Search

Due to the high noise caused by solar background radiation, the existing satellite-based free-space quantum key distribution (QKD) experiments are mainly carried out at night, hindering the establishment of a practical all-day real-time global-scale quantum network. Given that the 3-5 {\mu}m mid-infrared (MIR) band has extremely low solar background radiation and strong scattering resistance, it is one of the ideal bands for free-space quantum communication. Here, firstly, we report on the preparation of a high-quality MIR (3370 nm) and telecom band (1555 nm) two-color polarization-entangled photon source, then we use this source to realize a principle QKD based on free-space and fiber hybrid channels in a laboratory. The theoretical analysis clearly shows that a long-distance QKD over 500 km of free-space and 96 km of fiber hybrid channels can be reached simultaneously. This work represents a significant step toward developing all-day global-scale quantum communication networks., Comment: 24 pages, 9 figures

Polarimetric imaging, a technique that captures the invisible polarization-related properties of given materials, has broad applications from fundamental physics to advanced fields such as target recognition, stress detection, biomedical diagnosis and remote sensing. The introduction of quantum sources into classical imaging systems has demonstrated distinct advantages, yet few studies have explored their combination with polarimetric imaging. In this study, we present a quantum polarimetric imaging system that integrates polarization-entangled photon pairs into a polarizer-sample-compensator-analyzer (PSRA)-type polarimeter. Our system visualizes the birefringence properties of a periodical-distributed anisotropic material under decreasing illumination levels and diverse disturbing light sources. Compared to the classical system, the quantum approach reveals the superior sensitivity and robustness in low-light conditions, particularly useful in biomedical studies where the low illumination and non-destructive detection are urgently needed. The study also highlights the nonlocality of entangled photons in birefringence measurement, indicating the potential of quantum polarimetric system in the remote sensing domain.

We tackle the novel class discovery in point cloud segmentation, which discovers novel classes based on the semantic knowledge of seen classes. Existing work proposes an online point-wise clustering method with a simplified equal class-size constraint on the novel classes to avoid degenerate solutions. However, the inherent imbalanced distribution of novel classes in point clouds typically violates the equal class-size constraint. Moreover, point-wise clustering ignores the rich spatial context information of objects, which results in less expressive representation for semantic segmentation. To address the above challenges, we propose a novel self-labeling strategy that adaptively generates high-quality pseudo-labels for imbalanced classes during model training. In addition, we develop a dual-level representation that incorporates regional consistency into the point-level classifier learning, reducing noise in generated segmentation. Finally, we conduct extensive experiments on two widely used datasets, SemanticKITTI and SemanticPOSS, and the results show our method outperforms the state of the art by a large margin., Comment: Accepted by ECCV2024

Recent advancements in multimodal foundation models have showcased impressive capabilities in understanding and reasoning with visual and textual information. Adapting these foundation models trained for general usage to specialized domains like biomedicine requires large-scale domain-specific instruction datasets. While existing works have explored curating such datasets automatically, the resultant datasets are not explicitly aligned with domain expertise. In this work, we propose a data-centric framework, Biomedical Visual Instruction Tuning with Clinician Preference Alignment (BioMed-VITAL), that incorporates clinician preferences into both stages of generating and selecting instruction data for tuning biomedical multimodal foundation models. First, during the generation stage, we prompt the GPT-4V generator with a diverse set of clinician-selected demonstrations for preference-aligned data candidate generation. Then, during the selection phase, we train a separate selection model, which explicitly distills clinician and policy-guided model preferences into a rating function to select high-quality data for medical instruction tuning. Results show that the model tuned with the instruction-following data from our method demonstrates a significant improvement in open visual chat (18.5% relatively) and medical VQA (win rate up to 81.73%). Our instruction-following data and models are available at BioMed-VITAL.github.io.

Echocardiography segmentation for cardiac analysis is time-consuming and resource-intensive due to the variability in image quality and the necessity to process scans from various standard views. While current automated segmentation methods in echocardiography show promising performance, they are trained on specific scan views to analyze corresponding data. However, this solution has a limitation as the number of required models increases with the number of standard views. To address this, in this paper, we present a prompt-driven universal method for view-agnostic echocardiography analysis. Considering the domain shift between standard views, we first introduce a method called prompt matching, aimed at learning prompts specific to different views by matching prompts and querying input embeddings using a pre-trained vision model. Then, we utilized a pre-trained medical language model to align textual information with pixel data for accurate segmentation. Extensive experiments on three standard views showed that our approach significantly outperforms the state-of-the-art universal methods and achieves comparable or even better performances over the segmentation model trained and tested on same views.

Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant progress in recent years, most existing methods focus on uniformly distributed datasets, significantly limiting the practical applicability of their methods. In this paper, we propose a more practical problem setting named deep imbalanced clustering, where the underlying classes exhibit an imbalance distribution. To address this challenge, we introduce a novel optimal transport-based pseudo-label learning framework. Our framework formulates pseudo-label generation as a Semantic-regularized Progressive Partial Optimal Transport (SP$^2$OT) problem, which progressively transports each sample to imbalanced clusters under several prior distribution and semantic relation constraints, thus generating high-quality and imbalance-aware pseudo-labels. To solve SP$^2$OT, we develop a Majorization-Minimization-based optimization algorithm. To be more precise, we employ the strategy of majorization to reformulate the SP$^2$OT problem into a Progressive Partial Optimal Transport problem, which can be transformed into an unbalanced optimal transport problem with augmented constraints and can be solved efficiently by a fast matrix scaling algorithm. Experiments on various datasets, including a human-curated long-tailed CIFAR100, challenging ImageNet-R, and large-scale subsets of fine-grained iNaturalist2018 datasets, demonstrate the superiority of our method., Comment: under review. arXiv admin note: substantial text overlap with arXiv:2401.09266

Accurate myocardium segmentation across all phases in one cardiac cycle in cine cardiac magnetic resonance (CMR) scans is crucial for comprehensively cardiac function analysis. Despite advancements in deep learning (DL) for automatic cine CMR segmentation, generalizability on unseen data remains a significant challenge. Recently, the segment-anything-model (SAM) has been invented as a segmentation foundation model, known for its accurate segmentation and more importantly, zero-shot generalization. SAM was trained on two-dimensional (2D) natural images; to adapt it for comprehensive cine CMR segmentation, we propose cineCMR-SAM which incorporates both temporal and spatial information through a modified model architecture. Compared to other state-of-the-art (SOTA) methods, our model achieved superior data-specific model segmentation accuracy on the STACOM2011 when fine-tuned on this dataset and demonstrated superior zero-shot generalization on two other large public datasets (ACDC and M&Ms) unseen during fine-tuning. Additionally, we introduced a text prompt feature in cineCMR-SAM to specify the view type of input slices (short-axis or long-axis), enhancing performance across all view types., Comment: 10 pages, 3 figures

Alzheimer's Disease (AD) is a neurodegenerative condition characterized by diverse progression rates among individuals, with changes in cortical thickness (CTh) closely linked to its progression. Accurately forecasting CTh trajectories can significantly enhance early diagnosis and intervention strategies, providing timely care. However, the longitudinal data essential for these studies often suffer from temporal sparsity and incompleteness, presenting substantial challenges in modeling the disease's progression accurately. Existing methods are limited, focusing primarily on datasets without missing entries or requiring predefined assumptions about CTh progression. To overcome these obstacles, we propose a conditional score-based diffusion model specifically designed to generate CTh trajectories with the given baseline information, such as age, sex, and initial diagnosis. Our conditional diffusion model utilizes all available data during the training phase to make predictions based solely on baseline information during inference without needing prior history about CTh progression. The prediction accuracy of the proposed CTh prediction pipeline using a conditional score-based model was compared for sub-groups consisting of cognitively normal, mild cognitive impairment, and AD subjects. The Bland-Altman analysis shows our diffusion-based prediction model has a near-zero bias with narrow 95% confidential interval compared to the ground-truth CTh in 6-36 months. In addition, our conditional diffusion model has a stochastic generative nature, therefore, we demonstrated an uncertainty analysis of patient-specific CTh prediction through multiple realizations.

Four wave mixing (FWM) is an important way to generate supercontinuum and frequency combs in the mid-infrared band. Here, we obtain simultaneous synthetic FWM in the visible and mid-infrared bands by cascading quadratic nonlinear processes in a periodically poled lithium niobate crystal (PPLN), which has a 110dB(at 3000nm) higher conversion efficiency than the FWM directly generated by third-order susceptibilities in bulk PPLN crystals. A general model of this process is developed that is in full agreement with the experimental verifications. The frequency difference between the new frequency components can be freely tuned by changing the frequency difference of the dual pump lasers. Furthermore, by increasing the conversion bandwidth and efficiency of the cascaded processes, it is feasible to generate frequency combs in three bands the visible, near-infrared and mid-infrared bands simultaneously through high-order cascaded processes. This work opens up a new avenue toward free-tuning multiband frequency comb generation with multi-octaves frequency spanning, which will have significant applications in fields such as mid-infrared gas sensing, lidar and precision spectroscopy.

Data scarcity and privacy concerns limit the availability of high-quality medical images for public use, which can be mitigated through medical image synthesis. However, current medical image synthesis methods often struggle to accurately capture the complexity of detailed anatomical structures and pathological conditions. To address these challenges, we propose a novel medical image synthesis model that leverages fine-grained image-text alignment and anatomy-pathology prompts to generate highly detailed and accurate synthetic medical images. Our method integrates advanced natural language processing techniques with image generative modeling, enabling precise alignment between descriptive text prompts and the synthesized images' anatomical and pathological details. The proposed approach consists of two key components: an anatomy-pathology prompting module and a fine-grained alignment-based synthesis module. The anatomy-pathology prompting module automatically generates descriptive prompts for high-quality medical images. To further synthesize high-quality medical images from the generated prompts, the fine-grained alignment-based synthesis module pre-defines a visual codebook for the radiology dataset and performs fine-grained alignment between the codebook and generated prompts to obtain key patches as visual clues, facilitating accurate image synthesis. We validate the superiority of our method through experiments on public chest X-ray datasets and demonstrate that our synthetic images preserve accurate semantic information, making them valuable for various medical applications., Comment: 5 figures

An ellipsometer is a vital precision tool used for measuring optical parameters with wide applications in many fields, including accurate measurements in film thickness, optical constants, structural profiles, etc. However, the precise measurement of photosensitive materials meets huge obstacles because of the excessive input photons, therefore the requirement of enhancing detection accuracy under low incident light intensity is an essential topic in the precision measurement. In this work, by combining a polarization-entangled photon source with a classical transmission-type ellipsometer, the quantum ellipsometer with the PSA (Polarizer-Sample-Analyzer) and the Senarmount method is constructed firstly to measure the phase retardation of the birefringent materials. The experimental results show that the accuracy can reach to nanometer scale at extremely low input intensity, and the stability are within 1% for all specimens tested with a compensator involved. Our work paves the way for precision measurement at low incident light intensity, with potential applications in measuring photosensitive materials, active-biological samples and other remote monitoring scenarios., Comment: 13 pages, 5 figures. This work has been submitted for possible publication

Inducing and controlling electrostatic barriers in two-dimensional (2D) quantum materials has shown extraordinary promise to enable control of charge carriers, and is key for the realization of nanoscale electronic and optoelectronic devices1-10. Because of their atomically thin nature, the 2D materials have a congenital advantage to construct the thinnest possible p-n junctions1,3,7,9,10. To realize the ultimate functional unit for future nanoscale devices, creating atomically wide electrostatic barriers embedded in 2D materials is desired and remains an extremely challenge. Here we report the creation and manipulation of atomically wide electrostatic barriers embedded in graphene WSe2 heterostructures. By using a STM tip, we demonstrate the ability to generate a one-dimensional (1D) atomically wide boundary between 1T-WSe2 domains and continuously tune positions of the boundary because of ferroelasticity of the 1T-WSe2. Our experiment indicates that the 1D boundary introduces atomically wide electrostatic barriers in graphene above it. Then the 1D electrostatic barrier changes a single graphene WSe2 heterostructure quantum dot from a relativistic artificial atom to a relativistic artificial molecule.

Participant recruitment based on unstructured medical texts such as clinical notes and radiology reports has been a challenging yet important task for the cohort establishment in clinical research. Recently, Large Language Models (LLMs) such as ChatGPT have achieved tremendous success in various downstream tasks thanks to their promising performance in language understanding, inference, and generation. It is then natural to test their feasibility in solving the cohort recruitment task, which involves the classification of a given paragraph of medical text into disease label(s). However, when applied to knowledge-intensive problem settings such as medical text classification, where the LLMs are expected to understand the decision made by human experts and accurately identify the implied disease labels, the LLMs show a mediocre performance. A possible explanation is that, by only using the medical text, the LLMs neglect to use the rich context of additional information that languages afford. To this end, we propose to use a knowledge graph as auxiliary information to guide the LLMs in making predictions. Moreover, to further boost the LLMs adapt to the problem setting, we apply a chain-of-thought (CoT) sample selection strategy enhanced by reinforcement learning, which selects a set of CoT samples given each individual medical report. Experimental results and various ablation studies show that our few-shot learning method achieves satisfactory performance compared with fine-tuning strategies and gains superb advantages when the available data is limited. The code and sample dataset of the proposed CohortGPT model is available at: https://anonymous.4open.science/r/CohortGPT-4872/, Comment: 16 pages, 10 figures

Alzheimer's disease (AD) is a common form of dementia that severely impacts patient health. As AD impairs the patient's language understanding and expression ability, the speech of AD patients can serve as an indicator of this disease. This study investigates various methods for detecting AD using patients' speech and transcripts data from the DementiaBank Pitt database. The proposed approach involves pre-trained language models and Graph Neural Network (GNN) that constructs a graph from the speech transcript, and extracts features using GNN for AD detection. Data augmentation techniques, including synonym replacement, GPT-based augmenter, and so on, were used to address the small dataset size. Audio data was also introduced, and WavLM model was used to extract audio features. These features were then fused with text features using various methods. Finally, a contrastive learning approach was attempted by converting speech transcripts back to audio and using it for contrastive learning with the original audio. We conducted intensive experiments and analysis on the above methods. Our findings shed light on the challenges and potential solutions in AD detection using speech and audio data.

Traditional biomedical artificial intelligence (AI) models, designed for specific tasks or modalities, often exhibit limited flexibility in real-world deployment and struggle to utilize holistic information. Generalist AI holds the potential to address these limitations due to its versatility in interpreting different data types and generating tailored outputs for diverse needs. However, existing biomedical generalist AI solutions are typically heavyweight and closed source to researchers, practitioners, and patients. Here, we propose BiomedGPT, the first open-source and lightweight vision-language foundation model, designed as a generalist capable of performing various biomedical tasks. BiomedGPT achieved state-of-the-art results in 16 out of 25 experiments while maintaining a computing-friendly model scale. We also conducted human evaluations to assess the capabilities of BiomedGPT in radiology visual question answering, report generation, and summarization. BiomedGPT exhibits robust prediction ability with a low error rate of 3.8% in question answering, satisfactory performance with an error rate of 8.3% in writing complex radiology reports, and competitive summarization ability with a nearly equivalent preference score to human experts. Our method demonstrates that effective training with diverse data can lead to more practical biomedical AI for improving diagnosis and workflow efficiency., Comment: Fix incorrect citations and add journal reference for the published version. Nat Med (2024)

Graphene quantum dots (GQDs) can exhibit a range of spectacular phenomena such as the Klein-tunneling-induced quasibound states1-6 and Berry-phase-tuned energy spectra7-15. According to previous studies, all these interesting quantum phenomena seem to be well understood in the free electron picture1-15. However, electronic motion in the GQDs is reduced to quantized orbits by quantum confinement, which implies that the kinetic energy may be comparable to or even smaller than the Coulomb energy of the quasiparticles, possibly resulting in exotic correlated phases in the GQDs. Here we present a scanning tunneling microscopy and spectroscopy study of gate-tunable GQDs in graphene/WSe2 heterostructure devices and report for the first time the observation of electron-electron interaction and correlation-induced spin-charge separation in the GQDs. Gating allows us to precise characterize effects of the electron-electron interaction on the energy spectra of the GQDs. By measuring density of states as a function of energy and position, we explicitly uncover two density waves with different velocities in the GQDs, attributing to spin-charge separation in real space.

Modern supervised learning neural network models require a large amount of manually labeled data, which makes the construction of domain-specific knowledge graphs time-consuming and labor-intensive. In parallel, although there has been much research on named entity recognition and relation extraction based on distantly supervised learning, constructing a domain-specific knowledge graph from large collections of textual data without manual annotations is still an urgent problem to be solved. In response, we propose an integrated framework for adapting and re-learning knowledge graphs from one coarse domain (biomedical) to a finer-define domain (oncology). In this framework, we apply distant-supervision on cross-domain knowledge graph adaptation. Consequently, no manual data annotation is required to train the model. We introduce a novel iterative training strategy to facilitate the discovery of domain-specific named entities and triples. Experimental results indicate that the proposed framework can perform domain adaptation and construction of knowledge graph efficiently.

This paper presents the 2nd place solution to the Google Landmark Retrieval Competition 2020. We propose a training method of global feature model for landmark retrieval without post-processing, such as local feature and spatial verification. There are two parts in our retrieval method in this competition. This training scheme mainly includes training by increasing margin value of arcmargin loss and increasing image resolution step by step. Models are trained by PaddlePaddle framework and Pytorch framework, and then converted to tensorflow 2.2. Using this method, we got a public score of 0.40176 and a private score of 0.36278 and achieved 2nd place in the Google Landmark Retrieval Competition 2020.

We aim to tackle the problem of point-based interactive segmentation, in which the key challenge is to propagate the user-provided annotations to unlabeled regions efficiently. Existing methods tackle this challenge by utilizing computationally expensive fully connected graphs or transformer architectures that sacrifice important fine-grained information required for accurate segmentation. To overcome these limitations, we propose a cascade sparse feature propagation network that learns a click-augmented feature representation for propagating user-provided information to unlabeled regions. The sparse design of our network enables efficient information propagation on high-resolution features, resulting in more detailed object segmentation. We validate the effectiveness of our method through comprehensive experiments on various benchmarks, and the results demonstrate the superior performance of our approach. Code is available at \href{https://github.com/kleinzcy/CSFPN}{https://github.com/kleinzcy/CSFPN}., Comment: The first two authors contribute equally. Accepted by BMVC 2023