Medical large Vision-Language Models (Med-LVLMs) have shown strong potential in multimodal clinical applications such as medical visual question answering and report generation. However, Med-LVLMs remain challenged by hallucinations caused by modality misalignment, where models prioritize textual knowledge over visual evidence and generate outputs that conflict with medical images. To mitigate this issue, recent studies have explored preference optimization to improve image–text alignment, achieving promising results. Despite these advances, existing preference-based methods still face two limitations in medical settings: (1) overfitting to superficial cues, and (2) pseudo convergence of the preference signal. In this paper, we propose Dynamic Evidence-Guided Preference Optimization (DEPO), a new framework that enables evidence-aware and adaptive preference learning for Med-LVLMs. DEPO introduces Multi-Modal Evidence Perturbation (MEP) to suppress non-causal textual and visual shortcuts, and Dispreferred Evidence Resampling (DER) to continuously update dispreferred responses as hallucination patterns evolve. Experiments on multiple medical VQA and report generation benchmarks demonstrate consistent improvements over existing methods, with strong robustness across datasets and architectures. All Codes and data will be released after review.

Colored point cloud comprising geometry and attribute components is one of the mainstream representations enabling realistic and immersive 3D applications. To generate large-scale and denser colored point clouds, we propose a deep learning-based Joint Geometry and Attribute Up-sampling (JGAU) method, which learns to model both geometry and attribute patterns and leverages the spatial attribute correlation. Firstly, we establish and release a large-scale dataset for colored point cloud up-sampling, named SYSU-PCUD, which has 121 large-scale colored point clouds with diverse geometry and attribute complexities in six categories and four sampling rates. Secondly, to improve the quality of up-sampled point clouds, we propose a deep learning-based JGAU framework to up-sample the geometry and attribute jointly. It consists of a geometry up-sampling network and an attribute up-sampling network, where the latter leverages the up-sampled auxiliary geometry to model neighborhood correlations of the attributes. Thirdly, we propose two coarse attribute up-sampling methods, Geometric Distance Weighted Attribute Interpolation (GDWAI) and Deep Learning-based Attribute Interpolation (DLAI), to generate coarsely up-sampled attributes for each point. Then, we propose an attribute enhancement module to refine the up-sampled attributes and generate high quality point clouds by further exploiting intrinsic attribute and geometry patterns. Extensive experiments show that Peak Signal-to-Noise Ratio (PSNR) achieved by the proposed JGAU are 33.90 dB, 32.10 dB, 31.10 dB, and 30.39 dB when up-sampling rates are $4\times $ , $8\times $ , $12\times $ , and $16\times $ , respectively. Compared to the state-of-the-art schemes, the JGAU achieves an average of 2.32 dB, 2.47 dB, 2.28 dB and 2.11 dB PSNR gains at four up-sampling rates, respectively, which are significant. The code is released with https://github.com/SYSU-Video/JGAU.

Cuffless blood pressure (BP) measurement has gained increasing attention due to the global aging population. Data-driven approaches have shown high accuracy for cuffless BP estimation. However, when deployed on wearable devices, they often suffer from being time-consuming because a complete retraining process is required if the training samples or structure need to be expanded. To address these issues, we propose a Knowledge-embedded Bi-incremental Broad Learning System (BpBLS) for cuffless BP estimation using biosignals collected from wearable devices.With a flat structure, BpBLS can be updated flexibly and quickly without retraining the entire model for incremental biosignals and/or training samples. In BpBLS, a novel Pulse Pressure Regularization (PPR) method is proposed to comprehensively capture the BP knowledge, which is then embedded into the system to enhance its accuracy. Experimental results demonstrate that BpBLS exhibits superior performance in both estimation accuracy and computational efficiency compared to the state-of-the-art approaches. For the CAS-BP dataset, the estimation error is 0.60 $\pm$ 8.44 for systolic BP (SBP) and 0.29 $\pm$ 6.45 for diastolic BP (DBP); while for the Aurora-BP dataset, the estimation error is -0.32 $\pm$ 8.46 mmHg for SBP and 0.05 $\pm$ 6.65 mmHg for DBP. More importantly, the training time for both datasets is less than ten seconds, and the computational efficiency is improved by an order of magnitude compared to traditional machine learning methods. Our work will serve as a novel flexible and lightweight framework for cuffless BP measurement.

Hypertension is a leading controllable risk factor for cardiovascular disease and premature death, with blood pressure (BP) variability potentially posing greater risks than sustained hypertension. However, intermittent single-point measurements cannot capture dynamic BP changes, and although invasive arterial catheterization is the gold standard for continuous waveforms, its high complication risk limits clinical use. Consequently, non-invasive continuous BP monitoring has emerged as a promising alternative but still faces two major limitations: (1) Separate modeling of waveform prediction and SBP/DBP estimation reduces supervision and physiological consistency; (2) Point-wise loss functions overlook the periodic structure of blood pressure waveforms. To address these challenges, we propose WaveMorph, a framework for high-fidelity long-term continuous BP waveform prediction with three key contributions: (1) We develop BP-Guided de-normalization to couple waveform prediction with SBP and DBP, strengthening supervision and improving physiological consistency; (2) We introduce a patchlevel morphology loss that preserves local periodic structure and morphological fidelity in predicted waveforms; (3) achieving state-of-the-art performance. The proposed method was evaluated on the MIMIC-III dataset. Results show that our model outperforms state-of-the-art methods in waveform reconstruction and SBP/DBP estimation, achieving mean absolute errors (MAE) of 3.52 mmHg (waveform), 4.78 mmHg (SBP), and 2.42 mmHg (DBP).

Monitoring the Depth of Anesthesia (DoA) using Electroencephalography (EEG) is essential for patient safety and optimal drug administration. However, existing methods face challenges like computational inefficiency and limited generalization, hindering real-time applicability. To address these, we propose a lightweight framework based on SimGate, a parameter-free RNN gating mechanism. SimGate simplifies gating by dynamically computing hidden states based on cosine similarity and requiring only a single linear layer and an initialization vector for training, thus reducing model complexity and enabling efficient parallel computation. To improve generalization, we introduce Harmonic Mix, a frequency augmentation strategy that enhances data diversity by applying harmonic-constrained low-pass filtering and convex combinations of EEG activities. This method preserves critical frequency bands and mitigates noise interference. Experimental results on the VitalDB dataset show that our model achieves 82.70% classification accuracy (ACC) and 5.79±0.64 root mean squared error (RMSE), outperforming existing models with only 16.9K parameters and an inference speed (IS) of 0.02ms. These results demonstrate the effectiveness of our model for real-time DoA monitoring in clinical settings.

Colorectal cancer (CRC) affects over 2.5 million people globally each year, with the majority of cases originating from the development of adenomatous polyps, which progress from intramucosal carcinoma to malignant tumors. Identifying the critical point (pre-disease state) and detecting early-stage cancer for endoscopic resection are primary objectives in cancer control. However, these tasks present significant challenges due to the extremely subtle or negligible differences in gross signs between the pre-disease and healthy states. In this study, inspired by the dynamic network biomarker (DNB) theory, we propose E-DNB, an unsupervised graph-based model, to detect pre-disease state of CRC deterioration before the onset of malignant tumors using metabolize data. Two stages are involved in the E-DNB model: network construction and graph similarity learning. In the network construction stage, individual networks based on Pearson correlation coefficients are constructed for subjects at different stages of CRC using metabolomics data. Subsequently, individual networks are compared to baseline networks to measure their similarity based on squared Euclidean distance in the graph similarity learning stage, to generate DNB for identifying the pre-disease state of CRCs. Experiments on 220 subjects at various stages of CRC demonstrate that E-DNB achieves an AUC of 71% in detecting pre-disease state of CRCs, which exceeds the current DNB and popular supervised methods, demonstrating the performance of the proposed E-DNB. Our findings offer novel insights into the early diagnosis of CRCs and may contribute to advancements in addressing complex diseases.

Biosignals collected by wearable devices, such as electrocardiogram and photoplethysmogram, exhibit redundancy and global temporal dependencies, posing a challenge in extracting discriminative features for blood pressure (BP) estimation. To address this challenge, we propose HGCTNet, a handcrafted feature-guided CNN and transformer network for cuffless BP measurement based on wearable devices. By leveraging convolutional operations and self-attention mechanisms, we design a CNN-Transformer hybrid architecture to learn features from biosignals that capture both local information and global temporal dependencies. Then, we introduce a handcrafted feature-guided attention module that utilizes handcrafted features extracted from biosignals as query vectors to eliminate redundant information within the learned features. Finally, we design a feature fusion module that integrates the learned features, handcrafted features, and demographics to enhance model performance. We validate our approach using two large wearable BP datasets: the CAS-BP dataset and the Aurora-BP dataset. Experimental results demonstrate that HGCTNet achieves an estimation error of 0.9 ± 6.5 mmHg for diastolic BP (DBP) and 0.7 ± 8.3 mmHg for systolic BP (SBP) on the CAS-BP dataset. On the Aurora-BP dataset, the corresponding errors are -0.4 ± 7.0 mmHg for DBP and -0.4 ± 8.6 mmHg for SBP. Compared to the current state-of-the-art approaches, HGCTNet reduces the mean absolute error of SBP estimation by 10.68% on the CAS-BP dataset and 9.84% on the Aurora-BP dataset. These results highlight the potential of HGCTNet in improving the performance of wearable cuffless BP measurements.

This study aimed to evaluate the performance of cuffless blood pressure (BP) measurement techniques in a large and diverse cohort of participants. We enrolled 3077 participants (aged 18-75, 65.16% women, 35.91% hypertensive participants) and conducted followed-up for approximately 1 month. Electrocardiogram, pulse pressure wave, and multiwavelength photoplethysmogram signals were simultaneously recorded using smartwatches; dual-observer auscultation systolic BP (SBP) and diastolic BP (DBP) reference measurements were also obtained. Pulse transit time, traditional machine learning (TML), and deep learning (DL) models were evaluated with calibration and calibration-free strategy. TML models were developed using ridge regression, support vector machine, adaptive boosting, and random forest; while DL models using convolutional and recurrent neural networks. The best-performing calibration-based model yielded estimation errors of 1.33 ± 6.43 mmHg for DBP and 2.31 ± 9.57 mmHg for SBP in the overall population, with reduced SBP estimation errors in normotensive (1.97 ± 7.85 mmHg) and young (0.24 ± 6.61 mmHg) subpopulations. The best-performing calibration-free model had estimation errors of -0.29 ± 8.78 mmHg for DBP and -0.71 ± 13.04 mmHg for SBP. We conclude that smartwatches are effective for measuring DBP for all participants and SBP for normotensive and younger participants with calibration; performance degrades significantly for heterogeneous populations including older and hypertensive participants. The availability of cuffless BP measurement without calibration is limited in routine settings. Our study provides a large-scale benchmark for emerging investigations on cuffless BP measurement, highlighting the need to explore additional signals or principles to enhance the accuracy in large-scale heterogeneous populations.

We developed a ballistocardiography (BCG)-based Internet-of-Medical-Things (IoMT) system for remote monitoring of cardiopulmonary health. The system composes of BCG sensor, edge node, and cloud platform. To improve computational efficiency and system stability, the system adopted collaborative computing between edge nodes and cloud platforms. Edge nodes undertake signal processing tasks, namely approximate entropy for signal quality assessment, a lifting wavelet scheme for separating the BCG and respiration signal, and the lightweight BCG and respiration signal peaks detection. Heart rate variability (HRV), respiratory rate variability (RRV) analysis and other intelligent computing are performed on cloud platform. In experiments with 25 participants, the proposed method achieved a mean absolute error (MAE)±standard deviation of absolute error (SDAE) of 9.6±8.2 ms for heartbeat intervals detection, and a MAE±SDAE of 22.4±31.1 ms for respiration intervals detection. To study the recovery of cardiopulmonary function in patients with coronavirus disease 2019 (COVID-19), this study recruited 186 discharged patients with COVID-19 and 186 control volunteers. The results indicate that the recovery performance of the respiratory rhythm is better than the heart rhythm among discharged patients with COVID-19. This reminds the patients to be aware of the risk of cardiovascular disease after recovering from COVID-19. Therefore, our remote monitoring system has the ability to play a major role in the follow up and management of discharged patients with COVID-19.

Ambulatory blood pressure (BP) provides valuable information for cardiovascular risk assessment. The present cuff-based devices are intrusive for long-term BP monitoring, whereas cuff-less BP measurement methods based on pulse transit time or multi-parameter are inferior in robustness and reliability by using electrocardiogram (ECG) and photoplethysmogram signals. This study examined a multi-sensor fusion-based platform and algorithm for systolic BP (SBP), mean arterial pressure (MAP), and diastolic BP (DBP) estimation. The proposed multi-sensor platform was comprised of one ECG sensor and two pulse pressure wave sensors for simultaneous signal collection. After extracting 35 features from the collected signals, a weakly supervised feature selection method was proposed for dimension reduction because the reference oscillometric technique-based BP are intermittent and can be redeemed as coarse-grained labels. BP models were then established using a multi-instance regression algorithm. A total of 85 participants including 17 hypertensive and 12 hypotensive patients were enrolled. Experimental results showed that the proposed approach exhibited good accuracy for diverse population with an estimation error of 1.62 ± 7.76 mmHg for SBP, 1.53 ± 6.03 mmHg for MAP, and 1.49 ± 5.52 for DBP, which complied with the association for the advancement of medical instrumentation standards in BP estimation. Moreover, the estimation accuracy is with random daily fluctuations rather than long-term degradation through a maximum two-month follow-up period indicated good robustness performance. These results suggest that the proposed approach is with high reliability and robustness and thus provides a novel insight for cuff-less BP measurement.

Atrial fibrillation (AF) is one of the most common sustained chronic cardiac arrhythmia in elderly population, associated with a high mortality and morbidity in stroke, heart failure, coronary artery disease, systemic thromboembolism, etc. The early detection of AF is necessary for averting the possibility of disability or mortality. However, AF detection remains problematic due to its episodic pattern. In this paper, a multiscaled fusion of deep convolutional neural network (MS-CNN) is proposed to screen out AF recordings from single lead short electrocardiogram (ECG) recordings. The MS-CNN employs the architecture of two-stream convolutional networks with different filter sizes to capture features of different scales. The experimental results show that the proposed MS-CNN achieves 96.99% of classification accuracy on ECG recordings cropped/padded to 5 s. Especially, the best classification accuracy, 98.13%, is obtained on ECG recordings of 20 s. Compared with artificial neural network, shallow single-stream CNN, and VisualGeometry group network, the MS-CNN can achieve the better classification performance. Meanwhile, visualization of the learned features from the MS-CNN demonstrates its superiority in extracting linear separable ECG features without hand-craft feature engineering. The excellent AF screening performance of the MS-CNN can satisfy the most elders for daily monitoring with wearable devices.

Continuous blood pressure (BP) estimation using pulse transit time (PTT) is a promising method for unobtrusive BP measurement. However, the accuracy of this approach must be improved for it to be viable for a wide range of applications. This study proposes a novel continuous BP estimation approach that combines data mining techniques with a traditional mechanism-driven model. First, 14 features derived from simultaneous electrocardiogram and photoplethysmogram signals were extracted for beat-to-beat BP estimation. A genetic algorithm-based feature selection method was then used to select BP indicators for each subject. Multivariate linear regression and support vector regression were employed to develop the BP model. The accuracy and robustness of the proposed approach were validated for static, dynamic, and follow-up performance. Experimental results based on 73 subjects showed that the proposed approach exhibited excellent accuracy in static BP estimation, with a correlation coefficient and mean error of 0.852 and -0.001 ± 3.102 mmHg for systolic BP, and 0.790 and -0.004 ± 2.199 mmHg for diastolic BP. Similar performance was observed for dynamic BP estimation. The robustness results indicated that the estimation accuracy was lower by a certain degree one day after model construction but was relatively stable from one day to six months after construction. The proposed approach is superior to the state-of-the-art PTT-based model for an approximately 2-mmHg reduction in the standard derivation at different time intervals, thus providing potentially novel insights for cuffless BP estimation.

The year 2016 marks the 200th birth anniversary of Carl Friedrich Wilhelm Ludwig (1816-1895). As one of the most remarkable scientists, Ludwig invented the kymograph, which for the first time enabled the recording of continuous blood pressure (BP), opening the door to the modern study of physiology. Almost a century later, intraarterial BP monitoring through an arterial line has been used clinically. Subsequently, arterial tonometry and volume clamp method were developed and applied in continuous BP measurement in a noninvasive way. In the last two decades, additional efforts have been made to transform the method of unobtrusive continuous BP monitoring without the use of a cuff. This review summarizes the key milestones in continuous BP measurement; that is, kymograph, intraarterial BP monitoring, arterial tonometry, volume clamp method, and cuffless BP technologies. Our emphasis is on recent studies of unobtrusive BP measurements as well as on challenges and future directions.

Recently, a kind of lightweight and resource‐efficient biometrics‐based security solutions were proposed for the emerging body sensor network (BSN). In such security solutions, physiological characteristics that can be captured by individual sensors of BSN were proposed to generate entity identifiers (EIs) for securing keying materials by a biometric approach. In this study, the authors focus on an improved key distribution solution with the energy distribution information of physiological signals (EDPSs) ‐based EIs. Firstly, different EDPS‐based EI generation schemes are studied. Based on the existing multi‐windows Fourier transform scheme, a modified one with single‐window is proposed to improve the identification performance of the generated EIs. Then, a different method based on the discrete cosine transform of the autocorrelation sequence of physiological signals is proposed aiming for a significant increase in identification rates. The performances of time‐varying randomness and identification rates are evaluated to examine EI's feasibility in securing the transmission of keying materials. Based on the characteristics of generated EIs, the corresponding key distribution solution, that is, user‐dependent fuzzy vault, is proposed. A detailed system performance analysis in terms of half total error rate, anti‐attack ability, as well as computational complexity, is conducted to demonstrate the effectiveness of the proposed solution.

The fuzzy vault scheme, which has been most widely used in biometric systems, has some weaknesses while applied in securing Body Sensor Network (BSN) communications. This is mainly because of the dynamic random characteristics of biometric identifiers independently generated by sensor nodes based on self-captured physiological signals. A modified fuzzy vault scheme is proposed to overcome this problem, aiming for a significant reduction in recognition errors. Error-correction encoding/decoding process is deployed in a way different from the existing ones at the transmitter/receiver to reduce the effect of bit differences in dynamic random patterns between biometric identifiers. An enveloping process is further deployed before the projection of real points onto the keying material constructed polynomial to protect the real points from being revealed by various potential attacks. This enveloping process can also be deployed in the traditional fuzzy vault scheme to prevent the known attacks based on statistical analysis of points in the vault. A detailed performance analysis in terms of False Acceptance Rate (FAR) and False Rejection Rate (FRR), as well as anti-attack capability was conducted to demonstrate the effectiveness of our solution.