A5102004786- Advanced Radiotherapy Techniques
- Medical Imaging Techniques and Applications
- Radiomics and Machine Learning in Medical Imaging
- Breast Cancer Treatment Studies
- Lung Cancer Diagnosis and Treatment
- Digital Radiography and Breast Imaging
- AI in cancer detection
- Advances in Oncology and Radiotherapy
- Domain Adaptation and Few-Shot Learning
- Advanced X-ray and CT Imaging
- Advanced Graph Neural Networks
- Radiation Dose and Imaging
- Food Supply Chain Traceability
- COVID-19 diagnosis using AI
- Ultrasound Imaging and Elastography
- Esophageal Cancer Research and Treatment
- MRI in cancer diagnosis
- Calpain Protease Function and Regulation
- Machine Learning in Healthcare
- Machine Learning and ELM
- Recommender Systems and Techniques
- Neonatal Respiratory Health Research
- Digital Media Forensic Detection
- Integrated Circuits and Semiconductor Failure Analysis
- Spinal Fractures and Fixation Techniques
University of Technology Sydney
2021-2025
Second Affiliated Hospital of Nanjing Medical University
2024
Air Force Medical University
2011-2024
General Hospital of Central Theater Command
2024
Wenzhou Medical University
2024
Chinese University of Hong Kong
2023
Stanford University
2023
Hong Kong University of Science and Technology
2023
Sun Yat-sen University Cancer Center
2018-2023
Sun Yat-sen University
2018-2023
ABUS, or Automated breast ultrasound, is an innovative and promising method of screening for examination. Comparing to common B-mode 2D ABUS attains operator-independent image acquisition also provides 3D views the whole breast. Nonetheless, reviewing images particularly time-intensive errors by oversight might occur. For this study, we offer convolutional network, which used automated cancer detection, in order accelerate meanwhile obtain high detection sensitivity with low false positives...
Purpose Breast cancer is the most common and leading cause of cancer‐related deaths for women all over world. Recently, automated breast ultrasound (ABUS) has become a new promising screening modality whole examination. However, reviewing volumetric ABUS time‐consuming lesions could be missed during Therefore, computer‐aided detection in volume extremely expected to help clinician screening. Methods We develop novel end‐to‐end 3D convolutional network volume, order accelerate meanwhile...
Inflammation takes responsibility for the seawater aspiration-induced lung injury. Tanshinone IIA (TIIA) can protect lipopolysaccharide-induced injury in mice through inhibition of inflammation, but it is not reported whether TIIA have a protective effect on induced by aspiration. Macrophage migration inhibitory factor (MIF) plays an important role acute In this study, we observed and MIF it. Seawater was aspirated into trachea rats to make model. administered investigate its beneficial...
The purpose of this study was to explore the correlation between respiration-induced target motion and volume variation with dosimetric variance on breast organ at risk (OAR) during free breathing.After breast-conserving surgery, seventeen patients underwent respiration-synchronized 4DCT simulation scans breathing. Treatment planning constructed using end inspiration scan, then copied applied other phases dose distribution calculated separately evaluate dose-volume histograms (DVH)...
The aim of this study was to explore the characteristic 3DCT scanning phases and estimate comparative amount respiration motion information included in 4DCT by comparing volumetric positional difference between volumes from for radiotherapy non-small-cell lung cancer (NSCLC). A total 28 patients with NSCLC sequentially underwent simulation scans thorax during free breathing. images respiratory signal data were reconstructed sorted into 10 throughout a cycle. GTV-3D 3DCT, GTV-0%, GTV-20%,...
To evaluate the diagnostic performance of a deep learning (DL) model for breast US across four hospitals and assess its value to readers with different levels experience.
To compare the target volume, position and matching index of patient-specific internal gross tumor volume (IGTV) based on three-dimensional (3D) four-dimensional (4D) computed tomography (CT) images for primary esophageal cancer. Twenty-nine patients with thoracic cancer underwent 3DCT 4DCT scans during free breathing. IGTVs were constructed using three approaches: combining volumes from 10 respiratory phases dataset to produce IGTV10; IGTV2 was acquired by two extreme phases; IGTV3D created...
Leveraging contextual dependencies is a commonly used technique to enhance the performance of image segmentation. However, existing solutions do not effectively catch class-level association between pixels along boundary across objects different classes but focus more on local pixel-to-pixel relation. This work proposes Class-Aware Affinity module (CAA) that considers both relation and pixel-to-class association. We try argue relations still (e.g. similarity, attention, or affiliation)...
This study was performed to explore and compare the dosimetric variance caused by respiratory movement in breast during forward-planned IMRT after breast-conserving surgery. A total of 17 enrolled patients underwent 3DCT simulation scans followed 4DCT free breathing. The treatment planning constructed using images copied applied end expiration (EE) inspiration (EI) dose distributions were calculated separately. CTV volume amplitude very small (11.93 ± 28.64 cm3), percentage change volumes...
Objective: To compare differences in setup error assessment and correction between planar kilovolt images cone beam computed tomography for external partial breast irradiation during free breathing. Methods: Nineteen patients who received after breast-conserving surgery were recruited. Interfraction was acquired using tomography. After online correction, the residual calculated, compared. The margin quantified images. Results: largest observed anteroposterior direction both imaging (−1.45...
Abstract: Soil temperature is a key factor for best planting dates decision-making in the large scale farming areas of northeast China because high latitudes and frigid environment. Continuous data were collected from wireless sensor network (WSN)-based monitoring system to exactly analyze understand soil whole farmland. Using classical statistics geo-statistics methods, real-time analyzed with three aspects, i.e. temporal variation, spatial variation spatio-temporal variation. Temporal...
The aim of this study was to investigate the detection efficacy deep learning (DL) for automatic breast ultrasound (ABUS) and factors affecting its efficacy.Females who underwent ABUS handheld from May 2016 June 2017 (N = 397) were enrolled divided into training (n 163 patients with cancer 33 benign lesions), test 57) control 144) groups. A convolutional neural network optimized detect lesions in ABUS. sensitivity false positives (FPs) evaluated compared different tissue compositions, lesion...
Abstract Introduction The study aims to compare the positional and volumetric differences of tumour volumes based on maximum intensity projection ( MIP ) four‐dimensional CT (4 DCT 18 F ‐fluorodexyglucose ‐ FDG positron emission tomography PET / images for primary non‐small cell lung cancer NSCLC ). Methods Ten patients with underwent 4 scans thorax same day. Internal gross target IGTVs tumours were contoured generate IGTV . Gross GTVs GTV determined nine different threshold methods using...
Objective: To measure the intra-fraction displacements of mediastinal metastatic lymph nodes by using four-dimensional CT (4D-CT) in non-small cell lung cancer (NSCLC).Materials and Methods: Twenty-four patients with NSCLC, who were to be treated three dimensional conformal radiation therapy (3D-CRT), underwent a 4D-CT simulation during free breathing.The delineated on images 10 phases breath cycle.The grouped as upper, middle lower groups depending regions.The center node left-right (LR),...
Purpose: To investigate the correlation of gross tumor volume (GTV) motion with structure interest (SOI) and variation for middle distal esophageal cancers using four-dimensional computed tomography (4DCT). Patients methods: Thirty-three patients or carcinoma underwent 4DCT simulation scan during free breathing. All image sets were registered 0% phase, GTV, apex diaphragm, lung, heart delineated on each phase data. The position GTV SOI was identified in all phases, lung also achieved....
Myocardial inflammation during myocardial infarction (MI) could be inhibited by regulating arachidonic acid (AA) metabolism. Recent studies demonstrated that Sini Decoction (SND) was identified to an effective prescription for treating heart failure (HF) caused MI. But the anti-inflammatory mechanism of SND remained unclear. The work designed investigate through AA metabolism pathway in vitro and vivo experiments. An inflammatory injury model H9c2 cells established lipopolysaccharide...