A5058573976- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Non-Invasive Vital Sign Monitoring
- Advanced Radiotherapy Techniques
- COVID-19 diagnosis using AI
- MRI in cancer diagnosis
- Air Quality Monitoring and Forecasting
- Glioma Diagnosis and Treatment
- 3D Surveying and Cultural Heritage
- Advanced Chemical Sensor Technologies
- Lung Cancer Treatments and Mutations
- Advanced X-ray and CT Imaging
- Microwave Engineering and Waveguides
- Hepatocellular Carcinoma Treatment and Prognosis
- Lung Cancer Diagnosis and Treatment
- Phonocardiography and Auscultation Techniques
- Advanced MRI Techniques and Applications
- Brain Metastases and Treatment
- Erosion and Abrasive Machining
- Innovative Microfluidic and Catalytic Techniques Innovation
- Magnetic properties of thin films
- Artificial Intelligence in Healthcare and Education
- Spinal Hematomas and Complications
- Flow Measurement and Analysis
- Heat Transfer and Boiling Studies
Ministry of Education of the People's Republic of China
2023-2025
Zhejiang University
2023-2025
Shandong University of Science and Technology
2025
Second Affiliated Hospital of Zhejiang University
2019-2024
Northeastern University
2024
People's Liberation Army No. 150 Hospital
2020-2021
University of Alberta
2021
Chongqing University of Posts and Telecommunications
2021
University of North Carolina at Chapel Hill
2012-2019
Shandong University
2016-2019
Summary Background Currently, the prevention and control of novel coronavirus disease (COVID-19) outside Hubei province in China, other countries have become more critically serious. We developed validated a diagnosis aid model without computed tomography (CT) images for early identification suspected COVID-19 pneumonia (S-COVID-19-P) on admission adult fever patients made available via an online triage calculator. Methods Patients admitted from Jan 14 to February 26, 2020 with...
Currently, the need to prevent and control spread of 2019 novel coronavirus disease (COVID-19) outside Hubei province in China internationally has become increasingly critical. We developed validated a diagnostic model that does not rely on computed tomography (CT) images aid early identification suspected COVID-19 pneumonia (S-COVID-19-P) patients admitted adult fever clinics made available via an online triage calculator.Patients from January 14 February 26, 2020 with epidemiological...
To investigate the effect of machine learning methods on predicting Overall Survival (OS) for non-small cell lung cancer based radiomics features analysis.A total 339 radiomic were extracted from segmented tumor volumes pretreatment computed tomography (CT) images. These quantify phenotypic characteristics medical images using shape and size, intensity statistics textures. The performance 5 feature selection 8 investigated OS prediction. predicted was evaluated with concordance index between...
This study aimed to investigate the effectiveness of using delta-radiomics predict overall survival (OS) for patients with recurrent malignant gliomas treated by concurrent stereotactic radiosurgery and bevacizumab, machine learning methods feature selection building classification models.The pre-treatment, one-week post-treatment, two-month post-treatment T1 T2 fluid-attenuated inversion recovery (FLAIR) MRI were acquired. 61 radiomic features (intensity histogram-based, morphological,...
To improve the prediction accuracy of respiratory signals using adaptive boosting and multi-layer perceptron neural network (ADMLP-NN) for gated treatment moving target in radiation therapy. The acquired a real-time position management (RPM) device from 138 previous 4DCT scans were retrospectively used this study. ADMLP-NN was composed several artificial networks (ANNs) which as weaker predictors to compose stronger predictor. signal initially smoothed Savitzky-Golay finite impulse response...
Compared with traditional manned airborne photogrammetry, unmanned aerial vehicle remote sensing (UAVRS) has the advantages of lower cost and higher flexibility in data acquisition. It has, therefore, found various applications fields such as three-dimensional (3D) mapping, emergency management, so on. However, due to instability UAVRS platforms low accuracy onboard exterior orientation (EO) observations, use direct georeferencing image leads large location errors. Light detection ranging...
Satellite platform vibration induced by the onboard dynamic components and exterior perturbation deteriorates stability causes attitude jitter, resulting in image distortion geometric accuracy degradation. This paper presents an jitter detection method based on images dense ground controls, which requires neither high-performance measurement devices nor specific sensor configuration like parallax observation. Attitude variations will result space discrepancies at control points, from can be...
Currently, in the domain of surface defect detection on hot-rolled strip steel, detecting small-target defects under complex background conditions and effectively balancing computational efficiency with accuracy presents a significant challenge. This study proposes CTL-YOLO based YOLO11, aimed at efficiently accurately blemishes steel industrial applications. Firstly, CGRCCFPN feature integration network is proposed to achieve multi-scale global fusion while preserving detailed information....
The objective of this study was to evaluate the discriminative capabilities radiomics signatures derived from three distinct machine learning algorithms and identify a robust signature capable predicting pathological complete response (pCR) after neoadjuvant chemoradiotherapy in patients diagnosed with locally advanced rectal cancer (LARC). In retrospective study, 211 LARC were consecutively enrolled divided into training cohort (n = 148) validation 63). From pretreatment contrast-enhanced...
Introduction: This study aimed to develop and validate the combination of radiomic features clinical characteristics that can predict patient survival in hepatocellular carcinoma (HCC) with portal vein tumor thrombosis (PVTT) treated stereotactic body radiotherapy (SBRT). Materials Methods: The prediction model was developed a primary cohort 70 patients HCC PVTT SBRT, using data acquired between December 2015 June 2017. were extracted from computed tomography (CT) scans. A least absolute...
To improve the prediction accuracy of respiratory signals by adapting multi-layer perceptron neural network (MLP-NN) model to changing signals. We have previously developed an MLP-NN predict obtained from a real-time position management (RPM) device. Preliminary testing results indicated that poor may be observed after several seconds for irregular breathing patterns as only set fixed data was used in one-time training. accuracy, we introduced continuous learning technique using updated...
The dynamic tracking of tumors with radiation beams in therapy requires the prediction real-time target locations prior to beam delivery, as treatment involving and gating results time latency.In this study, a deep learning model that was based on temporal convolutional neural network developed predict internal by using multiple external markers.Respiratory signals from 69 fractions 21 patients cancer who were treated CyberKnife Synchrony device (Accuray Incorporated) used train test model....
To predict real-time 3D deformation field maps (DFMs) using Volumetric Cine MRI (VC-MRI) and adaptive boosting multi-layer perceptron neural network (ADMLP-NN) for 4D target tracking. One phase of a prior 4D-MRI is set as the phase,
This study aimed to examine the effect of weight initializers on respiratory signal prediction performance using long short-term memory (LSTM) model.Respiratory signals collected with CyberKnife Synchrony device during 304 breathing motion traces were used in this study. The effectiveness four (Glorot, He, Orthogonal, and Narrow-normal) LSTM model was investigated. evaluated by normalized root mean square error (NRMSE) between ground truth predicted signal.Among initializers, He initializer...