A5100424095- Radiomics and Machine Learning in Medical Imaging
- Colorectal Cancer Surgical Treatments
- AI in cancer detection
- Colorectal and Anal Carcinomas
- Colorectal Cancer Screening and Detection
- Advanced X-ray and CT Imaging
- Thyroid Cancer Diagnosis and Treatment
- Surgical Simulation and Training
- Inflammatory Bowel Disease
- Fire Detection and Safety Systems
- Image Processing and 3D Reconstruction
- Video Surveillance and Tracking Methods
- Osteoarthritis Treatment and Mechanisms
- 3D Shape Modeling and Analysis
- Medical Imaging and Analysis
- Video Analysis and Summarization
- Anatomy and Medical Technology
- Health, Environment, Cognitive Aging
- Solar-Powered Water Purification Methods
- Pelvic and Acetabular Injuries
- Biomarkers in Disease Mechanisms
- Diabetes Management and Education
- Medicinal Plants and Bioactive Compounds
- Anorectal Disease Treatments and Outcomes
- Cloud Computing and Remote Desktop Technologies
The University of Melbourne
2025
College of Tourism
2025
Capital Normal University
2025
Beijing Institute of Water
2025
Beihang University
2016-2024
Chinese Academy of Medical Sciences & Peking Union Medical College
2024
State Key Laboratory of Virtual Reality Technology and Systems
2021-2024
First Affiliated Hospital of Anhui Medical University
2023-2024
Anhui Medical University
2023-2024
Second Military Medical University
2019-2023
Interfacial solar vapor generation offers a promising zero-CO2-consuming energy conversion technology for the production of renewable clean water. The key boosting efficiency relies on rational design materials composition and structure at micro/nanoscale to improve light utilization. Here, we demonstrate Janus evaporator based hydrophilic carbon-black-decorated copper oxide (C@CuO) membrane as light-absorbing layer an opposite hydrophobic polymer nanofibers thermal insulation layer, which...
Thyroid ultrasonography is a widely used clinical technique for nodule diagnosis in thyroid regions. However, it remains difficult to detect and recognize the nodules due low contrast, high noise, diverse appearance of nodules. In today's practice, senior doctors could pinpoint by analyzing global context features, local geometry structure, intensity changes, which would require rich experience accumulated from hundreds thousands case studies. To alleviate doctors' tremendous labor...
Abstract Background: Early diagnosis and accurate staging are important to improve the cure rate prognosis for pancreatic cancer. This study was performed develop an automatic imaging processing technique system, allowing this system read computed tomography (CT) images correctly make of cancer faster. Methods: The establishment artificial intelligence (AI) based on sequential contrast-enhanced CT were composed two processes: training verification. During process, our used all 4385 from 238...
Abstract Background The purpose of this study was to compare the diagnostic efficiency a thyroid ultrasound computer‐aided diagnosis (CAD) system with that 1 radiologist. Methods This retrospectively reviewed 342 surgically resected nodules from July 2013 December at our center. were assessed on typical images using CAD and by experienced radiologist stratified risk malignancy Thyroid Imaging Reporting Data Systems (TIRADS) American Association (ATA) guidelines. Results radiologist, TI‐RADS...
Abstract Background: Artificial intelligence-assisted image recognition technology is currently able to detect the target area of an and fetch information make classifications according features. This study aimed use deep neural networks for computed tomography (CT) diagnosis perigastric metastatic lymph nodes (PGMLNs) simulate by radiologists, acquire more accurate identification results. Methods: A total 1371 images suspected node metastasis from enhanced abdominal CT scans were identified...
Background: An artificial intelligence system of Faster Region-based Convolutional Neural Network (Faster R-CNN) is newly developed for the diagnosis metastatic lymph node (LN) in rectal cancer patients. The primary objective this study was to comprehensively verify its accuracy clinical use. Methods: Four hundred fourteen patients with discharged between January 2013 and March 2015 were collected from 6 centers, magnetic resonance imaging data pelvic LNs each patient identified by R-CNN....
High-resolution MRI is regarded as the best method to evaluate whether there an involved circumferential resection margin in rectal cancer.We explored application of faster region-based convolutional neural network identify positive margins high-resolution images.This was a retrospective study.The study conducted at single surgical unit public university hospital.We studied 240 patients with cancer Affiliated Hospital Qingdao University from July 2016 August 2018, who were determined have...
The purpose of this article is to develop a deep learning automatic segmentation model for the Crohn's disease (CD) lesions in computed tomography enterography (CTE) images. Additionally, radiomics features extracted from segmented CD will be analyzed and multiple machine classifiers built distinguish activity.This was retrospective study with 2 sets CTE image data. Segmentation datasets were used establish nnU-Net neural network's model. classification dataset processed using obtain results...
Abstract Background Preoperative diagnoses of metastatic lymph nodes (LNs) by the most advanced deep learning technology Faster Region‐based Convolutional Neural Network (Faster R‐CNN) have not yet been reported. Materials and Methods In total, 545 patients with pathologically confirmed rectal cancer between January 2016 March 2019 were included randomly allocated a split ratio 2:1 to training validation sets, respectively. The MRI images for LNs evaluated R‐CNN. Multivariate regression...
The intelligent synthesis/generation of daily-life motion sequences is fundamental and urgently needed for many VR/metaverse-related applications. However, existing approaches commonly focus on monotonic generation (e.g., walking, jumping, etc.) based single instruction-like text, which still not enough can't meet practical demands. To this end, we propose a cohesive human sequence synthesis framework free-form sequential texts while ensuring semantic connection natural transitions between...
Tumor sprouting can reflect independent risk factors for tumor malignancy and a poor clinical prognosis. However, there are significant differences difficulties associated with manually identifying sprouting. This study used the Faster region convolutional neural network (RCNN) model to build colorectal cancer artificial intelligence recognition framework based on pathological sections automatically identify budding area assist in diagnosis treatment of cancer. We retrospectively collected...
Abstract Objectives This study developed a deep learning radiomics (DLR) model utilizing baseline computed tomography enterography (CTE) to non-invasively predict stratified healing in Crohn’s disease (CD) patients following infliximab (IFX) treatment. Methods The included 246 CD diagnosed at three hospitals. From the first two hospitals, 202 were randomly divided into training cohort ( n = 141) and testing 61) 7:3 ratio. remaining 44 from third hospital served as validation cohort....
Precision medicine still remains to be a prevalent treatment strategy which has been continuously pushed forward by the upcoming targeted therapies. To improve precision and quantitative level, researches in radiomics radiogenomics have devoted much of their endeavors transform digital standard medical images mineable high-dimensional data way extracting mathematically features. However, most prior efforts could not effectively combine multi-source sets together generate satisfactory results...
To build and validate an MRI-based radiomics nomogram to predict the therapeutic response neoadjuvant chemoradiotherapy (nCRT) in rectal mucinous adenocarcinoma (RMAC).Totally, 92 individuals with pathologically confirmed RMAC administered surgical resection upon nCRT two different centers were assessed retrospectively (training set, n = 52, validation 40). Rectal MRI was performed pre-nCRT. Radiomics parameters obtained from high-resolution T2-weighted images selected construct a signature....
Objective: To examine the value and clinical application of convolutional neural network in pathological diagnosis metastatic lymph nodes gastric cancer. Methods: Totally 124 patients with advanced cancer who underwent radical gastrectomy plus D2 lymphadenectomy at Affiliated Hospital Qingdao University from July 2016 to December 2018 were selected study. According chronological order, first 80 cases served as learning group. The remaining 44 verification There 45 males 35 females study...
Thyroid nodule classification in ultrasound images has gained great momentum based on deep convolutional neural networks recent years. Nevertheless, it is still challenging to intelligently classify the fine-grained thyroid nodules, which significant for subsequent clinical treatments. The difficulties mainly stem from four aspects: few training dataset, highly-variable appearances of intra-class overall-similar characteristics inter-class and low resolution contrast degree ultrasonic as...
This study proposes a series of geometry and physics modeling methods for personalized cardiovascular intervention procedures, which can be applied to virtual endovascular simulator. Based on clinical computed tomography angiography (CTA) data, mesh models the system were constructed semi-automatically. By coupling 4D magnetic resonance imaging (MRI) sequences corresponding complete cardiac cycle with related models, hybrid kinetic model was built drive kinematics dynamics simulation. On...