A5100730127- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Gastric Cancer Management and Outcomes
- Advanced X-ray and CT Imaging
- Head and Neck Cancer Studies
- AI in cancer detection
- Medical Imaging Techniques and Applications
- Lung Cancer Treatments and Mutations
- Colorectal Cancer Screening and Detection
- MRI in cancer diagnosis
- Gastrointestinal Tumor Research and Treatment
- Photoacoustic and Ultrasonic Imaging
- COVID-19 diagnosis using AI
- Renal cell carcinoma treatment
- Optical Imaging and Spectroscopy Techniques
- Advanced Fluorescence Microscopy Techniques
- Colorectal Cancer Surgical Treatments
- Colorectal Cancer Treatments and Studies
- HER2/EGFR in Cancer Research
- Sarcoma Diagnosis and Treatment
- Cancer-related molecular mechanisms research
- Artificial Intelligence in Healthcare and Education
- Medical Image Segmentation Techniques
- Glioma Diagnosis and Treatment
- Colorectal and Anal Carcinomas
Shandong Institute of Automation
2016-2025
Chinese Academy of Sciences
2016-2025
University of Chinese Academy of Sciences
2016-2025
Beijing Academy of Artificial Intelligence
2019-2025
Institute of Forest Ecology, Environment and Protection
2025
Chinese Academy of Forestry
2025
State Forestry and Grassland Administration
2025
Nanjing University of Chinese Medicine
2025
Sichuan University
2024
China Southern Power Grid (China)
2017-2024
Purpose: To identify MRI-based radiomics as prognostic factors in patients with advanced nasopharyngeal carcinoma (NPC).Experimental Design: One-hundred and eighteen (training cohort: n = 88; validation 30) NPC were enrolled. A total of 970 features extracted from T2-weighted (T2-w) contrast-enhanced T1-weighted (CET1-w) MRI. Least absolute shrinkage selection operator (LASSO) regression was applied to select for progression-free survival (PFS) nomograms. Nomogram discrimination calibration...
Accurate lung nodule segmentation from computed tomography (CT) images is of great importance for image-driven cancer analysis. However, the heterogeneity nodules and presence similar visual characteristics between their surroundings make it difficult robust segmentation. In this study, we propose a data-driven model, termed Central Focused Convolutional Neural Networks (CF-CNN), to segment heterogeneous CT images. Our approach combines two key insights: 1) proposed model captures diverse...
Epidermal growth factor receptor (EGFR) genotyping is critical for treatment guidelines such as the use of tyrosine kinase inhibitors in lung adenocarcinoma. Conventional identification EGFR genotype requires biopsy and sequence testing which invasive may suffer from difficulty accessing tissue samples. Here, we propose a deep learning model to predict mutation status adenocarcinoma using non-invasive computed tomography (CT). We retrospectively collected data 844 patients with pre-operative...
BackgroundOccult peritoneal metastasis (PM) in advanced gastric cancer (AGC) patients is highly possible to be missed on computed tomography (CT) images. Patients with occult PMs are subject late detection or even improper surgical treatment. We therefore aimed develop a radiomic nomogram preoperatively identify AGC patients.Patients and methodsA total of 554 from 4 centers were divided into 1 training, internal validation, 2 external validation cohorts. All patients' PM status was firstly...
•Evaluation of the lymph node metastasis (LNM) is basis individual treatment locally advanced gastric cancer (LAGC).•Deep leaning radiomic nomogram (DLRN) based on CT images can preoperatively determine number LNM in LAGC.•DLRN significantly superior to routinely used clinical N stages, tumor size, and model.•DLRN associated with overall survival LAGC. BackgroundPreoperative evaluation (LAGC). However, preoperative determination method not accurate enough.Patients methodsWe enrolled 730 LAGC...
We aimed to evaluate the value of deep learning on positron emission tomography with computed (PET/CT)-based radiomics for individual induction chemotherapy (IC) in advanced nasopharyngeal carcinoma (NPC).
Abstract Purpose: We established a CT-derived approach to achieve accurate progression-free survival (PFS) prediction EGFR tyrosine kinase inhibitors (TKI) therapy in multicenter, stage IV EGFR-mutated non–small cell lung cancer (NSCLC) patients. Experimental Design: A total of 1,032 CT-based phenotypic characteristics were extracted according the intensity, shape, and texture NSCLC pretherapy images. On basis these CT features from 117 EGFR-mutant patients, signature was proposed using Cox...
Background Tumor mutational burden (TMB) is a significant predictor of immune checkpoint inhibitors (ICIs) efficacy. This study investigated the correlation between deep learning radiomic biomarker and TMB, including its predictive value for ICIs treatment response in patients with advanced non-small-cell lung cancer (NSCLC). Methods CT images from 327 TMB data (TMB median=6.067 mutations per megabase (range: 0 to 42.151)) were retrospectively collected randomly divided into training...
Abstract Artificial intelligence (AI) is rapidly advancing, yet its applications in radiology remain relatively nascent. From a spatiotemporal perspective, this review examines the forces driving AI development and integration with medicine radiology, particular focus on advancements addressing major diseases that significantly threaten human health. Temporally, advent of foundational model architectures, combined underlying drivers development, accelerating progress interventions their...
To investigative the predictive ability of radiomics signature for preoperative staging (I-IIvs.III-IV) primary colorectal cancer (CRC).This study consisted 494 consecutive patients (training dataset: n=286; validation cohort, n=208) with stage I-IV CRC. A was generated using LASSO logistic regression model. Association between and CRC explored. The classification performance explored respect to receiver operating characteristics(ROC) curve.The 16-feature-based an independent predictor CRC,...
Discovering evolving communities in dynamic networks is essential to important applications such as analysis for web content and disease progression. Evolutionary clustering uses the temporal smoothness framework that simultaneously maximizes accuracy at current time step minimizes drift between two successive steps. In this paper, we propose evolutionary nonnegative matrix factorization (ENMF) frameworks detecting communities. To address theoretical relationship among algorithms, first...
OBJECTIVE: To compare 2D and 3D radiomics features prognostic performance differences in CT images of non-small cell lung cancer (NSCLC). METHOD: We enrolled 588 NSCLC patients from three independent cohorts. Two sets 463 two different institutes were used as the training cohort. The remaining cohort with 125 was set validation A total 1014 (507 507 correspondingly) assessed. Based on dichotomized survival data, indicators calculated for each patient by trained classifiers. area under...
Many complex systems are composed of coupled networks through different layers, where each layer represents one many possible types interactions. A fundamental question is how to extract communities in multi-layer networks. The current algorithms either collapses into a single-layer network or extends the for by using consensus clustering. However, these approaches have been criticized ignoring connection among various thereby resulting low accuracy. To attack this problem, quantitative...
PurposeTo evaluate the performance of a multi-parametric MRI (mp-MRI)-based radiomics signature for discriminating between clinically significant prostate cancer (csPCa) and insignificant PCa (ciPCa).Materials methodsTwo hundred eighty patients with pathology-proven were enrolled randomly divided into training test cohorts. Eight nineteen features extracted from mp-MRI each patient. The minority group in cohort was balanced via synthetic over-sampling technique (SMOTE) method. We used...