Searcharxiv⌕ Search

arXiv subjects

Xiaojuan Li

Publications and source records attributed to Xiaojuan Li.

At least 19 recordsLinked to original sources
arXiv2026

Medical Image Spatial Grounding with Semantic Sampling

Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos. In medical imaging research, VLMs represent a bridge between object detection and segmentation, and report understanding and generation. However, spatial grounding of anatomical structures in the three-dimensional space of medical images poses many unique challenges. In this study, we examine image modalities, slice directions, and coordinate systems as differentiating factors for vision components of VLMs, and the use of anatomical, directional, and relational terminology as factors for the language components. We then demonstrate that visual and textual prompting systems such as labels, bounding boxes, and mask overlays have varying effects on the spatial grounding ability of VLMs. To enable measurement and reproducibility, we introduce MIS-Ground, a benchmark that comprehensively tests a VLM for vulnerabilities against specific modes of Medical Image Spatial Grounding. We release MIS-Ground to the public at github.com/asy51/mis-ground. In addition, we present MIS-SemSam, a low-cost, inference-time, and model-agnostic optimization of VLMs that improves their spatial grounding ability with the use of Semantic Sampling. We find that MIS-SemSam improves the accuracy of Qwen3-VL-32B on MIS-Ground by 13.06%.

cs.CV↗
arXiv2026

A Discordance-Aware Multimodal Framework with Multi-Agent Clinical Reasoning

Knee osteoarthritis frequently exhibits discordance between structural damage observed in imaging and patient-reported symptoms such as pain. This mismatch complicates clinical interpretation and patient stratification and remains insufficiently modeled in existing decision support systems. We propose a discordance aware multimodal framework that combines machine learning prediction models with a tool grounded multi agent reasoning system. Using baseline data from the FNIH Osteoarthritis Biomarkers Consortium, we trained multimodal models to predict two progression tasks, joint space loss only progression versus non progression, and pain only progression versus non progression. The predictive system integrates three modality specific experts: a CatBoost tabular model using demographic, radiographic, MRI-derived scalar, and biomarker features; MRI image embeddings extracted using a ResNet18 backbone; and Xray embeddings derived from the same architecture. Expert predictions are fused using a stacking ensemble. Residual based models estimate expected pain from structural features, enabling the computation of a pain structure discordance score between observed and expected symptoms. A multi-agent reasoning layer interprets these signals to assign clinically interpretable OA phenotypes and generate phenotype specific management recommendations.

cs.LG↗
arXiv2026

Comparing causal estimands from sequential nested versus single point target trials: A simulation study

Sequential nested trial (SNT) emulation is a powerful approach for maximizing precision and avoiding time-related biases. However, there exists little discussion about the implied causal estimands in comparison to a real-world single point trial. We used Monte Carlo simulation to compare treatment effect estimates from an SNT emulation that re-indexed patients annually and a SNT emulation with a treatment decision design to the estimates from a single point trial. We generated 5,000 cohorts of 5,000 people with 3 years of follow-up. For the single point trial, patients were randomized to initiate or not initiate treatment at Visit 1. For the SNT emulations, simulated patients could contribute up to two index dates. When disease severity did not modify the treatment effect, both SNT approaches returned treatment effect estimates identical to the single point trial. In the presence of treatment effect modification by disease severity, both SNT approaches returned treatment effect estimates that diverged from the single point trial even after confounding-adjustment. These findings underscore the difficulties of interpreting causal estimands from a SNT emulation: the target population does not correspond to a single time point trial. Such implications are important for communicating study results for evidence-based decision-making.

stat.AP↗
arXiv2025

Limit theorems under nonlinear expectations dominated by sublinear expectations

In this paper, we obtain a new estimate for uniform integrability under sublinear expectations. Based on this, we establish the limit theorems under nonlinear expectations dominated by sublinear expectations through tightness, and the limit distributions can be completely nonlinear. Finally, we study the limit theorem in a special case, where the limit distribution satisfies positive homogeneity.

math.PR↗
arXiv2025

Towards Quantum Tensor Decomposition in Biomedical Applications

Tensor decomposition has emerged as a powerful framework for feature extraction in multi-modal biomedical data. In this review, we present a comprehensive analysis of tensor decomposition methods such as Tucker, CANDECOMP/PARAFAC, spiked tensor decomposition, etc. and their diverse applications across biomedical domains such as imaging, multi-omics, and spatial transcriptomics. To systematically investigate the literature, we applied a topic modeling-based approach that identifies and groups distinct thematic sub-areas in biomedicine where tensor decomposition has been used, thereby revealing key trends and research directions. We evaluated challenges related to the scalability of latent spaces along with obtaining the optimal rank of the tensor, which often hinder the extraction of meaningful features from increasingly large and complex datasets. Additionally, we discuss recent advances in quantum algorithms for tensor decomposition, exploring how quantum computing can be leveraged to address these challenges. Our study includes a preliminary resource estimation analysis for quantum computing platforms and examines the feasibility of implementing quantum-enhanced tensor decomposition methods on near-term quantum devices. Collectively, this review not only synthesizes current applications and challenges of tensor decomposition in biomedical analyses but also outlines promising quantum computing strategies to enhance its impact on deriving actionable insights from complex biomedical data.

q-bio.QM↗
arXiv2024

Detection-Guided Deep Learning-Based Model with Spatial Regularization for Lung Nodule Segmentation

Lung cancer ranks as one of the leading causes of cancer diagnosis and is the foremost cause of cancer-related mortality worldwide. The early detection of lung nodules plays a pivotal role in improving outcomes for patients, as it enables timely and effective treatment interventions. The segmentation of lung nodules plays a critical role in aiding physicians in distinguishing between malignant and benign lesions. However, this task remains challenging due to the substantial variation in the shapes and sizes of lung nodules, and their frequent proximity to lung tissues, which complicates clear delineation. In this study, we introduce a novel model for segmenting lung nodules in computed tomography (CT) images, leveraging a deep learning framework that integrates segmentation and classification processes. This model is distinguished by its use of feature combination blocks, which facilitate the sharing of information between the segmentation and classification components. Additionally, we employ the classification outcomes as priors to refine the size estimation of the predicted nodules, integrating these with a spatial regularization technique to enhance precision. Furthermore, recognizing the challenges posed by limited training datasets, we have developed an optimal transfer learning strategy that freezes certain layers to further improve performance. The results show that our proposed model can capture the target nodules more accurately compared to other commonly used models. By applying transfer learning, the performance can be further improved, achieving a sensitivity score of 0.885 and a Dice score of 0.814.

cs.CV↗
arXiv2024

Relationship between stochastic maximum principle and dynamic programming principle under convex expectation

In this paper, we study the relationship between maximum principle (MP) and dynamic programming principle (DPP) for forward-backward control system under consistent convex expectation dominated by G-expectation. Under the smooth assumptions for the value function, we get the relationship between MP and DPP under a reference probability by establishing a useful estimate. If the value function is not smooth, then we obtain the first-order sub-jet and super-jet of the value function at any t. However, the processing method in this case is much more difficult than that when t equals 0.

math.OC↗
arXiv2024

Maximum principle for stochastic optimal control problem under convex expectation

In this paper, we study a stochastic optimal control problem under a type of consistent convex expectation dominated by G-expectation. By the separation theorem for convex sets, we get the representation theorems for this convex expectation and conditional convex expectation. Based on these results, we obtain the variational equation for cost functional by weak convergence and discretization methods. Furthermore, we establish the maximum principle which is sufficient under usual convex assumptions. Finally, we study the linear quadratic control problem by using the obtained maximum principle.

math.OC↗
arXiv2024

Novel adaptation of video segmentation to 3D MRI: efficient zero-shot knee segmentation with SAM2

Intelligent medical image segmentation methods are rapidly evolving and being increasingly applied, yet they face the challenge of domain transfer, where algorithm performance degrades due to different data distributions between source and target domains. To address this, we introduce a method for zero-shot, single-prompt segmentation of 3D knee MRI by adapting Segment Anything Model 2 (SAM2), a general-purpose segmentation model designed to accept prompts and retain memory across frames of a video. By treating slices from 3D medical volumes as individual video frames, we leverage SAM2's advanced capabilities to generate motion- and spatially-aware predictions. We demonstrate that SAM2 can efficiently perform segmentation tasks in a zero-shot manner with no additional training or fine-tuning, accurately delineating structures in knee MRI scans using only a single prompt. Our experiments on the Osteoarthritis Initiative Zuse Institute Berlin (OAI-ZIB) dataset reveal that SAM2 achieves high accuracy on 3D knee bone segmentation, with a testing Dice similarity coefficient of 0.9643 on tibia. We also present results generated using different SAM2 model sizes, different prompt schemes, as well as comparative results from the SAM1 model deployed on the same dataset. This breakthrough has the potential to revolutionize medical image analysis by providing a scalable, cost-effective solution for automated segmentation, paving the way for broader clinical applications and streamlined workflows.

cs.CV↗
arXiv2023

Self-supervised Deep Unrolled Reconstruction Using Regularization by Denoising

Deep learning methods have been successfully used in various computer vision tasks. Inspired by that success, deep learning has been explored in magnetic resonance imaging (MRI) reconstruction. In particular, integrating deep learning and model-based optimization methods has shown considerable advantages. However, a large amount of labeled training data is typically needed for high reconstruction quality, which is challenging for some MRI applications. In this paper, we propose a novel reconstruction method, named DURED-Net, that enables interpretable self-supervised learning for MR image reconstruction by combining a self-supervised denoising network and a plug-and-play method. We aim to boost the reconstruction performance of Noise2Noise in MR reconstruction by adding an explicit prior that utilizes imaging physics. Specifically, the leverage of a denoising network for MRI reconstruction is achieved using Regularization by Denoising (RED). Experiment results demonstrate that the proposed method requires a reduced amount of training data to achieve high reconstruction quality among the state-of-art of MR reconstruction utilizing the Noise2Noise method.

eess.IV↗
arXiv2023

A Geometric Flow Approach for Segmentation of Images with Inhomongeneous Intensity and Missing Boundaries

Image segmentation is a complex mathematical problem, especially for images that contain intensity inhomogeneity and tightly packed objects with missing boundaries in between. For instance, Magnetic Resonance (MR) muscle images often contain both of these issues, making muscle segmentation especially difficult. In this paper we propose a novel intensity correction and a semi-automatic active contour based segmentation approach. The approach uses a geometric flow that incorporates a reproducing kernel Hilbert space (RKHS) edge detector and a geodesic distance penalty term from a set of markers and anti-markers. We test the proposed scheme on MR muscle segmentation and compare with some state of the art methods. To help deal with the intensity inhomogeneity in this particular kind of image, a new approach to estimate the bias field using a fat fraction image, called Prior Bias-Corrected Fuzzy C-means (PBCFCM), is introduced. Numerical experiments show that the proposed scheme leads to significantly better results than compared ones. The average dice values of the proposed method are 92.5%, 85.3%, 85.3% for quadriceps, hamstrings and other muscle groups while other approaches are at least 10% worse.

cs.CV↗
arXiv2022

Forward-backward stochastic differential equations driven by G-Brownian motion under weakly coupling condition

In this paper, we obtain the existence and uniqueness theorem of $L^{p}$-solution for coupled forward-backward stochastic differential equations driven by G-Brownian motion (G-FBSDEs) with arbitrary $T$ under weakly coupling condition. Specially, the result for $p\in(1,2)$ is completely different from the one for $p\geq2$. Furthermore, by considering the dual linear FBSDE under a suitable reference probability, we establish the comparison theorem for G-FBSDEs under weakly coupling condition.

math.PR↗
arXiv2022

Dynamic programming principle for stochastic optimal control problem under degenerate G-expectation

In this paper, we study a stochastic optimal control problem under degenerate G-expectation. By using implied partition method, we show that the approximation result for admissible controls still hold. Based on this result, we prove that the value function is deterministic, and obtain the dynamic programming principle. Furthermore, we prove that the value function is the unique viscosity solution to the related HJB equation under degenerate case.

math.OC↗
arXiv2022

Relationship between MP and DPP for stochastic recursive optimal control problem under volatility uncertainty

In this paper, we study the relationship between maximum principle (MP) and dynamic programming principle (DPP) for stochastic recursive optimal control problem driven by $G$-Brownian motion. Under the smooth assumption for the value function, we obtain the connection between MP and DPP under a reference probability $P_{t,x}^{\ast}$. Within the framework of viscosity solution, we establish the relation between the first-order super-jet, sub-jet of the value function and the solution to the adjoint equation respectively.

math.OC↗
arXiv2022

G-capacity under degenerate case and its application

In this paper, we first find a type of viscosity solution of $G$-heat equation under degenerate case, and then obtain the related $G$-capacity $c(\{B_{T}\in A\})$ for any Borel set $A$. Furthermore, we prove that $I_{A}(B_{T})$ has no quasi-continuous version when it is not a constant function.

math.AP↗
arXiv2022

Maximum principle for discrete-time stochastic optimal control problem under distribution uncertainty

In this paper, we study a discrete-time stochastic optimal control problem under distribution uncertainty with convex control domain. By weak convergence method and Sion's minimax theorem, we obtain the variational inequality for cost functional under a reference probability $P^{\ast}$. Moreover, under the square integrability condition for noise and control, we establish the discrete-time stochastic maximum principle under $P^{\ast}$. Finally, we introduce a backward algorithm to calculate the reference probability $P^{\ast}$ and the optimal control $u^{\ast}$.

math.OC↗
arXiv2022

Quantifying Wetting Dynamics with Triboelectrification

Wetting is often perceived as an intrinsic surface property of materials, but determining its evolution is complicated by its complex dependence on roughness across the scales. The Wenzel state, where liquids have intimate contact with the rough substrate, and the Cassie-Baxter state, where liquids sit onto air pockets formed between asperities, are only two states among the plethora of wetting behaviors. Furthermore, transitions from the Cassie-Baxter to the Wenzel state dictate completely different surface performance, such as anti-contamination, anti-icing, drag reduction etc.; however, little is known about how transition occurs during time between the several wetting modes. In this paper, we show that wetting dynamics can be accurately quantified and tracked using solid-liquid triboelectrification. Theoretical underpinning reveals how surface micro-/nano-geometries regulate stability/infiltration, also demonstrating the generality of our theoretical approach in understanding wetting transitions.

cond-mat.soft↗