A5027249472- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Head and Neck Cancer Studies
- MRI in cancer diagnosis
- Radiation Dose and Imaging
- Cancer Diagnosis and Treatment
- Cholangiocarcinoma and Gallbladder Cancer Studies
- Hepatocellular Carcinoma Treatment and Prognosis
- Lung Cancer Diagnosis and Treatment
- Medical Imaging and Pathology Studies
- Pancreatic and Hepatic Oncology Research
- Head and Neck Surgical Oncology
- AI in cancer detection
- Breast Cancer Treatment Studies
- Lymphoma Diagnosis and Treatment
- Urinary and Genital Oncology Studies
- Metabolomics and Mass Spectrometry Studies
- Advanced X-ray Imaging Techniques
- Polyomavirus and related diseases
- Brain Metastases and Treatment
- Thyroid Cancer Diagnosis and Treatment
- Colorectal Cancer Surgical Treatments
- Cardiac Imaging and Diagnostics
- Photoacoustic and Ultrasonic Imaging
Sun Yat-sen University
1992-2025
Sun Yat-sen University Cancer Center
2014-2025
State Key Laboratory of Oncology in South China
2014-2023
Columbia University Irving Medical Center
2016
Guangzhou Medical University Cancer Hospital
1992
Guangzhou Medical University
1992
Abstract Radiomics (radiogenomics) characterizes tumor phenotypes based on quantitative image features derived from routine radiologic imaging to improve cancer diagnosis, prognosis, prediction and response therapy. Although radiomic must be reproducible qualify as biomarkers for clinical care, little is known about how acquisition techniques/parameters affect reproducibility. To begin fill this knowledge gap, we assessed the reproducibility of a comprehensive, commonly-used set using...
To evaluate the use of dual-energy spectral computed tomographic (CT) quantitative parameters compared with conventional CT imaging features for preoperative diagnosis metastasis to cervical lymph nodes in patients papillary thyroid cancer.This study was approved by ethics committee and all provided written informed consent. Analyses gemstone data qualitative were independently performed different groups radiologists. Excised located labeled during surgery according location on images...
Objective: To develop an imaging-derived biomarker for prediction of overall survival (OS) pancreatic cancer by analyzing preoperative multiphase contrast-enhanced computed topography (CECT) using deep learning. Background: Exploiting prognostic biomarkers guiding neoadjuvant and adjuvant treatment decisions may potentially improve outcomes in patients with resectable cancer. Methods: This multicenter, retrospective study included 1516 resected ductal adenocarcinoma (PDAC) from 5 centers...
Spectral computed tomography (CT) can be used as a valuable complement to ultrasound (US) in the detection of thyroid nodules. This study sought investigate effects various arm positions during spectral CT scans terms radiation exposure, image quality, and micronodule (≤10 mm). A total 180 patients (mean age: 48 years; 136 females) who underwent were assigned traditional position (TDN; n=60), swimmer's (SWIM; modified (M-SWIM; n=60) groups. Image quality plain, arterial, venous phases was...
This study aimed to develop and validate a dual-layer spectral CT based clinical-radiomic model for pre-treatment prediction of pathological T4 (pT4) in gastric cancer (GC) patients. retrospective included 148 surgically confirmed GC patients who underwent scanning before surgery were divided into training (n=104) test (n=44) cohorts. Subjective assessments performed on conventional 120-kV images by two readers. Clinical models developed using patient demographics, serum tumor markers, image...
Purpose: The aim of the study was to describe clinical and computed tomography (CT) findings primary lymphoepithelioma-like carcinoma (LELC) lung. Materials Methods: data CT 35 patients with histologically proven LELC lung were retrospectively reviewed. included age, sex, smoking history, signs symptoms, tumor location, size, stage, Epstein-Barr virus (EBV)-encoded small nuclear RNA status, treatment, outcomes. Pretreatment scans thorax used access site, contour, density, vascular and/or...
Abstract Background Using texture features derived from contrast-enhanced computed tomography (CT) combined with general imaging as well clinical information to predict treatment response and survival in patients hepatocellular carcinoma (HCC) who received transarterial chemoembolization (TACE) treatment. Methods From January 2014 November 2022, 289 HCC underwent TACE were retrospectively reviewed. Their was documented. treatment-naïve CTs retrieved reviewed by two independent radiologists....
Background Field-of-view optimized and constrained undistorted single-shot imaging (FOCUS) is a new sequence that shows enhanced anatomical details, improving the diffusion-weighted (DW) images. Purpose To investigate value of FOCUS (DWI) in evaluation nasopharyngeal carcinoma (NPC) compare it with echo planner (SS-EPI) DWI approach. Material Methods A total 87 patients NPC underwent magnetic resonance imaging, including SS-EPI sequences. The signal-to-noise ratio (SNR), signal-intensity...
The Vesical Imaging Reporting and Data System (VI-RADS) has been widely used for diagnosing muscle-invasive bladder cancer (MIBC), yet instances of misdiagnosis persist. However, limited research discusses the factors affecting its accuracy. This study aimed to evaluate diagnostic efficacy VI-RADS in our center preliminarily identify possible magnetic resonance imaging (MRI) characteristics misdiagnosis.From January 2018 February 2023, a consecutive series 211 participants pathologically...
To improve the assessment of primary tumor heterogeneity in magnetic resonance imaging (MRI) non-small cell lung cancer (NSCLC), we proposed a method using basic measurements from T1- and T2-weighted MRI.One hundred four NSCLC patients with different T stages were studied. Fifty-two analyzed as training group another 52 testing group. The ratios standard deviation (SD)/mean signal value T1-weighted (T1WI), T1-enhanced (T1C), (T2WI), T2 fat suppression (T2fs) images calculated. In group,...
Abstract Purpose To construct radiomics models based on MRI at different time points for the early prediction of cystic brain radionecrosis (CBRN) nasopharyngeal carcinoma (NPC). Methods A total 202 injured temporal lobes from 155 NPC patients with radiotherapy-induced lobe injury (RTLI) after intensity modulated radiotherapy (IMRT) were included in study. All randomly divided into training (n = 143) and validation 59) sets. Radiomics constructed by using features extracted T2WI two points:...
Abstract Background: Differentiating glioma recurrence from treatment-related changes can be challenging on conventional imaging. We evaluated the use of dual-energy spectral computed tomographic (CT) quantitative parameters for this differentiation. Methods: Twenty-eight patients were examined by imaging CT. The slope Hounsfield unit curve (λHU), effective atomic number (Zeff), normalized (Zeff-N), iodine concentration (IC), and (ICN) in post-treatment enhanced areas calculated....
The clinical significance of synthetic MRI in rectal adenocarcinoma remains unclear. This study aimed to explore the quantitative parameters derived from SyMRI stage according “DISTANCE” criteria and differentiation adenocarcinoma. Our preliminary demonstrated that T2 PD values obtained by might be used for noninvasive evaluation prognostic factors Furthermore, combining two relaxation metrics further improved their diagnostic performance mrN
Objective: To compare and analyze the image quality radiation dose of three scanning modes dual-source CT coronary artery retrospectively, to discuss application value TurboFlash coarse pitch mode. Methods: The imaging data 100 patients who underwent angiography (CCTA) using Siemens force retrospective gated triggering spiral scan (RES-SPIRAL), adaptive prospective sequence (SEQ) (TurboFlash) retrospectively was collected. evaluated by objective subjective methods. effective compared...
Abstract Background: Differentiating glioma recurrence from treatment-related changes can be challenging on conventional imaging. We evaluated the use of dual-energy spectral computed tomographic (CT) quantitative parameters for this differentiation. Methods: Twenty-eight patients were examined by imaging CT. The slope Hounsfield unit curve (λ HU ), effective atomic number (Z eff normalized eff-N iodine concentration (IC), and (IC N ) in post-treatment enhanced areas calculated. Pathological...
Abstract Background: Differentiating glioma recurrence from treatment-related changes can be challenging on conventional imaging. We evaluated the efficacy of quantitative parameters measured by dual-energy spectral computed tomographic (CT) for this differentiation. Methods: Twenty-eight patients were examined CT. The effective and normalized atomic number (Zeff Zeff-N, respectively); Hounsfield unit curve (λHU) slope; iodine concentration (IC ICN, respectively) in post-treatment enhanced...
Abstract Background Using texture features derived from contrast-enhanced computed tomography (CT) combined with general imaging as well clinical information to predict treatment response and survival in patients hepatocellular carcinoma (HCC) who received transarterial chemoembolization (TACE) treatment. Methods From January 2014 June 2020, 301 HCC underwent TACE were retrospectively reviewed. Their treatment-naïve CTs retrieved reviewed by two independent radiologists. Four evaluated,...
Abstract Background : This study aimed to develop and validate models preoperatively predict the risk of lymph node (LN) burden based on Z0011 clinical trial assist breast cancer surgical decision-making. Methods Data 1394 consecutive patients who presented at Sun Yat-sen University Cancer Center for Cone-beam computerized tomography (CBBCT) examinations between April 3, 2019, July 17, 2020, were retrospectively collected. 387 met inclusion criteria included randomly divided into training...