Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks108 from public data
- 218
- Hulu-Med: A Transparent Generalist Model towards Holistic Medical Vision-Language Understanding113
Hulu-Med is introduced, a transparent, generalist medical Vision-Language Model (VLM) designed to unify language-only, 2D/3D vision-language, and video understanding within a single architecture, and outperforms proprietary systems such as GPT-4o on 16 benchmarks.
- 91
- 88
- Fetal cardiac cycle detection in multi-resource echocardiograms using hybrid classification framework80
This is the first framework that utilizes a hybrid classification framework for the detection task and integrates the extracting region-of-interest (ROI) component based on target detection, retaining a temporal dependency module and classification module based on a domain-transferred deep convolutional neural network (CNN).
- 59
- MLMSeg: A multi-view learning model for ultrasound thyroid nodule segmentation52
The exceptional segmentation capability of MLMSeg for thyroid nodules can greatly assist in localizing thyroid nodules and facilitating more precise measurements of their transverse and longitudinal diameters, which is of significant clinical relevance for the diagnosis of thyroid nodules.
- HN-PPISP: a hybrid network based on MLP-Mixer for protein–protein interaction site prediction46
A novel hybrid neural network named HN-PPISP is proposed, which integrates a Multi-layer Perceptron Mixer module for local feature extraction and a two-stage multi-branch module for global feature capture and merits Transformer, TextCNN and Bi-LSTM as a powerful alternative for PPI site prediction.
- 37
- A knowledge-interpretable multi-task learning framework for automated thyroid nodule diagnosis in ultrasound videos34
This study develops a user-friendly framework for the automated diagnosis of thyroid nodules in ultrasound videos, by simulating the typical diagnostic workflow used by radiologists and demonstrated this approach outperformed other state-of-the-art video classification methods.
- 34
- 31
- 31
- 29
- HWOA: an intelligent hybrid whale optimization algorithm for multi-objective task selection strategy in edge cloud computing system28
A fuzzy function is designed to address the uncertainty of task’s economic profits and execution time and some improved strategies are designed to solve the problem that the whale optimization algorithm (WOA) is subject to local optima entrapment.
- ED-ACNN: Novel attention convolutional neural network based on encoder–decoder framework for human traffic prediction27
It is concluded that the c l o s e n e s s feature is the most significant for human traffic prediction in the proposed approach, and the results show that the proposed method can be very competitive with state-of-the-art baselines.
- 26
- 23
- 22
- 21
- CardiacNet: Learning to Reconstruct Abnormalities for Cardiac Disease Assessment from Echocardiogram Videos21
This work proposes a novel reconstruction-based approach named CardiacNet to learn a better representation of local cardiac structures and motion abnormalities through echocardiogram videos and proposes benchmark datasets named CardiacNet-PAH and CardiacNet-ASD to evaluate the effectiveness of cardiac disease assessment.
- Random RotBoost: An Ensemble Classification Method Based on Rotation Forest and AdaBoost in Random Subsets and Its Application to Clinical Decision Support20
An ensemble classification method with an AdaBoost mechanism in random, automatically generating rotation subsets termed Random RotBoost, which reaches better classification performance when compared with existing methods and can potentially be enhanced and supported in medical tasks.
- DH-GAC: deep hierarchical context fusion network with modified geodesic active contour for multiple neurofibromatosis segmentation19
Experimental results demonstrate that DH-GAC not only improves the segmentation precision, but also overcomes the intrinsic drawback of classical geodesic active contour in boundary delineation.
- Deep endpoints focusing network under geometric constraints for end-to-end biometric measurement in fetal ultrasound images18
This is the first AI-based application to address the biometric measurement of irregular anatomical structures in fetal ultrasound images with an end-to-end approach and experiment results showed that E2EBM-Net outperformed the existing methods and achieved the state-of-the-art performance.
- 17
- Research on massive ECG data in XGBoost16
A method of anomaly threshold based on multiple classifiers can be well suited to datasets containing abnormal data, and use XGBoost algorithm as a sub-classifier to process massive ECG data and show that tree-based model classifier is the best fit to predict arrhythmia.
- 15
- 13
- 13
- 12
- 12
- A Novel Mutual Fractional Grey Bernoulli Model With Differential Evolution Algorithm and Its Application in Education Investment Forecasting in China12
A fractional non-linear grey Bernoulli model [MFNGBM (1,1)] is proposed to reduce the perturbation limit of the classical NGBM and further improve the accuracy of the model, which uses mutual fractional operators and a new optimization scheme with a differential evolution (DE) algorithm for forecasting education investment.
- Vision Foundation Models in Medical Image Analysis: Advances and Challenges11
This paper reviews the state-of-the-art research on the adaptation of VFMs to medical image segmentation, focusing on the challenges of domain adaptation, model compression, and federated learning.
- Real-Time Automatic M-Mode Echocardiography Measurement With Panel Attention11
The experimental results show that RAMEM surpasses existing RIS schemes (CNNs with NL & Transformers as the backbone) in PASCAL 2012 SBD and human performances in MEIS and introduces AMEM, an efficient algorithm of automatic M-mode echocardiography measurement, for automatic diagnosis.
- Test-Time Domain Generalization via Universe Learning: A Multi-Graph Matching Approach for Medical Image Segmentation10
This work introduces learnable universe embeddings that integrate morphological priors during multi-source training, along with novel unsupervised test-time paradigms for domain adaptation that guarantees cycle-consistency in multi-matching while enabling the model to more effectively capture the invariant priors of unseen data, significantly mitigating the effects of domain shifts.
- 9
- 9
- TMHSCA: a novel hybrid two-stage mutation with a sine cosine algorithm for discounted {0-1} knapsack problems9
An enhanced version of the sine-cosine algorithm (SCA) called TMHSCA is proposed to solve the discounted {0-1} knapsack problem, and the number of mutations can be adaptively adjusted based on the optimization capabilities of the optimal individual.
- A Deep Graph Network with Multiple Similarity for User Clustering in Human–Computer Interaction9
This paper proposes a deep graph embedding network with feature and structure similarity (called DGENFS) to cluster users’ attributes in HCI applications based on feature andructure similarity and designs an attributed graph clustering method to divide users into clusters by making full use of their attributes.
- 8
- Data free knowledge distillation with feature synthesis and spatial consistency for image analysis8
A novel DFKD strategy is proposed with three innovations: an enhanced DCGAN generator with an attention module for synthesizing samples with improved micro-discriminative features, a Multi-Scale Spatial Activation Region Consistency mechanism to accurately replicate the teacher’s spatial attributes, and an adversarial learning framework that creates a dynamic competitive environment between the generative and distillation phases.
- 7
- 7
- 7
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 3
- Self-FAGCFN: Graph-Convolution Fusion Network Based on Feature Fusion and Self-Supervised Feature Alignment for Pneumonia and Tuberculosis Diagnosis3
A Graph-Convolution Fusion Network with Self-Supervised Feature Alignment (Self-FAGCFN) to address the limitations of traditional feature fusion methods in deep learning-based medical image classification for respiratory diseases such as pneumonia and tuberculosis and develops a feature alignment loss that minimizes disparities.
- 3
- 3
- 3
- Anatomical Knowledge Mining and Matching for Semi-supervised Medical Multi-structure Detection3
This work introduces a novel semi-supervised approach named Semi-akmm for mining and matching anatomical knowledge in ultrasound images, and develops an Adaptive Prior Knowledge Transfer (APKT) module to mine and explore the distribution and knowledge of potential proposal boxes by proposal proportion constraint.
- A multi-label image classification method combining multi-stage image semantic information and label relevance3
This work proposes a new approach for multi-label image classification that achieves better results on several generic evaluation indicators compared with state-of-the-art methods.
- 3
- A transfer learning algorithm for automatic requirement model generation3
This algorithm hybridizes deep-learning algorithms such as word2vec and recurrent neural network with classical techniques to improve the performance of text analysis and potentially increase opportunities for requirement classification, promote software requirement quality, and deliver more reliable software products.
- WE-YOLO: Wavelet Enhanced YOLO for Small Object Detection in Optical Aerial Remote Sensing Images2
Wavelet Enhanced YOLO (THE AUTHORS-YOLO), an improved detector incorporating two novel modules: Mixed Haar Wavelet Downsampling (MixHWD) and Spatial Frequency Enhancement Mamba (SFEM), demonstrates superior detection accuracy while maintaining comparable parameters and computational efficiency to YOLO11n.
- 2
- 2
- 2
- 2
- Unified Mixture-of-Experts Framework for Joint Cardiac and Vascular Ultrasound Analysis and Report Generation2
The vision-language framework named the Echo-Cardiac-Vascular (ECV), for joint cardiac and vascular ultrasound report generation and parameter measurements, achieves high accuracy, improving diagnostic efficiency, consistency, and cross-disciplinary clinical applicability.
- Concept Relationship Embedding-Based Interactive Web Application for Explainable Medical Diagnosis2
The Concept Relationship Embedding Model (CREM) is proposed for interpretable medical diagnosis and deployed as an interactive web-based demo that allows clinicians to visualize concept activations, trace diagnostic reasoning paths, and iteratively refine concept cues, facilitating effective human-in-the-loop decision-making.
- 2
- Topology-Aware Wavelet Mamba for Airway Structure Segmentation in Postoperative Recurrent Nasopharyngeal Carcinoma CT Scans2
This study introduces TopoWMamba (Topology-aware Wavelet Mamba), a novel segmentation model specifically designed to address the challenges of postoperative airway risk evaluation in recurrent NPC patients, which outperforms existing models such as UNet, Attention UNet, and SwinUNet.
- 2
- Boosting the Transferability of Ensemble Adversarial Attack via Stochastic Average Variance Descent2
A new kind of ensemble attack method called stochastic average ensemble attack, which continuously optimize the ensemble gradient in an internal loop using the model history gradient and the average gradient of different models to make the crafted adversarial examples more transferable.
- 2
- Real-time Automatic M-mode Echocardiography Measurement with Panel Attention from Local-to-Global Pixels2
RAMEM, a real-time automatic M-mode echocardiography measurement scheme, contributes three aspects to answer the problems and the experimental results show that RAMEM surpasses existing RIS backbones (with non-local attention) in PASCAL 2012 SBD and human performances in real- time MEIS tested.
- 1
- 1
- 1
- MPA: Multimodal Prototype Augmentation for Few-Shot Learning1
A novel Multimodal Prototype Augmentation FSL framework called MPA, including LLM-based Multi-Variant Semantic Enhancement, Hierarchical Multi-View Augmentation, and an Adaptive Uncertain Class Absorber (AUCA) is proposed, which achieves superior performance compared to existing state-of-the-art methods across most settings.
- AI-Enabled Accurate Non-Invasive Assessment of Pulmonary Hypertension Progression via Multi-Modal Echocardiography1
It is shown that MePH significantly outperforms echocardiographers' assessments using echocardiography, reducing the mean absolute error in estimating mean pulmonary arterial pressure and pulmonary vascular resistance by 49.73% and 43.81%, respectively.
- 1
- 1
- Rapid Bone Scintigraphy Enhancement via Semantic Prior Distillation from Segment Anything Model1
This work proposes the first application of SAM-based semantic priors for medical image restoration, leveraging the Segment Anything Model (SAM) to enhance rapid bone scintigraphy images in pediatric populations.
- 1
- 1
- 1
- 1
- –
- CMCF: A Confidence-aware Multi-feature Fusion Correlation Filter for Visual Tracking–
A confidence-aware multi-feature fusion correlation filter for visual tracking, which enhances CF’s discriminative ability by fusing multiple types of features and perceiving the filter response.
- –
- –
- –
- Topology-Inspired Backward-Free Framework for Test-Time Adaptation in Medical Detection–
A novel backward-free Topology-aware TTA framework named T^3 that integrates Structural Perception Modeling and Box Regression Adaptation is proposed that achieves state-of-the-art cross-domain detection performance while maintaining high efficiency, offering a practical and robust solution for real-world medical diagnostic applications.
- Organ-Aware Routing Mixture-of-Retrieval Augmented Generation for Fetal Ultrasound Reporting–
FetusR is introduced, the first large-scale dataset for multi-organ fetal ultrasound reporting, containing 15,594 real-world cases with rich organ-wise annotations, and ORM-RAG, an organ-aware mixture-of-retrieval module that partitions the retrieval space into organ-specific corpora for independent retrieval, and a dynamic routing mechanism that selectively aggregates high-confidence organ-specific reports while filtering uncertain ones.
- –
- –
- –
- ToMo-UDA++: Unsupervised Domain Adaptation for Anatomical Structure Detection Using Enhanced Topology and Morphology Knowledge–
A new Unsupervised Domain Adaptation (UDA) method integrated with the enhanced Anatomy-oriented Topology Knowledge Transfer, Anatomy-aligned Morphology Knowledge Transfer, and Auxiliary Network and Ensembling Learning (ANEL) modules for anatomical structure detection in medical images, named ToMo-UDA++ is proposed.
- FUSEP: A Multi-Center Benchmark for Diverse Tasks in Fetal Ultrasound Screening Early Pregnancy–
This work presents a benchmark dataset for Fetal Ultrasound Screening in Early Pregnancy to facilitate intelligent ultrasound examination and assisted diagnosis called FUSEP and believes that FUSEP and benchmark can contribute to the medical community in the development of multiple tasks such as standard plane recognition, quality control on ultrasound images, automated assisted diagnostics in early fetal pregnancy, medical multi-object detection, domain adaptation for object detection, etc.
- –
- –
- –
- –
- –
- –
- Correction to: TMHSCA: a novel hybrid two-stage mutation with a sine cosine algorithm for discounted {0-1} knapsack problems–
An enhanced version of the sine-cosine algorithm (SCA) called TMHSCA is proposed to solve the discounted {0-1} knapsack problem and achieves a state-of-the-art performance.
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.