A5026130852- Flow Measurement and Analysis
- Medical Imaging Techniques and Applications
- Electrical and Bioimpedance Tomography
- Radiomics and Machine Learning in Medical Imaging
- Retinal and Macular Surgery
- Retinal Imaging and Analysis
- Advanced X-ray and CT Imaging
- Optical Coherence Tomography Applications
- Non-Destructive Testing Techniques
- Topic Modeling
- Medical Imaging and Analysis
- AI and Big Data Applications
- Lung Cancer Diagnosis and Treatment
- Advanced Technology in Applications
- Microfluidic and Bio-sensing Technologies
- Dental Radiography and Imaging
- Biomedical Text Mining and Ontologies
- Natural Language Processing Techniques
- Spine and Intervertebral Disc Pathology
- Hemodynamic Monitoring and Therapy
University of Iowa
2019-2024
Newcastle University
2021-2022
Jiangxi University of Finance and Economics
2021
Hubei University of Chinese Medicine
2021
Shanghai Jiao Tong University
2016-2017
Radiation treatment of cancers like prostate or cervix cancer requires considering nearby bone structures vertebrae. In this work, we present and validate a novel automated method for the 3D segmentation individual lumbar thoracic vertebra in computed tomography (CT) scans. It is based on single, low-complexity convolutional neural network (CNN) architecture which works well even if little application-specific training data are available. volume patch-based processing, enabling handling...
Abstract Purpose The purpose of this work was to develop and validate a deep convolutional neural network (CNN) approach for the automated pelvis segmentation in computed tomography (CT) scans enable quantification active pelvic bone marrow by means Fluorothymidine F‐18 (FLT) tracer uptake measurement positron emission (PET) scans. This is critical step calculating dose radiopharmaceutical therapy clinical applications as well external beam radiation doses. Methods An combined localization...
Convolutional neural networks (CNNs) have a proven track record in medical image segmentation. Recently, Vision Transformers were introduced and are gaining popularity for many computer vision applications, including object detection, classification, Machine learning algorithms such as CNNs or subject to an inductive bias, which can significant impact on the performance of machine models. This is especially relevant segmentation applications where limited training data available, model’s...
Electrical Impedance Tomography (EIT) is a kind of functional imaging technology which has great potential for tumor diagnosis, and physiological process monitoring. This article introduces prototype design semi-parallel EIT data acquisition system with the purpose ease hardware upgrades scalability. The consists one control module an expandable number independent front-end modules. Compared most existing systems, newly developed features symmetric parallel signal conditional circuits. All...
A new symmetric semi-parallel Electrical Impedance Tomography system has been developed and calibrated for physiological process monitoring. This article explains demonstrates the advantages of structure bandwidth expansion. The wide frequency range, 1 kHz to MHz, provides flexibility different application purposes. performance tests show that, its Signal-to-Noise Ratio (SNR) is higher than 70 dB at tested representative frequencies in range from MHz. amplitude phase measurement...
Purpose The purpose of this work was to assess the potential deep convolutional neural networks in automated measurement cerebellum tracer uptake F‐18 fluorodeoxyglucose (FDG) positron emission tomography (PET) scans. Methods Three different three‐dimensional (3D) network architectures (U‐Net, V‐Net, and modified U‐Net) were implemented compared regarding their performance 3D segmentation FDG PET For training testing, 134 scans with corresponding manual volumetric segmentations utilized....
This paper takes a project comprehensive office building of Chaoyang financial center as an example, based on the construction visualization requirements BIM technology, this analyzes modeling and Suggestions applicable to project. With help Revit software, architecture structure model whole drawing three floors underground two above ground electromechanical are completed. There is collision detection between structural subject that be established by Navisworks Manage 2016 also, causes puts...
In this work, we compared the performance of 2D and 3D versions three state-of-the-art deep neural networks on segmenting retinal external limiting membrane (ELM) using a publicly available image dataset spectral-domain optical coherence tomography (OCT) scans. Based our results, generally outperformed in Dice coefficient, mean surface distance false positive rate but lagged behind Hausdorff distance. also produce smoother surfaces based curvedness.