arXiv subjects

Xiaofeng Yang

Publications and source records attributed to Xiaofeng Yang.

At least 127 records · Page 7Linked to original sources

arXiv2024

Full-dose Whole-body PET Synthesis from Low-dose PET Using High-efficiency Denoising Diffusion Probabilistic Model: PET Consistency Model

Objective: Positron Emission Tomography (PET) has been a commonly used imaging modality in broad clinical applications. One of the most important tradeoffs in PET imaging is between image quality and radiation dose: high image quality comes with high radiation exposure. Improving image quality is desirable for all clinical applications while minimizing radiation exposure is needed to reduce risk to patients. Approach: We introduce PET Consistency Model (PET-CM), an efficient diffusion-based method for generating high-quality full-dose PET images from low-dose PET images. It employs a two-step process, adding Gaussian noise to full-dose PET images in the forward diffusion, and then denoising them using a PET Shifted-window Vision Transformer (PET-VIT) network in the reverse diffusion. The PET-VIT network learns a consistency function that enables direct denoising of Gaussian noise into clean full-dose PET images. PET-CM achieves state-of-the-art image quality while requiring significantly less computation time than other methods. Results: In experiments comparing eighth-dose to full-dose images, PET-CM demonstrated impressive performance with NMAE of 1.278+/-0.122%, PSNR of 33.783+/-0.824dB, SSIM of 0.964+/-0.009, NCC of 0.968+/-0.011, HRS of 4.543, and SUV Error of 0.255+/-0.318%, with an average generation time of 62 seconds per patient. This is a significant improvement compared to the state-of-the-art diffusion-based model with PET-CM reaching this result 12x faster. Similarly, in the quarter-dose to full-dose image experiments, PET-CM delivered competitive outcomes, achieving an NMAE of 0.973+/-0.066%, PSNR of 36.172+/-0.801dB, SSIM of 0.984+/-0.004, NCC of 0.990+/-0.005, HRS of 4.428, and SUV Error of 0.151+/-0.192% using the same generation process, which underlining its high quantitative and clinical precision in both denoising scenario.

eess.IV↗

arXiv2024

Dual-Energy Cone-Beam CT Using Two Complementary Limited-Angle Scans with A Projection-Consistent Diffusion Model

Background: Dual-energy imaging on cone-beam CT (CBCT) scanners has great potential in different clinical applications, including image-guided surgery and adaptive proton therapy. However, the clinical practice of dual-energy CBCT (DE-CBCT) has been hindered by the requirement of sophisticated hardware components. Purpose: In this work, we aim to propose a practical solution for single-scan dual-energy imaging on current CBCT scanners without hardware modifications, using two complementary limited-angle scans with a projection-consistent diffusion model. Methods: Our approach has two major components: data acquisition using two complementary limited-angle scans, and dual-energy projections restoration with subsequent FDK reconstruction. Two complementary scans at different kVps are performed in a single rotation by switching the tube voltage at the middle of the source trajectory, acquiring the mixed-spectra projection in a single CBCT scan. Full-sampled dual-energy projections are then restored by a projection-consistent diffusion model in a slice-by-slice manner, followed by the DE-CBCT reconstruction using the FDK algorithm. Results: The proposed method was evaluated in a simulation study of digital abdomen phantoms and a study of real rat data. In the simulation study, the proposed method produced DE-CBCT images at a mean absolute error (MAE) of 20 HU. In the small-animal study, reconstructed DE-CBCT images using the proposed method gave an MAE of 25 HU. Conclusion: This study demonstrates the feasibility of DE-CBCT imaging using two complementary limited-angle scans with a projection-consistent diffusion model in both half-fan and short scans. The proposed method may allow quantitative applications of DE-CBCT and enable DE-CBCT-based adaptive proton therapy.

physics.med-ph↗

arXiv2024

Cross-Shaped Windows Transformer with Self-supervised Pretraining for Clinically Significant Prostate Cancer Detection in Bi-parametric MRI

Biparametric magnetic resonance imaging (bpMRI) has demonstrated promising results in prostate cancer (PCa) detection using convolutional neural networks (CNNs). Recently, transformers have achieved competitive performance compared to CNNs in computer vision. Large scale transformers need abundant annotated data for training, which are difficult to obtain in medical imaging. Self-supervised learning (SSL) utilizes unlabeled data to generate meaningful semantic representations without the need for costly annotations, enhancing model performance on tasks with limited labeled data. We introduce a novel end-to-end Cross-Shaped windows (CSwin) transformer UNet model, CSwin UNet, to detect clinically significant prostate cancer (csPCa) in prostate bi-parametric MR imaging (bpMRI) and demonstrate the effectiveness of our proposed self-supervised pre-training framework. Using a large prostate bpMRI dataset with 1500 patients, we first pretrain CSwin transformer using multi-task self-supervised learning to improve data-efficiency and network generalizability. We then finetune using lesion annotations to perform csPCa detection. Five-fold cross validation shows that self-supervised CSwin UNet achieves 0.888 AUC and 0.545 Average Precision (AP), significantly outperforming four comparable models (Swin UNETR, DynUNet, Attention UNet, UNet). Using a separate bpMRI dataset with 158 patients, we evaluate our method robustness to external hold-out data. Self-supervised CSwin UNet achieves 0.79 AUC and 0.45 AP, still outperforming all other comparable methods and demonstrating good generalization to external data.

eess.IV↗

arXiv2024

DUE: Dynamic Uncertainty-Aware Explanation Supervision via 3D Imputation

Explanation supervision aims to enhance deep learning models by integrating additional signals to guide the generation of model explanations, showcasing notable improvements in both the predictability and explainability of the model. However, the application of explanation supervision to higher-dimensional data, such as 3D medical images, remains an under-explored domain. Challenges associated with supervising visual explanations in the presence of an additional dimension include: 1) spatial correlation changed, 2) lack of direct 3D annotations, and 3) uncertainty varies across different parts of the explanation. To address these challenges, we propose a Dynamic Uncertainty-aware Explanation supervision (DUE) framework for 3D explanation supervision that ensures uncertainty-aware explanation guidance when dealing with sparsely annotated 3D data with diffusion-based 3D interpolation. Our proposed framework is validated through comprehensive experiments on diverse real-world medical imaging datasets. The results demonstrate the effectiveness of our framework in enhancing the predictability and explainability of deep learning models in the context of medical imaging diagnosis applications.

cs.CV↗

arXiv2024

Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior

Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the back view) and inaccurate shapes (e.g., animals with extra legs). Existing methods mainly address this issue by retraining diffusion models with images rendered from 3D data to ensure multi-view consistency while struggling to balance 2D generation quality with 3D consistency. In this paper, we present a new framework Sculpt3D that equips the current pipeline with explicit injection of 3D priors from retrieved reference objects without re-training the 2D diffusion model. Specifically, we demonstrate that high-quality and diverse 3D geometry can be guaranteed by keypoints supervision through a sparse ray sampling approach. Moreover, to ensure accurate appearances of different views, we further modulate the output of the 2D diffusion model to the correct patterns of the template views without altering the generated object's style. These two decoupled designs effectively harness 3D information from reference objects to generate 3D objects while preserving the generation quality of the 2D diffusion model. Extensive experiments show our method can largely improve the multi-view consistency while retaining fidelity and diversity. Our project page is available at: https://stellarcheng.github.io/Sculpt3D/.

cs.CV↗

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

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the other hand, methods based on implicit 3D representations, like Neural Radiance Field (NeRF), render complex scenes effectively but suffer from slow processing speeds and limited control over specific scene areas. In response to these challenges, our paper presents GaussianEditor, an innovative and efficient 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation. GaussianEditor enhances precision and control in editing through our proposed Gaussian semantic tracing, which traces the editing target throughout the training process. Additionally, we propose Hierarchical Gaussian splatting (HGS) to achieve stabilized and fine results under stochastic generative guidance from 2D diffusion models. We also develop editing strategies for efficient object removal and integration, a challenging task for existing methods. Our comprehensive experiments demonstrate GaussianEditor's superior control, efficacy, and rapid performance, marking a significant advancement in 3D editing. Project Page: https://buaacyw.github.io/gaussian-editor/

cs.CV↗

arXiv2023

Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting

We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks. Despite the critical importance of these tasks, existing methodologies often struggle to generate high-caliber results. We begin by examining the inherent limitations in previous diffusion priors. We identify a divergence between the diffusion priors and the training procedures of diffusion models that substantially impairs the quality of 3D generation. To address this issue, we propose a novel, unified framework that iteratively optimizes both the 3D model and the diffusion prior. Leveraging the different learnable parameters of the diffusion prior, our approach offers multiple configurations, affording various trade-offs between performance and implementation complexity. Notably, our experimental results demonstrate that our method markedly surpasses existing techniques, establishing new state-of-the-art in the realm of text-to-3D generation. Furthermore, our approach exhibits impressive performance on both NeRF and the newly introduced 3D Gaussian Splatting backbones. Additionally, our framework yields insightful contributions to the understanding of recent score distillation methods, such as the VSD and DDS loss.

cs.CV↗

arXiv2023

High-resolution 3T to 7T MRI Synthesis with a Hybrid CNN-Transformer Model

7 Tesla (7T) apparent diffusion coefficient (ADC) maps derived from diffusion-weighted imaging (DWI) demonstrate improved image quality and spatial resolution over 3 Tesla (3T) ADC maps. However, 7T magnetic resonance imaging (MRI) currently suffers from limited clinical unavailability, higher cost, and increased susceptibility to artifacts. To address these issues, we propose a hybrid CNN-transformer model to synthesize high-resolution 7T ADC maps from multi-modal 3T MRI. The Vision CNN-Transformer (VCT), composed of both Vision Transformer (ViT) blocks and convolutional layers, is proposed to produce high-resolution synthetic 7T ADC maps from 3T ADC maps and 3T T1-weighted (T1w) MRI. ViT blocks enabled global image context while convolutional layers efficiently captured fine detail. The VCT model was validated on the publicly available Human Connectome Project Young Adult dataset, comprising 3T T1w, 3T DWI, and 7T DWI brain scans. The Diffusion Imaging in the Python library was used to compute ADC maps from the DWI scans. A total of 171 patient cases were randomly divided: 130 training cases, 20 validation cases, and 21 test cases. The synthetic ADC maps were evaluated by comparing their similarity to the ground truth volumes with the following metrics: peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and mean squared error (MSE). The results are as follows: PSNR: 27.0+-0.9 dB, SSIM: 0.945+-0.010, and MSE: 2.0+-0.4E-3. Our predicted images demonstrate better spatial resolution and contrast compared to 3T MRI and prediction results made by ResViT and pix2pix. These high-quality synthetic 7T MR images could be beneficial for disease diagnosis and intervention, especially when 7T MRI scanners are unavailable.

physics.med-ph↗

arXiv2023

Image-Domain Material Decomposition for Dual-energy CT using Unsupervised Learning with Data-fidelity Loss

Background: Dual-energy CT (DECT) and material decomposition play vital roles in quantitative medical imaging. However, the decomposition process may suffer from significant noise amplification, leading to severely degraded image signal-to-noise ratios (SNRs). While existing iterative algorithms perform noise suppression using different image priors, these heuristic image priors cannot accurately represent the features of the target image manifold. Although deep learning-based decomposition methods have been reported, these methods are in the supervised-learning framework requiring paired data for training, which is not readily available in clinical settings. Purpose: This work aims to develop an unsupervised-learning framework with data-measurement consistency for image-domain material decomposition in DECT.

physics.med-ph↗

arXiv2023

Artificial Intelligence-based Motion Tracking in Cancer Radiotherapy: A Review

Radiotherapy aims to deliver a prescribed dose to the tumor while sparing neighboring organs at risk (OARs). Increasingly complex treatment techniques such as volumetric modulated arc therapy (VMAT), stereotactic radiosurgery (SRS), stereotactic body radiotherapy (SBRT), and proton therapy have been developed to deliver doses more precisely to the target. While such technologies have improved dose delivery, the implementation of intra-fraction motion management to verify tumor position at the time of treatment has become increasingly relevant. Recently, artificial intelligence (AI) has demonstrated great potential for real-time tracking of tumors during treatment. However, AI-based motion management faces several challenges including bias in training data, poor transparency, difficult data collection, complex workflows and quality assurance, and limited sample sizes. This review serves to present the AI algorithms used for chest, abdomen, and pelvic tumor motion management/tracking for radiotherapy and provide a literature summary on the topic. We will also discuss the limitations of these algorithms and propose potential improvements.

physics.med-ph↗

arXiv2023

DESCN: Deep Entire Space Cross Networks for Individual Treatment Effect Estimation

Causal Inference has wide applications in various areas such as E-commerce and precision medicine, and its performance heavily relies on the accurate estimation of the Individual Treatment Effect (ITE). Conventionally, ITE is predicted by modeling the treated and control response functions separately in their individual sample spaces. However, such an approach usually encounters two issues in practice, i.e. divergent distribution between treated and control groups due to treatment bias, and significant sample imbalance of their population sizes. This paper proposes Deep Entire Space Cross Networks (DESCN) to model treatment effects from an end-to-end perspective. DESCN captures the integrated information of the treatment propensity, the response, and the hidden treatment effect through a cross network in a multi-task learning manner. Our method jointly learns the treatment and response functions in the entire sample space to avoid treatment bias and employs an intermediate pseudo treatment effect prediction network to relieve sample imbalance. Extensive experiments are conducted on a synthetic dataset and a large-scaled production dataset from the E-commerce voucher distribution business. The results indicate that DESCN can successfully enhance the accuracy of ITE estimation and improve the uplift ranking performance. A sample of the production dataset and the source code are released to facilitate future research in the community, which is, to the best of our knowledge, the first large-scale public biased treatment dataset for causal inference.

cs.LG↗

arXiv2023

Streamlined Pin-Ridge-Filter Design for Single-energy Proton FLASH Planning

Purpose: This study explored the feasibility of a streamlined pin-shaped ridge filter (pin-RF) design for single-energy proton FLASH planning. Methods: An inverse planning framework integrated within a TPS was established for FLASH planning. The framework involves generating a IMPT plan based on downstream energy modulation strategy (IMPT-DS), followed by a nested spot reduction process to iteratively reduce the total number of pencil beam directions (PBDs) and energy layers along each PBD for the IMPT-DS plan. The IMPT-DS plan is then translated into the pin-RFs for a single-energy IMPT plan (IMPT-RF). The framework was validated on three lung cases, quantifying the FLASH dose of the IMPT-RF plan using the FLASH effectiveness model and comparing it with the reference dose of a conventional IMPT plan to assess the clinical benefit of the FLASH planning technique. Results: The IMPT-RF plans closely matched the corresponding IMPT-DS plans in high dose conformity, with minimal changes in V7Gy and V7.4Gy for the lung (< 5%) and small increases in Dmax for other OARs (< 3.2 Gy). Comparing the FLASH doses to the doses of corresponding IMPT-RF plans, drastic reductions of up to ~33% were observed in Dmax for OARs in the high-to-moderate-dose regions with negligible changes in Dmax for OARs in low-dose regions. Positive clinical benefits were observed with notable reductions of 18.4-33.0% in Dmax for OARs in the high-dose regions. However, in the moderate-to-low-dose regions, only marginal positive or even negative clinical benefit for OARs were observed, such as increased lung V7Gy and V7.4Gy (16.4-38.9%). Conclusions: A streamlined pin-RF design for single-energy proton FLASH planning was validated, revealing positive clinical benefits for OARs in the high dose regions. The coarsened design of the pin-RF demonstrates potential cost efficiency and efficient production.

physics.med-ph↗

arXiv2023

Towards General and Efficient Online Tuning for Spark

The distributed data analytic system -- Spark is a common choice for processing massive volumes of heterogeneous data, while it is challenging to tune its parameters to achieve high performance. Recent studies try to employ auto-tuning techniques to solve this problem but suffer from three issues: limited functionality, high overhead, and inefficient search. In this paper, we present a general and efficient Spark tuning framework that can deal with the three issues simultaneously. First, we introduce a generalized tuning formulation, which can support multiple tuning goals and constraints conveniently, and a Bayesian optimization (BO) based solution to solve this generalized optimization problem. Second, to avoid high overhead from additional offline evaluations in existing methods, we propose to tune parameters along with the actual periodic executions of each job (i.e., online evaluations). To ensure safety during online job executions, we design a safe configuration acquisition method that models the safe region. Finally, three innovative techniques are leveraged to further accelerate the search process: adaptive sub-space generation, approximate gradient descent, and meta-learning method. We have implemented this framework as an independent cloud service, and applied it to the data platform in Tencent. The empirical results on both public benchmarks and large-scale production tasks demonstrate its superiority in terms of practicality, generality, and efficiency. Notably, this service saves an average of 57.00% memory cost and 34.93% CPU cost on 25K in-production tasks within 20 iterations, respectively.

cs.DC↗

arXiv2023

IT3D: Improved Text-to-3D Generation with Explicit View Synthesis

Recent strides in Text-to-3D techniques have been propelled by distilling knowledge from powerful large text-to-image diffusion models (LDMs). Nonetheless, existing Text-to-3D approaches often grapple with challenges such as over-saturation, inadequate detailing, and unrealistic outputs. This study presents a novel strategy that leverages explicitly synthesized multi-view images to address these issues. Our approach involves the utilization of image-to-image pipelines, empowered by LDMs, to generate posed high-quality images based on the renderings of coarse 3D models. Although the generated images mostly alleviate the aforementioned issues, challenges such as view inconsistency and significant content variance persist due to the inherent generative nature of large diffusion models, posing extensive difficulties in leveraging these images effectively. To overcome this hurdle, we advocate integrating a discriminator alongside a novel Diffusion-GAN dual training strategy to guide the training of 3D models. For the incorporated discriminator, the synthesized multi-view images are considered real data, while the renderings of the optimized 3D models function as fake data. We conduct a comprehensive set of experiments that demonstrate the effectiveness of our method over baseline approaches.

cs.CV↗

arXiv2023

Attention-Driven Lightweight Model for Pigmented Skin Lesion Detection

This study presents a lightweight pipeline for skin lesion detection, addressing the challenges posed by imbalanced class distribution and subtle or atypical appearances of some lesions. The pipeline is built around a lightweight model that leverages ghosted features and the DFC attention mechanism to reduce computational complexity while maintaining high performance. The model was trained on the HAM10000 dataset, which includes various types of skin lesions. To address the class imbalance in the dataset, the synthetic minority over-sampling technique and various image augmentation techniques were used. The model also incorporates a knowledge-based loss weighting technique, which assigns different weights to the loss function at the class level and the instance level, helping the model focus on minority classes and challenging samples. This technique involves assigning different weights to the loss function on two levels - the class level and the instance level. By applying appropriate loss weights, the model pays more attention to the minority classes and challenging samples, thus improving its ability to correctly detect and classify different skin lesions. The model achieved an accuracy of 92.4%, a precision of 84.2%, a recall of 86.9%, a f1-score of 85.4% with particularly strong performance in identifying Benign Keratosis-like lesions (BKL) and Nevus (NV). Despite its superior performance, the model's computational cost is considerably lower than some models with less accuracy, making it an optimal solution for real-world applications where both accuracy and efficiency are essential.

cs.CV↗

arXiv2023

One-step Iterative Estimation of Effective Atomic Number and Electron Density for Dual Energy CT

Dual-energy computed tomography (DECT) is a promising technology that has shown a number of clinical advantages over conventional X-ray CT, such as improved material identification, artifact suppression, etc. For proton therapy treatment planning, besides material-selective images, maps of effective atomic number (Z) and relative electron density to that of water ($ρ_e$) can also be achieved and further employed to improve stopping power ratio accuracy and reduce range uncertainty. In this work, we propose a one-step iterative estimation method, which employs multi-domain gradient $L_0$-norm minimization, for Z and $ρ_e$ maps reconstruction. The algorithm was implemented on GPU to accelerate the predictive procedure and to support potential real-time adaptive treatment planning. The performance of the proposed method is demonstrated via both phantom and patient studies.

physics.med-ph↗

arXiv2023

The reconstruction of dark energy with Ridge Regression Approach

It may be determined by non-parametric method if the dark energy evolves with time. We propose a method of combining PCA and biased estimation on the basis of ridge regression analysis to reconstruct parameters, meanwhile we present an interesting principal component selection criterion to avoid the arbitrariness of principal component selections, and use numerical integral by Lagrange interpolation to linearize the luminosity distance integral formula in nearly flat space to avoid instability of derivative for functional data. We get the preliminary test results that shows if $Δ\overline w (z) = \overline {\left| {1 + w(z)} \right|} <=0.05$ included $w(z) = -1$, the probability of making a type I error for ${w_{recon}} \ne -1$ is almost zero ($1\% $) in the test; otherwise, if $Δ\overline w (z) = \overline {\left| {1 + w(z)} \right|} > 0.05$, the probability of making a type I error for ${w_{recon}} = -1$ is not more than $10\% $. Finally, we use JLA sample to reconstruct $w(z)$, and the results reject ${\rm{w(z) }} \ne {\rm{ - 1}}$, which is agreement with $ΛCDM$ model.

astro-ph.CO↗