. Causal analysis further supported the positive survival impact of ECOG 0, HPV-positive status, and chemoradiation. Conclusions: A compact, MB-derived BN model can robustly stratify survival risk in HN cancer. The model enables explainable prognostication and supports individualized decision-making across key clinical subgroups.

physics.med-ph↗

arXiv2025

A Physics-Informed Deep Learning Model for MRI Brain Motion Correction

Background: MRI is crucial for brain imaging but is highly susceptible to motion artifacts due to long acquisition times. This study introduces PI-MoCoNet, a physics-informed motion correction network that integrates spatial and k-space information to remove motion artifacts without explicit motion parameter estimation, enhancing image fidelity and diagnostic reliability. Materials and Methods: PI-MoCoNet consists of a motion detection network (U-net with spatial averaging) to identify corrupted k-space lines and a motion correction network (U-net with Swin Transformer blocks) to reconstruct motion-free images. The correction is guided by three loss functions: reconstruction (L1), perceptual (LPIPS), and data consistency (Ldc). Motion artifacts were simulated via rigid phase encoding perturbations and evaluated on IXI and MR-ART datasets against Pix2Pix, CycleGAN, and U-net using PSNR, SSIM, and NMSE. Results: PI-MoCoNet significantly improved image quality. On IXI, for minor artifacts, PSNR increased from 34.15 dB to 45.95 dB, SSIM from 0.87 to 1.00, and NMSE reduced from 0.55% to 0.04%. For moderate artifacts, PSNR improved from 30.23 dB to 42.16 dB, SSIM from 0.80 to 0.99, and NMSE from 1.32% to 0.09%. For heavy artifacts, PSNR rose from 27.99 dB to 36.01 dB, SSIM from 0.75 to 0.97, and NMSE decreased from 2.21% to 0.36%. On MR-ART, PI-MoCoNet achieved PSNR gains of ~10 dB and SSIM improvements of up to 0.20, with NMSE reductions of ~6%. Ablation studies confirmed the importance of data consistency and perceptual losses, yielding a 1 dB PSNR gain and 0.17% NMSE reduction. Conclusions: PI-MoCoNet effectively mitigates motion artifacts in brain MRI, outperforming existing methods. Its ability to integrate spatial and k-space information makes it a promising tool for clinical use in motion-prone settings. Code: https://github.com/mosaf/PI-MoCoNet.git.

cs.CV↗

arXiv2025

Stereotactic Arrhythmia Radioablation for Refractory Ventricular Tachycardia: A Narrative Review and Exploratory Pooled Analysis of Clinical Outcomes and Toxicity

Purpose: Stereotactic arrhythmia radioablation (STAR) is a non-invasive salvage therapy for refractory ventricular tachycardia (VT), especially in patients ineligible for catheter ablation. This narrative review and pooled analysis evaluates the safety, efficacy, and technical characteristics of STAR, integrating preclinical studies, case reports, case series, and clinical trials. Methods and Materials: A comprehensive review identified 86 studies published between 2015 and 2025, including 12 preclinical studies, 49 case reports, 18 case series, and 7 clinical trials. Study-level data were extracted for pooled analysis of 6- and 12-month mortality, VT burden reduction, and grade 3+ acute toxicities. Subgroup analyses were performed by delivery modality, age, left ventricular ejection fraction (LVEF), and cardiomyopathy type. Results: Pooled mortality was 16% (95% CI: 11-20%) at 6 months and 33% (95% CI: 27-38%) at 12 months. VT burden reduction at 6 months averaged 75% (95% CI: 73-77%) but showed substantial heterogeneity (I^2 = 98.8%). Grade 3+ acute toxicities occurred in 7% (95% CI: 4-10%), with heart failure being most common. Subgroup analyses suggested better outcomes in younger patients, those with NICM, and those with higher LVEF. Conclusions: STAR is a promising salvage therapy with favorable acute safety and efficacy. Outcome heterogeneity and inconsistent reporting highlight the need for standardized definitions, dosimetric protocols, and longer-term follow-up. Prospective trials and real-world registries are critical for refining STAR's role in VT management.

physics.med-ph↗

arXiv2024

Current Progress of Digital Twin Construction Using Medical Imaging

Medical imaging has played a pivotal role in advancing and refining digital twin technology, allowing for the development of highly personalized virtual models that represent human anatomy and physiological functions. A key component in constructing these digital twins is the integration of high-resolution imaging data, such as MRI, CT, PET, and ultrasound, with sophisticated computational models. Advances in medical imaging significantly enhance real-time simulation, predictive modeling, and early disease diagnosis, individualized treatment planning, ultimately boosting precision and personalized care. Although challenges persist, such as the complexity of anatomical modeling, integrating various imaging modalities, and high computational demands, recent progress in imaging and machine learning has greatly improved the precision and clinical applicability of digital twins. This review investigates the role of medical imaging in developing digital twins across organ systems. Key findings demonstrate that improvements in medical imaging have enhanced the diagnostic and therapeutic potential of digital twins beyond traditional methods, particularly in imaging accuracy, treatment effectiveness, and patient outcomes. The review also examines the technical barriers that currently limit further development of digital twin technology, despite advances in medical imaging, and outlines future research avenues aimed at overcoming these challenges to unlock the full potential of this technology in precision medicine.

physics.med-ph↗

arXiv2024

A Review of Artificial Intelligence in Brachytherapy

Artificial intelligence (AI) has the potential to revolutionize brachytherapy's clinical workflow. This review comprehensively examines the application of AI, focusing on machine learning and deep learning, in facilitating various aspects of brachytherapy. We analyze AI's role in making brachytherapy treatments more personalized, efficient, and effective. The applications are systematically categorized into seven categories: imaging, preplanning, treatment planning, applicator reconstruction, quality assurance, outcome prediction, and real-time monitoring. Each major category is further subdivided based on cancer type or specific tasks, with detailed summaries of models, data sizes, and results presented in corresponding tables. This review offers insights into the current advancements, challenges, and the impact of AI on treatment paradigms, encouraging further research to expand its clinical utility.

physics.med-ph↗

arXiv2024

Unsupervised Bayesian Generation of Synthetic CT from CBCT Using Patient-Specific Score-Based Prior

Background: Cone-beam computed tomography (CBCT) scans, performed fractionally (e.g., daily or weekly), are widely utilized for patient alignment in the image-guided radiotherapy (IGRT) process, thereby making it a potential imaging modality for the implementation of adaptive radiotherapy (ART) protocols. Nonetheless, significant artifacts and incorrect Hounsfield unit (HU) values hinder their application in quantitative tasks such as target and organ segmentations and dose calculation. Therefore, acquiring CT-quality images from the CBCT scans is essential to implement online ART in clinical settings. Purpose: This work aims to develop an unsupervised learning method using the patient-specific diffusion model for CBCT-based synthetic CT (sCT) generation to improve the image quality of CBCT. Methods: The proposed method is in an unsupervised framework that utilizes a patient-specific score-based model as the image prior alongside a customized total variation (TV) regularization to enforce coherence across different transverse slices. The score-based model is unconditionally trained using the same patient's planning CT (pCT) images to characterize the manifold of CT-quality images and capture the unique anatomical information of the specific patient. The efficacy of the proposed method was assessed on images from anatomical sites including head and neck (H&N) cancer, pancreatic cancer, and lung cancer. The performance of the proposed CBCT correction method was evaluated using quantitative metrics including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and normalized cross-correlation (NCC). Additionally, the proposed algorithm was benchmarked against two other unsupervised diffusion model-based CBCT correction algorithms.

physics.med-ph↗

arXiv2024

Assessing Bilateral Neurovascular Bundles Function with Pulsed Wave Doppler Ultrasound: Implications for Reducing Erectile Dysfunction Following Prostate Radiotherapy

This study aims to evaluate the functional status of bilateral neurovascular bundles (NVBs) using pulsed wave Doppler ultrasound in patients undergoing prostate radiotherapy (RT). Sixty-two patients (mean age: 66.1 +/- 7.2 years) underwent transrectal ultrasound scan using a conventional ultrasound scanner, a 7.5 MHz bi-plane probe and a mechanical stepper. The ultrasound protocol comprised 3 steps: 1) 3D B-mode scans of the entire prostate, 2) localization of NVBs using color flow Doppler imaging, and 3) measurement of NVB function using pulsed wave Doppler. Five pulsed Doppler waveform features were extracted: peak systolic velocity (PSV), end-diastolic velocity (EDV), mean velocity (Vm), resistive index (RI), and pulsatile index (PI). In summary, this study presents a Doppler evaluation of NVBs in patients undergoing prostate RT. It highlights substantial differences in Doppler ultrasound waveform features between bilateral NVBs. The proposed ultrasound method may prove valuable as clinicians strive to deliver NVB-sparing RT to preserve sexual function effectively and enhance patients' overall well-being.

physics.med-ph↗

arXiv2023

Understanding and Mitigating Extrapolation Failures in Physics-Informed Neural Networks

Physics-informed Neural Networks (PINNs) have recently gained popularity due to their effective approximation of partial differential equations (PDEs) using deep neural networks (DNNs). However, their out of domain behavior is not well understood, with previous work speculating that the presence of high frequency components in the solution function might be to blame for poor extrapolation performance. In this paper, we study the extrapolation behavior of PINNs on a representative set of PDEs of different types, including high-dimensional PDEs. We find that failure to extrapolate is not caused by high frequencies in the solution function, but rather by shifts in the support of the Fourier spectrum over time. We term these spectral shifts and quantify them by introducing a Weighted Wasserstein-Fourier distance (WWF). We show that the WWF can be used to predict PINN extrapolation performance, and that in the absence of significant spectral shifts, PINN predictions stay close to the true solution even in extrapolation. Finally, we propose a transfer learning-based strategy to mitigate the effects of larger spectral shifts, which decreases extrapolation errors by up to 82%.

cs.LG↗

arXiv2023

Deep Learning Detection and Classification of Gravitational Waves from Neutron Star-Black Hole Mergers

The Laser Interferometer Gravitational-Wave Observatory (LIGO) and Virgo Interferometer Collaborations have now detected all three classes of compact binary mergers: binary black hole (BBH), binary neutron star (BNS), and neutron star-black hole (NSBH). For coalescences involving neutron stars, the simultaneous observation of gravitational and electromagnetic radiation produced by an event, has broader potential to enhance our understanding of these events, and also to probe the equation of state (EOS) of dense matter. However, electromagnetic follow-up to gravitational wave (GW) events requires rapid real-time detection and classification of GW signals, and conventional detection approaches are computationally prohibitive for the anticipated rate of detection of next-generation GW detectors. In this work, we present the first deep learning based results of classification of GW signals from NSBH mergers in \textit{real} LIGO data. We show for the first time that a deep neural network can successfully distinguish all three classes of compact binary mergers and separate them from detector noise. Specifically, we train a convolutional neural network (CNN) on $\sim 500,000$ data samples of real LIGO noise with injected BBH, BNS, and NSBH GW signals, and we show that our network has high sensitivity and accuracy. Most importantly, we successfully recover the two confirmed NSBH events to-date (GW200105 and GW200115) and the two confirmed BNS mergers to-date (GW170817 and GW190425), together with $\approx 90\%$ of all BBH candidate events from the third Gravitational Wave Transient Catalog, GWTC-3. These results are an important step towards low-latency real-time GW detection, enabling multi-messenger astronomy.

astro-ph.IM↗

arXiv2023

Using Machine Learning to Link Black Hole Accretion Flows with Spatially Resolved Polarimetric Observables

We introduce a new library of 535,194 model images of the supermassive black holes and Event Horizon Telescope (EHT) targets Sgr A* and M87*, computed by performing general relativistic radiative transfer calculations on general relativistic magnetohydrodynamics simulations. Then, to infer underlying black hole and accretion flow parameters (spin, inclination, ion-to-electron temperature ratio, and magnetic field polarity), we train a random forest machine learning model on various hand-picked polarimetric observables computed from each image. Our random forest is capable of making meaningful predictions of spin, inclination, and the ion-to-electron temperature ratio, but has more difficulty inferring magnetic field polarity. To disentangle how physical parameters are encoded in different observables, we apply two different metrics to rank the importance of each observable at inferring each physical parameter. Details of the spatially resolved linear polarization morphology stand out as important discriminators between models. Bearing in mind the theoretical limitations and incompleteness of our image library, for the real M87* data, our machinery favours high-spin retrograde models with large ion-to-electron temperature ratios. Due to the time-variable nature of these targets, repeated polarimetric imaging will further improve model inference as the EHT and next-generation (EHT) continue to develop and monitor their targets.

astro-ph.HE↗

arXiv2022

Automatic Fake News Detection: Are current models "fact-checking" or "gut-checking"?

Automatic fake news detection models are ostensibly based on logic, where the truth of a claim made in a headline can be determined by supporting or refuting evidence found in a resulting web query. These models are believed to be reasoning in some way; however, it has been shown that these same results, or better, can be achieved without considering the claim at all -- only the evidence. This implies that other signals are contained within the examined evidence, and could be based on manipulable factors such as emotion, sentiment, or part-of-speech (POS) frequencies, which are vulnerable to adversarial inputs. We neutralize some of these signals through multiple forms of both neural and non-neural pre-processing and style transfer, and find that this flattening of extraneous indicators can induce the models to actually require both claims and evidence to perform well. We conclude with the construction of a model using emotion vectors built off a lexicon and passed through an "emotional attention" mechanism to appropriately weight certain emotions. We provide quantifiable results that prove our hypothesis that manipulable features are being used for fact-checking.

cs.CL↗

arXiv2021

Black Hole Magnetic Fields and Their Imprint on Circular Polarization Images

The circular polarization of black hole accretion flows can encode properties of the underlying magnetic field structure. Using general relativistic magnetohydrodynamics (GRMHD) simulations, we study the imprint of magnetic field geometry on circular polarization images potentially observable by the Event Horizon Telescope (EHT). We decompose images into the different mechanisms that generate circular polarization in these models, which are sensitive to both the line of sight direction and twist of the magnetic field. In these models, a stable sign of the circular polarization over time, as observed for several sources, can be attributed to a stability of these properties. We illustrate how different aspects of a generic helical magnetic field geometry become imprinted on a circular polarization image. We also identify novel effects of light bending that affect the circular polarization image on event horizon scales. One consequence is the sign flipping of successive photon rings in face-on systems, which if observable and uncorrupted by Faraday rotation, can directly encode the handedness of the approaching magnetic field.

astro-ph.HE↗