Publications by authors named "BaiYing Lei"

Article Synopsis
  • Researchers developed a new deep learning model called STGF R-CNN to improve the detection of senescent cells, which are important for studying cell aging but often hard to identify due to their small size and similar appearances.* -
  • The STGF R-CNN combines a Faster R-CNN framework with a Swin Transformer and group normalization to enhance the model's performance and make it more efficient for clinical use.* -
  • Experimental results showed that this model achieved a high detection accuracy (mean Average Precision of 0.835) and significantly reduced assessment time from 12 hours to under 1 second, indicating its potential for applications like drug screening.*
View Article and Find Full Text PDF

The sellar region tumor is a brain tumor that only exists in the brain sellar, which affects the central nervous system. The early diagnosis of the sellar region tumor subtypes helps clinicians better understand the best treatment and recovery of pa-tients. Magnetic resonance imaging (MRI) has proven to be an effective tool for the early detection of sellar region tumors.

View Article and Find Full Text PDF

Automatic and accurate classification of breast cancer in multimodal ultrasound images is crucial to improve patients' diagnosis and treatment effect and save medical resources. Methodologically, the fusion of multimodal ultrasound images often encounters challenges such as misalignment, limited utilization of complementary information, poor interpretability in feature fusion, and imbalances in sample categories. To solve these problems, we propose a feature alignment mutual attention fusion method (FAMF-Net), which consists of a region awareness alignment (RAA) block, a mutual attention fusion (MAF) block, and a reinforcement learning-based dynamic optimization strategy(RDO).

View Article and Find Full Text PDF
Article Synopsis
  • - The multi-attention guided UNet (MAUNet) is proposed for improved segmentation of thyroid nodules, addressing challenges due to their varying sizes and positions using a multi-scale cross attention (MSCA) module for better feature extraction.
  • - A dual attention (DA) module enhances information sharing between the encoder and decoder in the UNet architecture, further refining segmentation results.
  • - Extensive tests on ultrasound images from 17 hospitals reveal that MAUNet achieves high Dice scores (around 0.9) and outperforms existing segmentation methods, demonstrating effective generalization across diverse datasets while maintaining patient privacy through federal learning.
View Article and Find Full Text PDF
Article Synopsis
  • The paper discusses challenges in diagnosing brain disorders using resting-state fMRI due to complex imaging features and limited sample sizes.
  • It identifies three main limitations in existing graph convolutional network (GCN) approaches: sensitivity to non-imaging data, neglecting feature relationships, and the issues caused by multisite data variability.
  • To address these, the paper proposes a new method called a knowledge-aware multisite adaptive graph Transformer, which evaluates feature sensitivity, fuses subgraphs, and employs a domain adaptive GCN, demonstrating improved diagnostic performance in experiments on brain disorders.
View Article and Find Full Text PDF
Article Synopsis
  • Skin lesions are prevalent and similar in appearance, making accurate diagnosis challenging; existing deep learning models help but often only use surface data from clinical and dermatoscopic sources.
  • This paper introduces a novel diagnostic network that integrates both clinical and ultrasound data to enhance diagnostic accuracy by leveraging both surface and depth information of the lesions.
  • The proposed method includes an attention-guided learning module for better feature representation and a feature reconstruction learning strategy to improve the model's robustness and reliability, demonstrating superior performance in extensive experiments.
View Article and Find Full Text PDF

Brain network analysis plays an increasingly important role in studying brain function and the exploring of disease mechanisms. However, existing brain network construction tools have some limitations, including dependency on empirical users, weak consistency in repeated experiments and time-consuming processes. In this work, a diffusion-based brain network pipeline, DGCL is designed for end-to-end construction of brain networks.

View Article and Find Full Text PDF

Background: It was essential to identify individuals at high risk of fragility fracture and prevented them due to the significant morbidity, mortality, and economic burden associated with fragility fracture. The quantitative ultrasound (QUS) showed promise in assessing bone structure characteristics and determining the risk of fragility fracture.

Aims: To evaluate the performance of a multi-channel residual network (MResNet) based on ultrasonic radiofrequency (RF) signal to discriminate fragility fractures retrospectively in postmenopausal women, and compared it with the traditional parameter of QUS, speed of sound (SOS), and bone mineral density (BMD) acquired with dual X-ray absorptiometry (DXA).

View Article and Find Full Text PDF

Multi-modal data can provide complementary information of Alzheimer's disease (AD) and its development from different perspectives. Such information is closely related to the diagnosis, prevention, and treatment of AD, and hence it is necessary and critical to study AD through multi-modal data. Existing learning methods, however, usually ignore the influence of feature heterogeneity and directly fuse features in the last stages.

View Article and Find Full Text PDF

Multi-center disease diagnosis aims to build a global model for all involved medical centers. Due to privacy concerns, it is infeasible to collect data from multiple centers for training (i.e.

View Article and Find Full Text PDF
Article Synopsis
  • Accurate segmentation of gastric tumors from CT scans is crucial for effective diagnosis and treatment of gastric cancer, but it faces challenges like varying resolution and complex tumor characteristics.
  • The study introduces a new segmentation method called Hierarchical Class-Aware Domain Adaptive Network (HCA-DAN), which combines a 3D neural network and a Transformer to effectively extract features from 3D CT images while addressing cross-center data variations.
  • Results show that HCA-DAN outperforms other segmentation models, achieving higher mean dice similarity coefficients in both in-center and cross-center tests, indicating promising performance in accurately identifying gastric tumors.
View Article and Find Full Text PDF

Multimodal neuroimaging provides complementary information critical for accurate early diagnosis of Alzheimer's disease (AD). However, the inherent variability between multimodal neuroimages hinders the effective fusion of multimodal features. Moreover, achieving reliable and interpretable diagnoses in the field of multimodal fusion remains challenging.

View Article and Find Full Text PDF

Accurate and efficient prediction of drug-target interaction (DTI) is critical to advance drug development and reduce the cost of drug discovery. Recently, the employment of deep learning methods has enhanced DTI prediction precision and efficacy, but it still encounters several challenges. The first challenge lies in the efficient learning of drug and protein feature representations alongside their interaction features to enhance DTI prediction.

View Article and Find Full Text PDF

Purpose: We developed an Infant Retinal Intelligent Diagnosis System (IRIDS), an automated system to aid early diagnosis and monitoring of infantile fundus diseases and health conditions to satisfy urgent needs of ophthalmologists.

Methods: We developed IRIDS by combining convolutional neural networks and transformer structures, using a dataset of 7697 retinal images (1089 infants) from four hospitals. It identifies nine fundus diseases and conditions, namely, retinopathy of prematurity (ROP) (mild ROP, moderate ROP, and severe ROP), retinoblastoma (RB), retinitis pigmentosa (RP), Coats disease, coloboma of the choroid, congenital retinal fold (CRF), and normal.

View Article and Find Full Text PDF

The study of nicotine addiction mechanism is of great significance in both nicotine withdrawal and brain science. The detection of addiction-related brain connectivity using functional magnetic resonance imaging (fMRI) is a critical step in study of this mechanism. However, it is challenging to accurately estimate addiction-related brain connectivity due to the low-signal-to-noise ratio of fMRI and the issue of small sample size.

View Article and Find Full Text PDF

Alzheimer's disease (AD) is characterized by alterations of the brain's structural and functional connectivity during its progressive degenerative processes. Existing auxiliary diagnostic methods have accomplished the classification task, but few of them can accurately evaluate the changing characteristics of brain connectivity. In this work, a prior-guided adversarial learning with hypergraph (PALH) model is proposed to predict abnormal brain connections using triple-modality medical images.

View Article and Find Full Text PDF

Effective connectivity estimation plays a crucial role in understanding the interactions and information flow between different brain regions. However, the functional time series used for estimating effective connectivity is derived from certain software, which may lead to large computing errors because of different parameter settings and degrade the ability to model complex causal relationships between brain regions. In this paper, a brain diffuser with hierarchical transformer (BDHT) is proposed to estimate effective connectivity for mild cognitive impairment (MCI) analysis.

View Article and Find Full Text PDF

Background: Cell senescence is a sign of aging and plays a significant role in the pathogenesis of age-related disorders. For cell therapy, senescence may compromise the quality and efficacy of cells, posing potential safety risks. Mesenchymal stem cells (MSCs) are currently undergoing extensive research for cell therapy, thus necessitating the development of effective methods to evaluate senescence.

View Article and Find Full Text PDF
Article Synopsis
  • In 2019, COVID-19 is a serious acute illness requiring effective automated diagnosis, particularly as CT scans show subtle differences between it and community-acquired pneumonia (CP).
  • Current diagnosis models struggle with multi-center data optimization and are not suitable for distinguishing between COVID-19, CP, and healthy individuals.
  • The proposed solution is a graph-enhanced 3D convolutional neural network (CNN) that improves feature extraction and uses domain adaptation for better accuracy across different centers, achieving 98.05% accuracy in a mixed dataset.
View Article and Find Full Text PDF

Contrast-enhanced ultrasound (CEUS) video plays an important role in post-ablation treatment response assessment in patients with hepatocellular carcinoma (HCC). However, the assessment of treatment response using CEUS video is challenging due to issues such as high inter-frame data repeatability, small ablation area and poor imaging quality of CEUS video. To address these issues, we propose a two-stage diagnostic framework for post-ablation treatment response assessment in patients with HCC using CEUS video.

View Article and Find Full Text PDF

Fibromyalgia syndrome (FMS) is a type of rheumatology that seriously affects the normal life of patients. Due to the complex clinical manifestations of FMS, it is challenging to detect FMS. Therefore, an automatic FMS diagnosis model is urgently needed to assist physicians.

View Article and Find Full Text PDF

As an early sign of thyroid cancer, thyroid nodules are the most common nodular lesions. As a non-invasive imaging method, ultrasound is widely used in the diagnosis of benign and malignant thyroid nodules. As there is no obvious difference in appearance between the two types of thyroid nodules, and the contrast with the surrounding muscle tissue is too low, it is difficult to distinguish the benign and malignant nodules.

View Article and Find Full Text PDF

12-lead electrocardiogram (ECG) is a widely used method in the diagnosis of cardiovascular disease (CVD). With the increase in the number of CVD patients, the study of accurate automatic diagnosis methods via ECG has become a research hotspot. The use of deep learning-based methods can reduce the influence of human subjectivity and improve the diagnosis accuracy.

View Article and Find Full Text PDF
Article Synopsis
  • Accurate segmentation of gastric tumors from CT images is vital for diagnosing and treating gastric cancer, but using data from multiple centers introduces challenges due to data variability.
  • Researchers developed a new method called USBDAN, which combines a 3D neural network with an Anisotropic neural network and a Transformer to extract features from CT images and adaptively align them between different data sources.
  • When tested on an in-house dataset from four medical centers, USBDAN showed better performance than current leading methods in tumor segmentation.
View Article and Find Full Text PDF

Fusing structural-functional images of the brain has shown great potential to analyze the deterioration of Alzheimer's disease (AD). However, it is a big challenge to effectively fuse the correlated and complementary information from multimodal neuroimages. In this work, a novel model termed cross-modal transformer generative adversarial network (CT-GAN) is proposed to effectively fuse the functional and structural information contained in functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI).

View Article and Find Full Text PDF