A5072470001- Radiomics and Machine Learning in Medical Imaging
- AI in cancer detection
- MRI in cancer diagnosis
- Magnetic properties of thin films
- MicroRNA in disease regulation
- Target Tracking and Data Fusion in Sensor Networks
- Medical Imaging Techniques and Applications
- Physics of Superconductivity and Magnetism
- Medical Image Segmentation Techniques
- Magnetic and transport properties of perovskites and related materials
- Sparse and Compressive Sensing Techniques
- PI3K/AKT/mTOR signaling in cancer
- Chronic Lymphocytic Leukemia Research
- Gene expression and cancer classification
- Digital Imaging for Blood Diseases
- Foot and Ankle Surgery
- Lung Cancer Diagnosis and Treatment
- Microwave Imaging and Scattering Analysis
- Chronic Myeloid Leukemia Treatments
- RNA Research and Splicing
- Indoor and Outdoor Localization Technologies
- Cancer Mechanisms and Therapy
- Additive Manufacturing Materials and Processes
- Structural Health Monitoring Techniques
- ZnO doping and properties
Shenyang Ligong University
2025
China Automotive Technology and Research Center
2021-2024
Northeastern University
2014-2023
Binzhou University
2020-2022
Binzhou Medical University
2020-2022
Nanjing University
2008
Background Multiparametric magnetic resonance imaging (MRI) is widely used in breast cancer screening. Accurate prediction of the axillary lymph nodes metastasis (ALNM) essential for surgery and treatment. However, there no mature effective discerning method ALNM based on multiparametric MRI. Purpose To evaluate using T1‐weighted (T1WI), T2‐weighted (T2WI), diffusion‐weighted (DWI) sequences, respectively, construct a quantitative model integrated Study Type Retrospective. Population...
Introduction Pulmonary granulomatous nodules (PGN) often exhibit similar CT morphological features to solid lung adenocarcinomas (SLA), making preoperative differentiation challenging. This study aims address this diagnostic challenge by developing a novel deep learning model. Methods proposes MAEMC-NET, model integrating generative (Masked AutoEncoder) and contrastive (Momentum Contrast) self-supervised learn image representations of intra- inter-solitary nodules. A task reconstructing...
Medical imaging examination is the primary method of diagnosis, treatment, and prevention cancer. However, amount medical image data often not enough to meet deep learning needs. This article aims expand small set in tumor segmentation based on method.This includes three main parts: cutting mirroring augmentation, augmented images, boundary reconstruction. Firstly, divided into four parts horizontally & vertically, diagonally along tumor's approximate center. Then each part mirrored get a...
Background Dynamic contrast‐enhanced magnetic resonance imaging (DCE‐MRI) is increasingly being used to detect and diagnose breast cancer. However, the effective methods based on quantitative feature analysis need be explored. Purpose To investigate a new approach for improving performance of benign malignant lesion classification by combining bilateral time–intensity curve (TIC) differentiation features with other features. Study Type Retrospective. Population In all, 112 DCE‐MRI...
The rapid development of artificial intelligence technology has improved the capability automatic breast cancer diagnosis, compared to traditional machine learning methods. Convolutional Neural Network (CNN) can automatically select high efficiency features, which helps improve level computer-aided diagnosis (CAD). It performance distinguishing benign and malignant ultrasound (BUS) tumor images, making screening possible.
OBJECTIVE:Various imaging modalities have been used to diagnose suspicious breast lesions. Purpose of this study is compare the diagnostic accuracy for cancer using mammography, ultrasonography and magnetic resonance (MRI). METHODS:Total 107 patients aged from 19 62 years are i ncluded in retrospective study. Mammography, MRI scans were performed each patient detected with suspected tumor within a month. In addition, diversity (10 types benign 5 malignant) was confirmed by pathological...
Chronic myeloid leukemia (CML) is a malignant hematological disease, and drug resistance often related to poor prognosis. MicroRNAs (miRNA) play pivotal role in transcriptional regulation, cell development, chemotherapy resistance. Here, we describe the effect of let-7b on resistant cells examine relevance as biomarker for adriamycin Results showed that was downregulated K562/ADM (KA) cells, downregulation K562 KA increased ADM The inhibition subsequently induced upregulation AURKB. Finally,...
The L1-norm regularization is usually used in positron emission tomography (PET) reconstruction to suppress noise artifacts while preserving edges. alternating direction method of multipliers (ADMM) proven be effective for solving this problem. It sequentially updates the additional variables, image pixels, and Lagrangian multipliers. Difficulties lie obtaining a nonnegative update image. And classic ADMM requires updating by greedy iteration minimize cost function, which computationally...
We have investigated thermally activated magnetization reversal influenced by the current in a Co/Pt thin film with perpendicular magnetic anisotropy at room temperature measuring extraordinary Hall effect. The could reverse fixed field lower than coercive as increasing current, which depends on current-sweep rate. characteristic for zero net is small low rate and high field. Magnetization becomes fast With constant large magnitude of propagation HP∗ reduces more 70 Oe when density J reaches...
Inconel 690 alloy is widely used in nuclear power, petrochemical, aerospace, and other fields due to its excellent high-temperature mechanical properties corrosion resistance. The with different Mo content was fabricated by laser melting deposition (LMD). effects of on the microstructure were investigated. as-deposited composed columnar dendrites grown epitaxially, M23C6 carbides are precipitated grain boundaries. With increase content, amount carbide increases gradually. At same time,...
Purpose This research aims to analyze the diagnostic contribution of different discriminative regions breast ultrasound image and develop a more effective diagnosis method taking advantage regions' complementarity. Methods First, original as inner region lesion, marginal zone posterior echo lesion were defined. The pretrained Inception‐V3 network was used these regions. Then, applied extract deep features other three images. Since there are many features, principal components analysis (PCA)...
Lung cancer is one of the most common types cancer, with highest mortality rate worldwide. MicroRNAs play notable roles in chemotherapeutic effects anticancer drugs. The present study used reverse transcription‑quantitative PCR, western blotting and cell migration invasion assays to reveal role let‑7f‑1‑3p non‑small lung (NSCLC) explore effect on doxorubicin (DOX) treatment. It was demonstrated that levels carcinoma tissues were lower compared those paracarcinoma tissues. Thus, may act as a...
Lesion segmentation is a critical step in computer-aided diagnostic(CAD) systems based on breast cancer imaging. Accurate directly affects the final determination of nature lesion. However, due to low quality ultrasound (US) images, lesion US images challenging. This paper presents an improved marker watershed algorithm for images. It uses efficient and fast curvature filtering(CF) Gaussian enhancement method pre-process image, then creates function through Newton filter computing gradient...
Computed tomography (CT) radiation dose can be reduced significantly by region of interest (ROI) CT scan. Automatically positioning the heart in scout images is an essential step to realize ROI scan heart. This paper proposed a fully
Chronic myeloid leukemia (CML) is a hematological disease, and imatinib (IM) resistance represents major problem for its clinical treatment. In the present study, role of tribbles pseudokinase 2 (TRIB2) in IM CML possible mechanism were investigated. It was found that TRIB2 highly expressed IM‑resistant patients with through Oncomine database this conclusion confirmed using reverse transcription‑quantitative PCR western blot experiments. Knockdown to increase drug sensitivity KG cells...
Considering the complementarity of mammography and breast MRI, research feature fusion diagnosis based on cross-modality images was explored to improve accuracy cancer diagnosis. 201 patients with both MRI were collected retrospectively, including 117 cases benign lesions 84 malignant ones. Two optimization strategies sequential floating forward selection (SFFS), SFFS-1 SFFS-2, defined method. Each strategy used analyze diagnostic performance single-modality then study images. Three...
With the swift development of intelligent driving, state art synchronous perception is widely used in many industrial domains even while there has out-of-sequence measurement problems due to existence unsynchronized measurements, different frequencies, or background noises which would be potential barrier further this technique. This paper presents a novel algorithm including process effectiveness validation and dual-thread particle filter (DTPF). Compared with current art, can efficiently...