A5083827056- Photoacoustic and Ultrasonic Imaging
- Optical Imaging and Spectroscopy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Optical Coherence Tomography Applications
- Acute Ischemic Stroke Management
- MRI in cancer diagnosis
- Nanoparticle-Based Drug Delivery
- Medical Imaging Techniques and Applications
- Medical Image Segmentation Techniques
- Pancreatic and Hepatic Oncology Research
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Advanced MRI Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Machine Learning in Materials Science
- Spectroscopy Techniques in Biomedical and Chemical Research
- Cerebrovascular and Carotid Artery Diseases
- Infrared Thermography in Medicine
- Venous Thromboembolism Diagnosis and Management
- Random lasers and scattering media
- Ophthalmology and Eye Disorders
- Medical Imaging and Analysis
- Gastric Cancer Management and Outcomes
- Thyroid Cancer Diagnosis and Treatment
- AI in cancer detection
- Non-Invasive Vital Sign Monitoring
Nanjing Medical University
2021-2025
Jiangsu Province Hospital
2021-2025
Southeast University
2019
Tsinghua University
2014-2016
Southern Medical University
2013
Understanding the complex interaction between nanoparticles (NPs) and tumors in vivo how it dominates delivery efficiency of NPs is critical for translation nanomedicine. Herein, we proposed an interpretable XGBoost-SHAP model by integrating information on physicochemical properties tumor genomic profile to predict efficiency. The correlation coefficients were 0.66, 0.75, 0.54 prediction maximum efficiency, at 24 168 h postinjection test sets. analysis feature importance revealed that...
Background MR imaging has been applied to determine therapeutic response glucocorticoid (GC) before treatment in thyroid‐associated ophthalmopathy (TAO), while the performance was still poor. Purpose To investigate value of T 2 ‐weighted (T WI)‐derived radiomics for pretreatment determination GC TAO patients, and compare its diagnostic with that semiquantitative parameters. Study Type Retrospective. Population A total 110 patients (49 ± 12 years; male/female, n = 48/62;...
Bioluminescence tomography (BLT) is a promising pre-clinical imaging technique for wide variety of biomedical applications, which can non-invasively reveal functional activities inside living animal bodies through the detection visible or near-infrared light produced by bioluminescent reactions. Recently, reconstruction approaches based on deep learning have shown great potential in optical modalities. However, these reports only generate data with stationary patterns constant target number,...
Accurately predicting nanomedicine accumulation is critical for guiding patient stratification and optimizing treatment strategies in the context of precision medicine. However, non-invasive prediction remains challenging, primarily due to complexity identifying relevant imaging features that predict accumulation. Here, a novel method proposed utilizes standard-of-care medical modalities, including computed tomography ultrasound, combined with radiomics-based model tumor. The validated using...
Generative adversarial networks (GANs) have recently demonstrated significant potential for producing virtual images with the same characteristics as real-life landscapes, thereby enhancing various medical tasks. To design a region-guided focal GAN (Focal-GAN) translating between CT and MRI test its clinical applicability in patients hepatocellular carcinoma (HCC). Between January 2012 October 2021, two cohorts of HCC who underwent contrast-enhanced (Center 1, n = 685) 516; Center 2, 318)...
Accurate preoperative non-invasive assessment of HER2 expression in breast cancer is crucial for personalized treatment and prognostic stratification. To evaluate the effectiveness radiomics models based on multi-parametric magnetic resonance imaging (MRI) distinguishing status invasive cancer. We conducted a retrospective analysis baseline MRI scans clinical data from 400 patients with between January 2018 December 2019. Two-dimensional regions interest were manually segmented maximum tumor...
Background Neoadjuvant chemotherapy (NAC) is a standard treatment strategy for breast cancer, with commonly used regimen consisting of 4-cycle anthracycline and cyclophosphamide (AC) followed sequentially by taxane (T) treatment. Variations in efficacy are observed at different stages AC-T regimen. Stratifying patients based on the variations could provide insights to prolong cycle AC or T treatment, potentially enhancing overall NAC. Therefore, this study aimed evaluate feasibility...
Fluorescence molecular tomography (FMT) as a noninvasive imaging modality has been widely used for biomedical preclinical applications. However, FMT reconstruction suffers from severe ill-posedness, especially when limited number of projections are used. In order to improve the quality results, discrete cosine transform (DCT) based reweighted L1-norm regularization algorithm is proposed. each iteration process, different parameters adaptively assigned according values DCT coefficients...
To construct a combined radiomics model based on pre-treatment ultrasound for predicting of advanced breast cancers sensitive to neoadjuvant chemotherapy (NAC).A total 288 eligible cancer patients who underwent NAC before surgery were enrolled in the retrospective study cohort. Radiomics features reflecting phenotype pre-NAC tumors extracted. With selected using least absolute shrinkage and selection operator (LASSO) regression, signature (Rad-score) was established ultrasound. Then,...
In order to obtain precise reconstruction results in fluorescence molecular tomography (FMT), large-scale matrix equations would be solved the inverse problem generally. Thus, much time and memory needs consumed. this paper, a permissible region extraction strategy is proposed solve problem. First, preliminary result rapidly reconstructed using weight compressed by principal component analysis or uniform sampling. And then target area considered as priori guide final reconstruction. Phantom...
High-intensity background fluorescence is generally encountered in molecular tomography (FMT), because of the accumulation fluorescent probes nontarget tissues or existence autofluorescence biological tissues. The reconstruction results are affected even distorted by fluorescence, especially when distribution targets relatively sparse. purpose this paper to reduce negative effect on FMT reconstruction.After each iteration Tikhonov regularization algorithm, 3-D discrete cosine transform...
For the reconstruction of time-domain fluorescence molecular lifetime tomography, conventional methods based on Laplace or Fourier transform utilize only part information from measurement data, and rely selection transformation factors. To make best all a direct algorithm is proposed. The yield map first reconstructed with full-time gate, then an objective function for inverse tomography (instead lifetime) developed so as to avoid dealing singularity zero points in image. Through simulations...
Peripheral arterial disease (PAD) can further cause lower limb ischemia. Quantitative evaluation of the vascular perfusion in ischemic contributes to diagnosis PAD and preclinical development new drug. In vivo time‐series indocyanine green (ICG) fluorescence imaging noninvasively monitor blood flow has a deep tissue penetration. The rate estimated from ICG images is not enough for hindlimb information relevant density also important, because angiogenesis an essential mechanism post‐ischemic...
Deep learning (DL)-based image reconstruction methods have garnered increasing interest in the last few years. Numerous studies demonstrate that DL-based function admirably optical tomographic imaging techniques, such as bioluminescence tomography (BLT). Nevertheless, nearly every existing method utilizes an explicit neural representation for problem, which either consumes much memory space or requires various complicated computations. In this paper, we present a field (NF)-based scheme BLT...