arXiv subjects

Shuhao Wang

Publications and source records attributed to Shuhao Wang.

11 recordsLinked to original sources

arXiv2026

Computational Pathology in the Era of Emerging Foundation and Agentic AI -- International Expert Perspectives on Clinical Integration and Translational Readiness

Recent breakthroughs in artificial intelligence through foundation models and agents have accelerated the evolution of computational pathology. Demonstrated performance gains reported across academia in benchmarking datasets in predictive tasks such as diagnosis, prognosis, and treatment response have ignited substantial enthusiasm for clinical application. Despite this development momentum, real world adoption has lagged, as implementation faces economic, technical, and administrative challenges. Beyond existing discussions of technical architectures and comparative performance, this review considers how these emerging AI systems can be responsibly integrated into medical practice by connecting deployable clinical relevance with downstream analytical capabilities and their technical maturity, operational readiness, and economic and regulatory context. Drawing on perspectives from an international group, we provide a practical assessment of current capabilities and barriers to adoption in patient care settings.

cs.CE↗

arXiv2024

Polarization-entangled photon pairs generation from a single lithium niobate waveguide with single poling period

Polarization-entangled photon pairs are essential sources for photonic quantum information processing. However, generating entangled photon pairs with large detuning via spontaneous parametric down-conversion (SPDC) often requires complex configurations to compensate for phase matching. Here, we propose a simple and efficient scheme to generate polarization-entangled photon pairs based on type-0 SPDC in a thin-film lithium niobate waveguide with a single poling period. By utilizing the strong dispersion engineering capabilities of thin-film waveguides, we can achieve both degenerate and highly detuned entangled photon pairs. Furthermore, we demonstrate on-chip temporal compensation using an integrated waveguide structure. Our approach offers a compact and scalable solution for integrated quantum photonic circuits.

physics.optics↗

arXiv2024

CAMEL2: Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio

Histopathology image analysis plays a crucial role in cancer diagnosis. However, training a clinically applicable segmentation algorithm requires pathologists to engage in labour-intensive labelling. In contrast, weakly supervised learning methods, which only require coarse-grained labels at the image level, can significantly reduce the labeling efforts. Unfortunately, while these methods perform reasonably well in slide-level prediction, their ability to locate cancerous regions, which is essential for many clinical applications, remains unsatisfactory. Previously, we proposed CAMEL, which achieves comparable results to those of fully supervised baselines in pixel-level segmentation. However, CAMEL requires 1,280x1,280 image-level binary annotations for positive WSIs. Here, we present CAMEL2, by introducing a threshold of the cancerous ratio for positive bags, it allows us to better utilize the information, consequently enabling us to scale up the image-level setting from 1,280x1,280 to 5,120x5,120 while maintaining the accuracy. Our results with various datasets, demonstrate that CAMEL2, with the help of 5,120x5,120 image-level binary annotations, which are easy to annotate, achieves comparable performance to that of a fully supervised baseline in both instance- and slide-level classifications.

cs.CV↗

arXiv2022

Automated Scoring System of HER2 in Pathological Images under the Microscope

Breast cancer is the most common cancer among women worldwide. The human epidermal growth factor receptor 2 (HER2) with immunohistochemical (IHC) is widely used for pathological evaluation to provide the appropriate therapy for patients with breast cancer. However, the deficiency of pathologists and subjective and susceptible to inter-observer variation of visual diagnosis are the main challenges. Recently, with the rapid development of artificial intelligence (AI) in disease diagnosis, several automated HER2 scoring methods using traditional computer vision or machine learning methods indicate the improvement of the HER2 diagnostic accuracy, but the unreasonable interpretation in pathology, as well as the expensive and ethical issues for annotation, make these methods still have a long way to deploy in hospitals to ease pathologists' burden in real. In this paper, we propose a HER2 automated scoring system that strictly follows the HER2 scoring guidelines simulating the real workflow of HER2 scores diagnosis by pathologists. Unlike the previous work, our method considers the positive control of HER2 to make sure the assay performance for each slide, eliminating work for repeated comparison between the current field of view (FOV) and positive control FOV, especially for the borderline cases. Besides, for each selected FOV under the microscope, our system provides real-time HER2 scores analysis and visualizations of the membrane staining intensity and completeness corresponding with the cell classifications. Our rigorous workflow along with the flexible interactive adjustion in demand substantially assists pathologists to finish the HER2 diagnosis faster and improves the robustness and accuracy. The proposed system will be embedded in our Thorough Eye platform for deployment in hospitals.

q-bio.QM↗

arXiv2019

CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation

Histopathology image analysis plays a critical role in cancer diagnosis and treatment. To automatically segment the cancerous regions, fully supervised segmentation algorithms require labor-intensive and time-consuming labeling at the pixel level. In this research, we propose CAMEL, a weakly supervised learning framework for histopathology image segmentation using only image-level labels. Using multiple instance learning (MIL)-based label enrichment, CAMEL splits the image into latticed instances and automatically generates instance-level labels. After label enrichment, the instance-level labels are further assigned to the corresponding pixels, producing the approximate pixel-level labels and making fully supervised training of segmentation models possible. CAMEL achieves comparable performance with the fully supervised approaches in both instance-level classification and pixel-level segmentation on CAMELYON16 and a colorectal adenoma dataset. Moreover, the generality of the automatic labeling methodology may benefit future weakly supervised learning studies for histopathology image analysis.

eess.IV↗

arXiv2015

Lower bound of local quantum uncertainty for high-dimensional bipartite quantum systems

Quantum correlations are of fundamental importance in quantum phenomena and quantum information processing studies. The measure of quantum correlations is one central issue. The recently proposed measure of quantum correlations, the local quantum uncertainty (LQU), satisfies the full physical requirements of a measure of quantum correlations. In this work, by using operator relaxation, a closed form lower bound of the LQU for arbitrary-dimensional bipartite quantum states is derived. We have compared the lower bound and the optimized LQU for several typical quantum states.

quant-ph↗

arXiv2015

Quantum correlations in qutrit-qutrit systems under local quantum noise channels

Due to decoherence, realistic quantum systems inevitably interact with the environment when quantum information is processed, which causes the loss of quantum properties. As a fundamental issue of quantum properties, quantum correlations have attracted a lot of interests in recent years. Because of the importance of high dimensional systems in quantum information, in this work, we study the quantum correlations affected by the Markovian environment by considering the quantum correlations of qutrit-qutrit quantum systems measured by the negativity and the geometric discord. The local noise channels covered in this work includes dephasing, trit-flip, trit-phase-flip, and depolarising channels. We have also investigated the cases where the local decoherence channels of two sides are identical and non-identical.

quant-ph↗

arXiv2014

Enhancement of quantum correlations between two particles under decoherence in finite temperature environment

Enhancing the quantum correlations in realistic quantum systems interacting with the environment of finite temperature is an important subject in quantum information processing. In this paper, we use weak measurement and measurement reversal to enhance the quantum correlations in a quantum system consisting of two particles. The transitions of the quantum correlations measured by the local quantum uncertainty of qubit-qubit and qutrit-qutrit quantum systems under generalized amplitude damping channels are investigated. We show that, after the weak measurement and measurement reversal, the joint system shows more robustness against decoherence.

quant-ph↗

arXiv2013

Entanglement classification of 2 X 2 X 2 X d quantum systems via the ranks of the multiple coefficient matrices

The coefficient matrix is an efficient tool in entanglement classification under stochastic local operation and classical communication. In this work, we take all the ranks of the coefficient matrices into account in the method of entanglement classification, and give the entanglement classification procedure for arbitrary-dimensional multipartite pure states under stochastic local operation and classical communication. As a main application, we study the entanglement classification for quantum systems in the Hilbert space ${\cal H} = \mathbb{C}^2 \otimes \mathbb{C}^2 \otimes \mathbb{C}^2 \otimes \mathbb{C}^d$ in terms of the ranks of the coefficient matrices.

quant-ph↗

arXiv2013

Quantifying entanglement of arbitrary-dimensional multipartite pure states in terms of the singular values of coefficient matrices

The entanglement quantification and classification of multipartite quantum states are two important research fields in quantum information. In this work, we study the entanglement of arbitrary-dimensional multipartite pure states by looking at the averaged partial entropies of various bipartite partitions of the system, namely, the so-called Manhattan distance ($l_1$ norm) of averaged partial entropies (MAPE), and it is proved to be an entanglement measure for pure states. We connected the MAPE with the coefficient matrices, which are important tools in entanglement classification and reexpressed the MAPE for arbitrary-dimensional multipartite pure states by the nonzero singular values of the coefficient matrices. The entanglement properties of the $n$-qubit Dicke states, arbitrary-dimensional Greenberger-Horne-Zeilinger states, and $D_3^n$ states are investigated in terms of the MAPE, and the relation between the rank of the coefficient matrix and the degree of entanglement is demonstrated for symmetric states by two examples.

quant-ph↗

arXiv2013

Classification of arbitrary-dimensional multipartite pure states under stochastic local operations and classical communication using the rank of coefficient matrix

We study multipartite entanglement under stochastic local operations and classical communication (SLOCC) and propose the entanglement classification under SLOCC for arbitrary-dimensional multipartite ($n$-qudit) pure states via the rank of coefficient matrix, together with the permutation of qudits. The ranks of the coefficient matrices have been proved to be entanglement monotones. The entanglement classification of the $2 \otimes 2 \otimes 2 \otimes 4$ system is discussed in terms of the generalized method, and 22 different SLOCC families are found.

quant-ph↗