A5038951411- AI in cancer detection
- Medical Image Segmentation Techniques
- Interstitial Lung Diseases and Idiopathic Pulmonary Fibrosis
- Lung Cancer Diagnosis and Treatment
- Sports Performance and Training
- Material Dynamics and Properties
- Thermoregulation and physiological responses
- Infrared Thermography in Medicine
- Advanced Neural Network Applications
- Cultural Heritage Materials Analysis
- Systemic Sclerosis and Related Diseases
- Colorectal Cancer Screening and Detection
- Advanced X-ray and CT Imaging
- Chronic Kidney Disease and Diabetes
- Renal and Vascular Pathologies
- Theoretical and Computational Physics
- MRI in cancer diagnosis
- Radiomics and Machine Learning in Medical Imaging
- Voice and Speech Disorders
Taiyuan University of Technology
2022-2025
Shanxi Medical University
2022
Second Hospital of Shanxi Medical University
2022
Shaanxi Provincial People's Hospital
2022
Accurately diagnosing chronic kidney disease requires pathologists to assess the structure of multiple tissues under different stains, a process that is timeconsuming and labor-intensive. Current AI-based methods for automatic assessment, like segmentation, often demand extensive manual annotation focus on single stain domain. To address these challenges, we introduce MSMTSeg, generative self-supervised meta-learning framework multi-stained multi-tissue segmentation in renal biopsy whole...
BACKGROUND: Interstitial lung disease (ILD) represents a group of chronic heterogeneous diseases, and current clinical practice in assessment ILD severity progression mainly rely on the radiologist-based visual screening, which greatly restricts accuracy due to high inter- intra-subjective observer variability. OBJECTIVE: To solve these problems, this work, we propose deep learning driven framework that can assess quantify lesion indicators outcome prediction ILD. METHODS: In detail, first...
Assessment of the glomerular basement membrane (GBM) in transmission electron microscopy (TEM) is crucial for diagnosing chronic kidney disease (CKD). The lack domain-independent automatic segmentation tools GBM necessitates an AI-based solution to automate process. In this study, we introduce GBMSeg, a training-free framework designed automatically segment TEM images guided only by one-shot annotated reference. Specifically, GBMSeg first exploits robust feature matching capabilities...
<title>Abstract</title> The characterization of amorphous materials has been a long-standing challenge in science due to their lack long-range order, which makes it difficult define structural metrics. Here, we describe 2D system-based high-precision detection model(HPDM) that utilizes the concepts “bag” and instances achieve image-level classification structure-level segmentation systems without any additional dynamical information. We introduce an order parameter describes evolution phase...