arXiv subjects

Yong Xia

Publications and source records attributed to Yong Xia.

At least 55 records · Page 3Linked to original sources

arXiv2025

Deformable Medical Image Registration with Effective Anatomical Structure Representation and Divide-and-Conquer Network

Effective representation of Regions of Interest (ROI) and independent alignment of these ROIs can significantly enhance the performance of deformable medical image registration (DMIR). However, current learning-based DMIR methods have limitations. Unsupervised techniques disregard ROI representation and proceed directly with aligning pairs of images, while weakly-supervised methods heavily depend on label constraints to facilitate registration. To address these issues, we introduce a novel ROI-based registration approach named EASR-DCN. Our method represents medical images through effective ROIs and achieves independent alignment of these ROIs without requiring labels. Specifically, we first used a Gaussian mixture model for intensity analysis to represent images using multiple effective ROIs with distinct intensities. Furthermore, we propose a novel Divide-and-Conquer Network (DCN) to process these ROIs through separate channels to learn feature alignments for each ROI. The resultant correspondences are seamlessly integrated to generate a comprehensive displacement vector field. Extensive experiments were performed on three MRI and one CT datasets to showcase the superior accuracy and deformation reduction efficacy of our EASR-DCN. Compared to VoxelMorph, our EASR-DCN achieved improvements of 10.31\% in the Dice score for brain MRI, 13.01\% for cardiac MRI, and 5.75\% for hippocampus MRI, highlighting its promising potential for clinical applications. The code for this work will be released upon acceptance of the paper.

eess.IV↗

arXiv2025

Pre-training Everywhere: Parameter-Efficient Fine-Tuning for Medical Image Analysis via Target Parameter Pre-training

Parameter-efficient fine-tuning (PEFT) techniques have emerged to address overfitting and high computational costs associated with fully fine-tuning in self-supervised learning. Mainstream PEFT methods add a few trainable parameters while keeping the pre-trained backbone parameters fixed. These methods achieve comparative, and often superior, performance to fully fine-tuning, demonstrating the powerful representation ability of the pre-trained backbone. Despite this success, these methods typically ignore the initialization of the new parameters, often relying solely on random initialization. We argue that if pre-training is significantly beneficial, it should be applied to all parameters requiring representational capacity. Motivated by this, we propose Target Parameter Pre-training (TPP), a simple yet effective fine-tuning framework. TPP pre-trains target parameters, i.e., the new parameters introduced during fine-tuning, in an additional stage before PEFT. During this stage, the pre-trained backbone parameters are frozen, and only the new parameters are trainable. A defined pretext task encourages the new parameters to learn specific representations of downstream data. Subsequently, when PEFT is employed, the pre-trained new parameters are loaded to enhance fine-tuning efficiency. The proposed TPP framework is versatile, allowing integration with various pre-trained backbones, pretext tasks, and PEFT methods. We evaluated the fine-tuning performance of our method on seven public datasets, covering four modalities and two task types. The results demonstrate that TPP can be easily integrated into existing PEFT methods, significantly improving performance.

cs.CV↗

arXiv2025

Enjoying Information Dividend: Gaze Track-based Medical Weakly Supervised Segmentation

Weakly supervised semantic segmentation (WSSS) in medical imaging struggles with effectively using sparse annotations. One promising direction for WSSS leverages gaze annotations, captured via eye trackers that record regions of interest during diagnostic procedures. However, existing gaze-based methods, such as GazeMedSeg, do not fully exploit the rich information embedded in gaze data. In this paper, we propose GradTrack, a framework that utilizes physicians' gaze track, including fixation points, durations, and temporal order, to enhance WSSS performance. GradTrack comprises two key components: Gaze Track Map Generation and Track Attention, which collaboratively enable progressive feature refinement through multi-level gaze supervision during the decoding process. Experiments on the Kvasir-SEG and NCI-ISBI datasets demonstrate that GradTrack consistently outperforms existing gaze-based methods, achieving Dice score improvements of 3.21\% and 2.61\%, respectively. Moreover, GradTrack significantly narrows the performance gap with fully supervised models such as nnUNet.

cs.CV↗

arXiv2025

Cubic NK-SVD: An Algorithm for Designing Parametric Dictionary in Frequency Estimation

We propose a novel parametric dictionary learning algorithm for line spectral estimation, applicable in both single measurement vector (SMV) and multiple measurement vectors (MMV) scenarios. This algorithm, termed cubic Newtonized K-SVD (NK-SVD), extends the traditional K-SVD method by incorporating cubic regularization into Newton refinements. The proposed Gauss-Seidel scheme not only enhances the accuracy of frequency estimation over the continuum but also achieves better convergence by incorporating higher-order derivative information. A key contribution of this work is the rigorous convergence analysis of the proposed algorithm within the Block Coordinate Descent (BCD) framework. To the best of our knowledge, this is the first convergence analysis of BCD with a higher-order regularization scheme. Moreover, the convergence framework we develop is generalizable, providing a foundation for designing alternating minimization algorithms with higher-order regularization techniques. Extensive simulations demonstrate that cubic NK-SVD outperforms state-of-the-art methods in both SMV and MMV settings, particularly excelling in the challenging task of recovering closely-spaced frequencies. The code for our method is available at https://github.com/xzliu-opt/Cubic-NK-SVD.

math.OC↗

arXiv2025

Meta Curvature-Aware Minimization for Domain Generalization

Domain generalization (DG) aims to enhance the ability of models trained on source domains to generalize effectively to unseen domains. Recently, Sharpness-Aware Minimization (SAM) has shown promise in this area by reducing the sharpness of the loss landscape to obtain more generalized models. However, SAM and its variants sometimes fail to guide the model toward a flat minimum, and their training processes exhibit limitations, hindering further improvements in model generalization. In this paper, we first propose an improved model training process aimed at encouraging the model to converge to a flat minima. To achieve this, we design a curvature metric that has a minimal effect when the model is far from convergence but becomes increasingly influential in indicating the curvature of the minima as the model approaches a local minimum. Then we derive a novel algorithm from this metric, called Meta Curvature-Aware Minimization (MeCAM), to minimize the curvature around the local minima. Specifically, the optimization objective of MeCAM simultaneously minimizes the regular training loss, the surrogate gap of SAM, and the surrogate gap of meta-learning. We provide theoretical analysis on MeCAM's generalization error and convergence rate, and demonstrate its superiority over existing DG methods through extensive experiments on five benchmark DG datasets, including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. Code will be available on GitHub.

cs.CV↗

arXiv2025

Long-Term Timing Analysis of PSR J1741-3016: Efficient Noise Characterization Using PINT

The stable rotation of young pulsars is often interrupted by two non-deterministic phenomena: glitches and red timing noise. Timing noise provides insights into plasma and nuclear physics under extreme conditions. The framework leverages rotational symmetry in pulsar spin-down models and temporal symmetry in noise processes to achieve computational efficiency, aligning with the journal's focus on symmetry principles in physical systems. In this paper, we apply a novel frequentist framework developed within the PINT software package (v0.9.8) to analyze single-pulsar noise processes. Using 17.5 years of pulse time-of-arrival (TOA) data for the young pulsar PSR J1741-3016, observed with the Nanshan 26 m radio telescope, we investigate its timing properties. In this study, we employed the Downhill Weighted Least-Squares Fitter to estimate the pulsar's spin parameters and position. The Akaike Information Criterion (AIC) was used for model parameter selection. The results obtained with PINT were compared to those from ENTERPRISE and TEMPONEST, two Bayesian-based frameworks. We demonstrate that PINT achieves comparable results with significantly reduced computational costs. Additionally, the adequacy of the noise model can be readily verified through visual inspection tools. Future research will utilize this framework to analyze timing noise across a large sample of young pulsars.

astro-ph.HE↗

arXiv2025

Searching for gravitational-wave bursts from cosmic string cusps with the Parkes Pulsar Timing Array third data release

Pulsar timing arrays (PTAs) are designed to detect nanohertz-frequency gravitational waves (GWs). Since GWs are anticipated from cosmic strings, PTAs offer a viable approach to testing their existence. We present the results of the first Bayesian search for gravitational-wave bursts from cosmic string cusps (GWCS) using the third PPTA data release for 30 millisecond pulsars. In this data collection, we find no evidence for GWCS signals. We compare a model with a GWCS signal to one with only noise, including a common spatially uncorrelated red noise (CURN), and find that our data is more consistent with the noise-only model.We then establish upper limits on the strain amplitude of GWCS at the pulsar term, based on the analysis of 30 millisecond pulsars, after finding no compelling evidence. We find the addition of a CURN with different spectral indices into the noise model has a negligible impact on the upper limits. And the upper limit range of the amplitude of the pulsar-term GWCS is concentrated between 10^{-12} and 10^{-11}. Finally, we set upper limits on the amplitude of GWCS events, parametrized by width and event epoch, for a single pulsar PSR J1857+0943. Moreover, we derive upper limit on the cosmic string tension as a function of burst width and compare it with previous results.

gr-qc↗

arXiv2025

A Unified Algorithmic Framework for Dynamic Compressive Sensing

We propose a unified dynamic tracking algorithmic framework (PLAY-CS) to reconstruct signal sequences with their intrinsic structured dynamic sparsity. By capitalizing on specific statistical assumptions concerning the dynamic filter of the signal sequences, the proposed framework exhibits versatility by encompassing various existing dynamic compressive sensing (DCS) algorithms. This is achieved through the incorporation of a newly proposed Partial-Laplacian filtering sparsity model, tailored to capture a more sophisticated dynamic sparsity. In practical scenarios such as dynamic channel tracking in wireless communications, the framework demonstrates enhanced performance compared to existing DCS algorithms.

cs.IT↗

arXiv2025

FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis

Federated domain generalization aims to train a global model from multiple source domains and ensure its generalization ability to unseen target domains. Due to the target domain being with unknown domain shifts, attempting to approximate these gaps by source domains may be the key to improving model generalization capability. Existing works mainly focus on sharing and recombining local domain-specific attributes to increase data diversity and simulate potential domain shifts. However, these methods may be insufficient since only the local attribute recombination can be hard to touch the out-of-distribution of global data. In this paper, we propose a simple-yet-efficient framework named Federated Domain Adversarial Generation (FedDAG). It aims to simulate the domain shift and improve the model generalization by adversarially generating novel domains different from local and global source domains. Specifically, it generates novel-style images by maximizing the instance-level feature discrepancy between original and generated images and trains a generalizable task model by minimizing their feature discrepancy. Further, we observed that FedDAG could cause different performance improvements for local models. It may be due to inherent data isolation and heterogeneity among clients, exacerbating the imbalance in their generalization contributions to the global model. Ignoring this imbalance can lead the global model's generalization ability to be sub-optimal, further limiting the novel domain generation procedure. Thus, to mitigate this imbalance, FedDAG hierarchically aggregates local models at the within-client and across-client levels by using the sharpness concept to evaluate client model generalization contributions. Extensive experiments across four medical benchmarks demonstrate FedDAG's ability to enhance generalization in federated medical scenarios.

cs.CV↗

arXiv2025

Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across various out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms on three test sets. In addition, we also evaluated pre-existing AI frameworks--which, differing from algorithms, are more flexible and can support different algorithms--including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

cs.CV↗

arXiv2024

Gradient Alignment Improves Test-Time Adaptation for Medical Image Segmentation

Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many Test-time Adaptation (TTA) methods have been proposed to address this issue by fine-tuning pre-trained models with test data during inference. These methods, however, often suffer from less-satisfactory optimization due to suboptimal optimization direction (dictated by the gradient) and fixed step-size (predicated on the learning rate). In this paper, we propose the Gradient alignment-based Test-time adaptation (GraTa) method to improve both the gradient direction and learning rate in the optimization procedure. Unlike conventional TTA methods, which primarily optimize the pseudo gradient derived from a self-supervised objective, our method incorporates an auxiliary gradient with the pseudo one to facilitate gradient alignment. Such gradient alignment enables the model to excavate the similarities between different gradients and correct the gradient direction to approximate the empirical gradient related to the current segmentation task. Additionally, we design a dynamic learning rate based on the cosine similarity between the pseudo and auxiliary gradients, thereby empowering the adaptive fine-tuning of pre-trained models on diverse test data. Extensive experiments establish the effectiveness of the proposed gradient alignment and dynamic learning rate and substantiate the superiority of our GraTa method over other state-of-the-art TTA methods on a benchmark medical image segmentation task. The code and weights of pre-trained source models are available at https://github.com/Chen-Ziyang/GraTa.

cs.CV↗

arXiv2024

Day-Night Adaptation: An Innovative Source-free Adaptation Framework for Medical Image Segmentation

Distribution shifts widely exist in medical images acquired from different medical centres, hindering the deployment of semantic segmentation models trained on one centre (source domain) to another (target domain). While unsupervised domain adaptation has shown significant promise in mitigating these shifts, it poses privacy risks due to sharing data between centres. To facilitate adaptation while preserving data privacy, source-free domain adaptation (SFDA) and test-time adaptation (TTA) have emerged as effective paradigms, relying solely on target domain data. However, SFDA requires a pre-collected target domain dataset before deployment. TTA insufficiently exploit the potential value of test data, as it processes the test data only once. Considering that most medical centres operate during the day and remain inactive at night in clinical practice, we propose a novel adaptation framework called Day-Night Adaptation (DyNA) with above insights, which performs adaptation through day-night cycles without requiring access to source data. During the day, a low-frequency prompt is trained to adapt the frozen model to each test sample. We construct a memory bank for prompt initialization and develop a warm-up mechanism to enhance prompt training. During the night, we reuse test data collected from the day and introduce a global student model to bridge the knowledge between teacher and student models, facilitating model fine-tuning while ensuring training stability. Extensive experiments demonstrate that our DyNA outperforms existing TTA and SFDA methods on two benchmark medical image segmentation tasks. Code will be available after the paper is published.

cs.CV↗

arXiv2024

Breaking the Cycle of Recurring Failures: Applying Generative AI to Root Cause Analysis in Legacy Banking Systems

Traditional banks face significant challenges in digital transformation, primarily due to legacy system constraints and fragmented ownership. Recent incidents show that such fragmentation often results in superficial incident resolutions, leaving root causes unaddressed and causing recurring failures. We introduce a novel approach to post-incident analysis, integrating knowledge-based GenAI agents with the "Five Whys" technique to examine problem descriptions and change request data. This method uncovered that approximately 70% of the incidents previously attributed to management or vendor failures were due to underlying internal code issues. We present a case study to show the impact of our method. By scanning over 5,000 projects, we identified over 400 files with a similar root cause. Overall, we leverage the knowledge-based agents to automate and elevate root cause analysis, transforming it into a more proactive process. These agents can be applied across other phases of the software development lifecycle, further improving development processes.

cs.SE↗

arXiv2024

A Survey of Medical Vision-and-Language Applications and Their Techniques

Medical vision-and-language models (MVLMs) have attracted substantial interest due to their capability to offer a natural language interface for interpreting complex medical data. Their applications are versatile and have the potential to improve diagnostic accuracy and decision-making for individual patients while also contributing to enhanced public health monitoring, disease surveillance, and policy-making through more efficient analysis of large data sets. MVLMS integrate natural language processing with medical images to enable a more comprehensive and contextual understanding of medical images alongside their corresponding textual information. Unlike general vision-and-language models trained on diverse, non-specialized datasets, MVLMs are purpose-built for the medical domain, automatically extracting and interpreting critical information from medical images and textual reports to support clinical decision-making. Popular clinical applications of MVLMs include automated medical report generation, medical visual question answering, medical multimodal segmentation, diagnosis and prognosis and medical image-text retrieval. Here, we provide a comprehensive overview of MVLMs and the various medical tasks to which they have been applied. We conduct a detailed analysis of various vision-and-language model architectures, focusing on their distinct strategies for cross-modal integration/exploitation of medical visual and textual features. We also examine the datasets used for these tasks and compare the performance of different models based on standardized evaluation metrics. Furthermore, we highlight potential challenges and summarize future research trends and directions. The full collection of papers and codes is available at: https://github.com/YtongXie/Medical-Vision-and-Language-Tasks-and-Methodologies-A-Survey.

cs.CV↗

arXiv2024

CoSAM: Self-Correcting SAM for Domain Generalization in 2D Medical Image Segmentation

Medical images often exhibit distribution shifts due to variations in imaging protocols and scanners across different medical centers. Domain Generalization (DG) methods aim to train models on source domains that can generalize to unseen target domains. Recently, the segment anything model (SAM) has demonstrated strong generalization capabilities due to its prompt-based design, and has gained significant attention in image segmentation tasks. Existing SAM-based approaches attempt to address the need for manual prompts by introducing prompt generators that automatically generate these prompts. However, we argue that auto-generated prompts may not be sufficiently accurate under distribution shifts, potentially leading to incorrect predictions that still require manual verification and correction by clinicians. To address this challenge, we propose a method for 2D medical image segmentation called Self-Correcting SAM (CoSAM). Our approach begins by generating coarse masks using SAM in a prompt-free manner, providing prior prompts for the subsequent stages, and eliminating the need for prompt generators. To automatically refine these coarse masks, we introduce a generalized error decoder that simulates the correction process typically performed by clinicians. Furthermore, we generate diverse prompts as feedback based on the corrected masks, which are used to iteratively refine the predictions within a self-correcting loop, enhancing the generalization performance of our model. Extensive experiments on two medical image segmentation benchmarks across multiple scenarios demonstrate the superiority of CoSAM over state-of-the-art SAM-based methods.

cs.CV↗

arXiv2024

Closing the duality gap of the generalized trace ratio problem

The generalized trace ratio problem {\rm (GTRP)} is to maximize a quadratic fractional objective function in trace formulation over the Stiefel manifold. In this paper, based on a newly developed matrix S-lemma, we show that {\rm (GTRP)}, if a redundant constraint is added and well scaled, has zero Lagrangian duality gap. However, this is not always true without the technique of scaling or adding the redundant constraint.

math.OC↗

arXiv2024

A polynomially solvable case of unconstrained (-1,1)-quadratic fractional optimization

In this paper, we consider an unconstrained (-1,1)-quadratic fractional optimization in the following form: $\min_{x\in\{-1,1\}^n}~(x^TAx+α)/(x^TBx+β)$, where $A$ and $B$, given by their nonzero eigenvalues and associated eigenvectors, have ranks not exceeding fixed integers $r_a$ and $r_b$, respectively. We show that this problem can be solved in $O(n^{r_a+r_b+1}\log^2 n)$ by the accelerated Newton-Dinkelbach method when the matrices $A$ has nonpositive diagonal entries only, $B$ has nonnegative diagonal entries only. Furthermore, this problem can be solved in $O(n^{r_a+r_b+2}\log^2 n)$ when $A$ has $O(\log(n))$ positive diagonal entries, $B$ has $O(\log(n))$ negative diagonal entries.

math.OC↗

arXiv2024

Revisiting Atomic Norm Minimization: A Sequential Approach for Atom Identification and Refinement

Atomic norm minimization (ANM) is a key approach for line spectral estimation (LSE). Most related algorithms formulate ANM as a semidefinite programming (SDP), which incurs high computational cost. In this letter, we revisit the ANM problem and present a novel limit-based formulation, which dissects the essential components of the semidefinite characterization of ANM. Our new formulation does not depend on SDP and can be extended to handle more general atomic sets beyond mixture of complex sinusoids. Furthermore, we reveal the connection between ANM and Bayesian LSE approaches, bridging the gap between these two methodologies. Based on this new formulation, we propose a low-complexity algorithm called Sequential Atom Identification and Refinement (SAIR) for ANM. Simulation results demonstrate that SAIR achieves superior estimation accuracy and computational efficiency compared to other state-of-the-art methods.

math.OC↗