Source author record

Xiuming Zhang

Xiuming Zhang appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Computer Vision gr-qc hep-th Graphics eess.IV Machine Learning

Catalog footprint

What is connected

8works

6topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

A Breast Vision Pathology Foundation Model for Real-world Clinical Utility

Pathology foundation models have shown strong retrospective performance, but whether such systems can support clinically relevant use remains unclear. This challenge is particularly important in breast cancer, where pathological assessment serves as the gold standard for diagnosis and guides treatment planning, surgical decision-making and risk stratification across pre-, intra- and post-operative stages. Here we present \textbf{BRAVE}, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast whole-slide images from 32 sources across Asia, Europe and North America. We assessed BRAVE across 34 tasks in 82 cohorts spanning pre-operative biopsy, intra-operative frozen section and post-operative resection, using an evidence chain comprising retrospective benchmarking, clinically challenging scenarios, workflow-oriented clinical impact simulations, prospective observational validation with the thresholds locked in the retrospective cohorts and crossover pathologist-AI interaction studies. Across these settings, BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine review, AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment. In prospective validation across three centres, BRAVE excluded 76.9% of negative biopsy cases (NPV 0.953) and 70.1% of negative frozen-section cases (NPV 0.973), and triaged 78.8% of post-operative subtyping cases as high-confidence clear-cut cases (NPV 1.000). In reader studies, AI assistance improved balanced accuracy from 88.5% to 95.1% (OR 3.14, P<0.001), with better efficiency, confidence and inter-rater agreement. BRAVE-derived scores also independently predicted disease-free survival (adjusted HR 4.79, P<0.001) and overall survival (adjusted HR 8.14, P<0.001).

preprint2022arXiv

Bone marrow sparing for cervical cancer radiotherapy on multimodality medical images

Cervical cancer threatens the health of women seriously. Radiotherapy is one of the main therapy methods but with high risk of acute hematologic toxicity. Delineating the bone marrow (BM) for sparing using computer tomography (CT) images to plan before radiotherapy can effectively avoid this risk. Comparing with magnetic resonance (MR) images, CT lacks the ability to express the activity of BM. Thus, in current clinical practice, medical practitioners manually delineate the BM on CT images by corresponding to MR images. However, the time?consuming delineating BM by hand cannot guarantee the accuracy due to the inconsistency of the CT-MR multimodal images. In this study, we propose a multimodal image oriented automatic registration method for pelvic BM sparing, which consists of three-dimensional bone point cloud reconstruction, a local spherical system iteration closest point registration for marking BM on CT images. Experiments on patient dataset reveal that our proposed method can enhance the multimodal image registration accuracy and efficiency for medical practitioners in sparing BM of cervical cancer radiotherapy. The method proposed in this contribution might also provide references for similar studies in other clinical application.

preprint2021arXiv

Neural Light Transport for Relighting and View Synthesis

The light transport (LT) of a scene describes how it appears under different lighting and viewing directions, and complete knowledge of a scene's LT enables the synthesis of novel views under arbitrary lighting. In this paper, we focus on image-based LT acquisition, primarily for human bodies within a light stage setup. We propose a semi-parametric approach to learn a neural representation of LT that is embedded in the space of a texture atlas of known geometric properties, and model all non-diffuse and global LT as residuals added to a physically-accurate diffuse base rendering. In particular, we show how to fuse previously seen observations of illuminants and views to synthesize a new image of the same scene under a desired lighting condition from a chosen viewpoint. This strategy allows the network to learn complex material effects (such as subsurface scattering) and global illumination, while guaranteeing the physical correctness of the diffuse LT (such as hard shadows). With this learned LT, one can relight the scene photorealistically with a directional light or an HDRI map, synthesize novel views with view-dependent effects, or do both simultaneously, all in a unified framework using a set of sparse, previously seen observations. Qualitative and quantitative experiments demonstrate that our neural LT (NLT) outperforms state-of-the-art solutions for relighting and view synthesis, without separate treatment for both problems that prior work requires.

preprint2020arXiv

Perspective Plane Program Induction from a Single Image

We study the inverse graphics problem of inferring a holistic representation for natural images. Given an input image, our goal is to induce a neuro-symbolic, program-like representation that jointly models camera poses, object locations, and global scene structures. Such high-level, holistic scene representations further facilitate low-level image manipulation tasks such as inpainting. We formulate this problem as jointly finding the camera pose and scene structure that best describe the input image. The benefits of such joint inference are two-fold: scene regularity serves as a new cue for perspective correction, and in turn, correct perspective correction leads to a simplified scene structure, similar to how the correct shape leads to the most regular texture in shape from texture. Our proposed framework, Perspective Plane Program Induction (P3I), combines search-based and gradient-based algorithms to efficiently solve the problem. P3I outperforms a set of baselines on a collection of Internet images, across tasks including camera pose estimation, global structure inference, and down-stream image manipulation tasks.

preprint2020arXiv

Portrait Shadow Manipulation

Casually-taken portrait photographs often suffer from unflattering lighting and shadowing because of suboptimal conditions in the environment. Aesthetic qualities such as the position and softness of shadows and the lighting ratio between the bright and dark parts of the face are frequently determined by the constraints of the environment rather than by the photographer. Professionals address this issue by adding light shaping tools such as scrims, bounce cards, and flashes. In this paper, we present a computational approach that gives casual photographers some of this control, thereby allowing poorly-lit portraits to be relit post-capture in a realistic and easily-controllable way. Our approach relies on a pair of neural networks---one to remove foreign shadows cast by external objects, and another to soften facial shadows cast by the features of the subject and to add a synthetic fill light to improve the lighting ratio. To train our first network we construct a dataset of real-world portraits wherein synthetic foreign shadows are rendered onto the face, and we show that our network learns to remove those unwanted shadows. To train our second network we use a dataset of Light Stage scans of human subjects to construct input/output pairs of input images harshly lit by a small light source, and variably softened and fill-lit output images of each face. We propose a way to explicitly encode facial symmetry and show that our dataset and training procedure enable the model to generalize to images taken in the wild. Together, these networks enable the realistic and aesthetically pleasing enhancement of shadows and lights in real-world portrait images

preprint2014arXiv

Effect of the Minimal Length on Bose-Einstein Condensation in the Relativistic Ideal Bose Gas

Based on the generalized uncertainty principle (GUP), the critical temperature and the Helmholtz free energy of Bose-Einstein condensation (BEC) in the relativistic ideal Bose gas are investigated. At the non-relativistic limit and the ultra-relativistic limit, we calculate the analytical form of the shifts of the critical temperature and the Helmholtz free energy caused by weak quantum gravitational effects. The exact numerical results of these shifts are obtained. Quantum gravity effects lift the critical temperature of BEC. By measuring the shift of the critical temperature, we can constrain the deformation parameter $β_0$. Furthermore, at lower densities, omitting quantum gravitational effects may lead to a metastable state while at sufficiently high densities, quantum gravitational effects tend to make BEC unstable. Using the numerical methods, the stable-unstable transition temperature is found.

preprint2012arXiv

Quantum gravity effects on compact star cores

Using the Tolman-Oppenheimer-Volkoff equation and the equation of state of zero temperature ultra-relativistic Fermi gas based on generalized uncertainty principle (GUP), the quantum gravitational effects on the cores of compact stars are discussed. Our results show that ${2m(r)}/ {r}$ varies with $r$. Quantum gravity plays an important role in the region $ r\sim 10^3 r_0$, where $r_0\sim β_0 l_p $, $l_p$ is the Planck length and $β_0$ is a dimensionless parameter accounting for quantum gravity effects. Furthermore, near the center of compact stars, we find that the metric components are $g_{tt}\sim r^4$ and $g_{rr}=[1-{r}^2/(6r_0^2)]^{-1}$. All these effects are different from those obtained from classical gravity. These results can be applied to neutron stars or denser ones like quark stars. The observed masses of neutron stars ($\leq 2M_\odot$) indicate that $β_0$ can not exceed $10^{37}$, not as good as the upper bound $β_0<10^{34}$ from simple electroweak consideration. This means that incorporating either quantum gravity effects or nuclear interactions, one obtains almost the same mass limits of neutron stars.

preprint2010arXiv

Quantum gravity effects on statistics and compact star configurations

The thermodynamics of classical and quantum ideal gases based on the Generalized uncertainty principle (GUP) are investigated. At low temperatures, we calculate corrections to the energy and entropy. The equations of state receive small modifications. We study a system comprised of a zero temperature ultra-relativistic Fermi gas. It turns out that at low Fermi energy $\varepsilon_F$, the degenerate pressure and energy are lifted. The Chandrasekhar limit receives a small positive correction. We discuss the applications on configurations of compact stars. As $\varepsilon_F$ increases, the radius, total number of fermions and mass first reach their nonvanishing minima and then diverge. Beyond a critical Fermi energy, the radius of a compact star becomes smaller than the Schwarzschild one. The stability of the configurations is also addressed. We find that beyond another critical value of the Fermi energy, the configurations are stable. At large radius, the increment of the degenerate pressure is accelerated at a rate proportional to the radius.