A5100418543- Spectroscopy Techniques in Biomedical and Chemical Research
- Spectroscopy and Chemometric Analyses
- AI in cancer detection
- Radiomics and Machine Learning in Medical Imaging
- Infrared Thermography in Medicine
- Advanced Chemical Sensor Technologies
- Digital Imaging for Blood Diseases
- Gold and Silver Nanoparticles Synthesis and Applications
- Metabolomics and Mass Spectrometry Studies
- Photoacoustic and Ultrasonic Imaging
- Bee Products Chemical Analysis
- Traditional Chinese Medicine Studies
- Brain Tumor Detection and Classification
- Advanced Image Fusion Techniques
- Cutaneous Melanoma Detection and Management
- Advanced Nanomaterials in Catalysis
- Molecular Biology Techniques and Applications
- Optical Imaging and Spectroscopy Techniques
- Identification and Quantification in Food
- Computational Drug Discovery Methods
- Colorectal Cancer Screening and Detection
- COVID-19 diagnosis using AI
- Systemic Lupus Erythematosus Research
- Advanced biosensing and bioanalysis techniques
- Medical Image Segmentation Techniques
Xinjiang University
2010-2025
Chongqing University
2025
Beijing Luhe Hospital Affiliated to Capital Medical University
2025
Sichuan Agricultural University
2024
Harbin University of Science and Technology
2024
University of Science and Technology of China
2024
Cloud Computing Center
2022-2024
Beihang University
2021-2023
People's Hospital of Xinjiang Uygur Autonomous Region
2023
Tumor Hospital of Xinjiang Medical University
2022
In recent years, deep learning has been widely used in breast cancer diagnosis, and many high-performance models have emerged. However, most of the existing are mainly based on static ultrasound (US) images. actual diagnostic process, contrast-enhanced (CEUS) is a commonly technique by radiologists. Compared with US images, CEUS videos can provide more detailed blood supply information tumors, therefore help radiologists make accurate diagnosis. this paper, we propose novel diagnosis model...
Lung cancer (LC) is one of the most serious cancers threatening human health. Histopathological examination gold standard for qualitative and clinical staging lung tumors. However, process doctors to examine thousands histopathological images very cumbersome, especially with less experience. Therefore, objective pathological diagnosis results can effectively help choose appropriate treatment mode, thereby improving survival rate patients. For current problem incomplete experimental subjects...
This paper investigates distributed online optimization for a group of agents communicating on undirected networks. The objective is to collaboratively minimize the sum locally known convex cost functions while overcoming communication bandwidth limitations. To tackle this challenge, we propose Q-DADAM algorithm, quantized adaptive momentum method that ensures interact with neighbors optimize global function collectively. Unlike many existing algorithms overlook constraints, algorithm...
Abstract Zhejiang Suichang native honey, which is included in the list of China’s National Geographical Indication Agricultural Products Protection Project, very popular. This study proposes a method Raman spectroscopy combined with machine learning algorithms to accurately detect low-concentration adulterated honey. In this study, honey collected by local beekeepers was selected for adulteration detection. The spectral data compressed Savitzky–Golay smoothing and partial least squares (PLS)...
Abstract Histopathological image analysis is the gold standard for pathologists to grade colorectal cancers of different differentiation types. However, diagnosis by highly subjective and prone misdiagnosis. In this study, we constructed a new attention mechanism named MCCBAM based on channel spatial mechanism, developed computer-aided (CAD) method CNN MCCBAM, called HCCANet. 630 histopathology images processed with Gaussian filtering denoising were included gradient-weighted class...
Abstract Surface-enhanced Raman spectroscopy (SERS), as a rapid, non-invasive and reliable spectroscopic detection technique, has promising applications in disease screening diagnosis. In this paper, an annealed silver nanoparticles/porous silicon Bragg reflector (AgNPs/PSB) composite SERS substrate with high sensitivity strong stability was prepared by immersion plating heat treatment using porous (PSB) the substrate. The combines five deep learning algorithms of improved AlexNet, ResNet,...
In this Letter, the surface-enhanced Raman scattering (SERS) signal of early breast cancer (BRC) patient serum is obtained by a composite silver nanoparticles (Ag NPs) PSi Bragg reflector SERS substrate. Based on these advantages, signals 30 normal people and BRC patients were detected After baseline correction experimental data, principal component analysis linear discriminant used to complete data processing. The results showed that diagnostic accuracy, specificity, sensitivity Ag NPs...
Cervical cancer is the fourth most common in world. Whole-slide images (WSIs) are an important standard for diagnosis of cervical cancer. Missed diagnoses and misdiagnoses often occur due to high similarity pathological images, large number readings, long reading time, insufficient experience levels pathologists. Existing models have feature extraction representation capabilities, they suffer from classification. Therefore, this work first designs image processing algorithm data...
Abstract Lung cancer and glioma are common malignancies worldwide pose a serious threat to human health. There may be certain correlation between lung patients in serum composition, but date, no study on the classification of is available. In this paper, differences relationships were analyzed from Raman spectra. The existing detection methods time consuming expensive, so we propose method based patient spectra combined with deep learning, which can screen accurately speed low cost. study,...
Abstract Medical diagnosis technology based on convolutional neural networks (CNNs) has achieved good performance. In this study, we collected serum samples from 38 glioma patients and 45 healthy controls used partial least squares (PLS) analysis to reduce the dimension of data. Different levels noise were added reduced data onto augmentation, AlexNet, ResNet, GoogLeNet fine‐tuning models applied for classification. To evaluate performance models, five‐fold cross‐validation. The accuracy...