A5007642188- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Advanced Radiotherapy Techniques
- Lung Cancer Diagnosis and Treatment
- Advanced X-ray and CT Imaging
- Radiation Therapy and Dosimetry
- AI in cancer detection
- Advanced MRI Techniques and Applications
- Gastric Cancer Management and Outcomes
- Head and Neck Cancer Studies
- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Cancer Immunotherapy and Biomarkers
- MRI in cancer diagnosis
- Lung Cancer Treatments and Mutations
- Cancer Genomics and Diagnostics
- Blind Source Separation Techniques
- Gene expression and cancer classification
- Machine Learning in Materials Science
- Colorectal and Anal Carcinomas
- Pancreatic and Hepatic Oncology Research
- Medical Imaging and Analysis
- Cell Image Analysis Techniques
- EEG and Brain-Computer Interfaces
- Global Cancer Incidence and Screening
Stanford University
2016-2025
Qilu Hospital of Shandong University
2023-2025
Jiangxi Provincial Academy of Medical Sciences
2025
Second Affiliated Hospital of Nanchang University
2025
Nanchang University
2025
Stratford University
2024-2025
Academy of Military Medical Sciences
2024-2025
Palo Alto University
2012-2024
Sanofi (China)
2023-2024
Sanofi (France)
2023-2024
<h3>Importance</h3> The prevalence of early-stage non–small cell lung cancer (NSCLC) is expected to increase with recent implementation annual screening programs. Reliable prognostic biomarkers are needed identify patients at a high risk for recurrence guide adjuvant therapy. <h3>Objective</h3> To develop robust, individualized immune signature that can estimate prognosis in nonsquamous NSCLC. <h3>Design, Setting, and Participants</h3> This retrospective study analyzed the gene expression...
Abstract Purpose: To identify immune subtypes and investigate the landscape of squamous cell carcinomas (SCC), which share common etiology histologic features. Experimental Design: Based on gene expression profiles 1,368 patients with SCC in Cancer Genome Atlas (TCGA), we used consensus clustering to robust clusters assessed their reproducibility an independent pan-SCC cohort 938 patients. We further applied graph structure learning-based dimensionality reduction visualize distribution...
Abstract Radiographic imaging is routinely used to evaluate treatment response in solid tumors. Current metrics do not reliably predict the underlying biological response. Here, we present a multi-task deep learning approach that allows simultaneous tumor segmentation and prediction. We design two Siamese subnetworks are joined at multiple layers, which enables integration of multi-scale feature representations in-depth comparison pre-treatment post-treatment images. The network trained...
Only around 20-30% of patients with non-small-cell lung cancer (NCSLC) have durable benefit from immune-checkpoint inhibitors. Although tissue-based biomarkers (eg, PD-L1) are limited by suboptimal performance, tissue availability, and tumour heterogeneity, radiographic images might holistically capture the underlying biology. We aimed to investigate application deep learning on chest CT scans derive an imaging signature response immune checkpoint inhibitors evaluate its added value in...
Importance Tertiary lymphoid structures (TLSs) are associated with a favorable prognosis and improved response to cancer immunotherapy. The current approach for evaluation of TLSs is limited by interobserver variability high complexity cost specialized imaging techniques. Objective To develop machine learning model automated quantitative based on routine histopathology images. Design, Setting, Participants In this multicenter, international diagnostic/prognostic study, an interpretable was...
Purpose To identify quantitative imaging biomarkers at fluorine 18 ((18)F) positron emission tomography (PET) for predicting distant metastasis in patients with early-stage non-small cell lung cancer (NSCLC). Materials and Methods In this institutional review board-approved HIPAA-compliant retrospective study, the pretreatment (18)F fluorodeoxyglucose PET images 101 treated stereotactic ablative radiation therapy from 2005 to 2013 were analyzed. Data 70 who before 2011 used discovery...
Purpose To predict pathological response of breast cancer to neoadjuvant chemotherapy (NAC) based on quantitative, multiregion analysis dynamic contrast enhancement magnetic resonance imaging (DCE‐MRI). Materials and Methods In this Institutional Review Board‐approved study, 35 patients diagnosed with stage II/III were retrospectively investigated using 3T DCE‐MR images acquired before after the first cycle NAC. First, principal component (PCA) was used reduce dimensionality DCE‐MRI data...
Accurate respiration measurement is crucial in motion-adaptive cancer radiotherapy. Conventional methods for are undesirable because they either invasive to the patient or do not have sufficient accuracy. In addition, of external signal based on conventional approaches requires close contact physical device which often causes discomfort and motion during radiation dose delivery. this paper, a dc-coupled continuous-wave radar sensor was presented provide noncontact noninvasive approach...
Purpose To characterize intratumoral spatial heterogeneity at perfusion magnetic resonance (MR) imaging and investigate as a predictor of recurrence-free survival (RFS) in breast cancer. Materials Methods In this retrospective study, discovery cohort (n = 60) multicenter validation 186) were analyzed. Each tumor was divided into multiple spatially segregated, phenotypically consistent subregions on the basis MR parameters. The authors first defined multiregional interaction (MSI) matrix...
Objectives To determine the added discriminative value of detailed quantitative characterization background parenchymal enhancement in addition to tumor itself on dynamic contrast-enhanced (DCE) MRI at 3.0 Tesla identifying "triple-negative" breast cancers. Materials and Methods In this Institutional Review Board-approved retrospective study, DCE-MRI 84 women presenting 88 invasive carcinomas were evaluated by a radiologist analyzed using computer-aided techniques. Each its surrounding...
To develop and independently validate prognostic imaging biomarkers for predicting survival in patients with glioblastoma on the basis of multiregion quantitative image analysis.This retrospective study was approved by local institutional review board, informed consent waived. A total 79 from two independent cohorts were included. The discovery validation consisted 46 33 Cancer Imaging Archive (TCIA) institution, respectively. Preoperative T1-weighted contrast material-enhanced T2-weighted...
Purpose To identify the molecular basis of quantitative imaging characteristics tumor-adjacent parenchyma at dynamic contrast material–enhanced magnetic resonance (MR) and to evaluate their prognostic value in breast cancer. Materials Methods In this institutional review board-approved, HIPAA-compliant study, 10 features depicting parenchymal enhancement patterns were extracted screened for a discovery cohort 60 patients. By using data from The Cancer Genome Atlas (TCGA), radiogenomic map...
Abstract Purpose: To identify novel breast cancer subtypes by extracting quantitative imaging phenotypes of the tumor and surrounding parenchyma to elucidate underlying biologic underpinnings evaluate prognostic capacity for predicting recurrence-free survival (RFS). Experimental Design: We retrospectively analyzed dynamic contrast–enhanced MRI data patients from a single-center discovery cohort (n = 60) an independent multicenter validation 96). Quantitative image features were extracted...
To determine whether dynamic contrast enhancement magnetic resonance imaging (DCE-MRI) characteristics of the breast tumor and background parenchyma can distinguish molecular subtypes (ie, luminal A/B or basal) cancer.In all, 84 patients from one institution 126 The Cancer Genome Atlas (TCGA) were used for discovery external validation, respectively. Thirty-five quantitative image features extracted DCE-MRI (1.5 3T) including morphology, texture, volumetric features, which capture both...
Imaging plays an important role in the diagnosis and staging of cancer, as well radiation treatment planning evaluation therapeutic response. Recently, there has been significant interest extracting quantitative information from clinical standard-of-care images, i.e. radiomics, order to provide a more comprehensive characterization image phenotypes tumor. A number studies have demonstrated that deeper radiomic analysis can reveal novel features could useful diagnostic, prognostic or...
<h3>Importance</h3> Occult peritoneal metastasis frequently occurs in patients with advanced gastric cancer and is poorly diagnosed currently available tools. Because the presence of precludes possibility curative surgery, there an unmet need for a noninvasive approach to reliably identify occult metastasis. <h3>Objective</h3> To assess use deep learning model predicting based on preoperative computed tomography images. <h3>Design, Setting, Participants</h3> In this multicenter,...
Objective: We aimed to develop a deep learning-based signature predict prognosis and benefit from adjuvant chemotherapy using preoperative computed tomography (CT) images. Background: Current staging methods do not accurately the risk of disease relapse for patients with gastric cancer. Methods: proposed novel neural network (S-net) construct CT predicting disease-free survival (DFS) overall in training cohort 457 patients, independently tested it an external validation 1158 patients. An...