A5024690120- Industrial Vision Systems and Defect Detection
- Medical Imaging Techniques and Applications
- MRI in cancer diagnosis
- Transportation Systems and Safety
- Sensor Technology and Measurement Systems
- Non-Destructive Testing Techniques
- Advanced MRI Techniques and Applications
- Gait Recognition and Analysis
- Advanced X-ray and CT Imaging
- Hydrocarbon exploration and reservoir analysis
- Pediatric Urology and Nephrology Studies
- Mineral Processing and Grinding
- Ultrasonics and Acoustic Wave Propagation
- Advanced Measurement and Detection Methods
- Fault Detection and Control Systems
- Power Line Communications and Noise
- Geophysical and Geoelectrical Methods
- Advanced Neural Network Applications
- Advanced Neuroimaging Techniques and Applications
- Human Pose and Action Recognition
- Medical Image Segmentation Techniques
- Renal and Vascular Pathologies
- Functional Brain Connectivity Studies
- EEG and Brain-Computer Interfaces
- Renal cell carcinoma treatment
University of Nottingham
2018-2024
Purpose Total kidney volume (TKV) is an important measure in renal disease detection and monitoring. We developed a fully automated method to segment the kidneys from T 2 ‐weighted MRI calculate TKV of healthy control (HC) chronic (CKD) patients. Methods This uses machine learning, specifically 2D convolutional neural network (CNN), accurately left right data. The data set consisted 30 HC subjects CKD model was trained on 50 manually defined segmentations. subsequently evaluated test sets,...
T
Abstract Simultaneous EEG‐fMRI allows multiparametric characterisation of brain function, in principle enabling a more complete understanding responses; unfortunately the hostile MRI environment severely reduces EEG data quality. Simply eliminating segments containing gross motion artefacts [MAs] (generated by movement system and head scanner's static magnetic field) was previously believed sufficient. However recently importance removal all MAs has been highlighted new methods developed. A...
Measures of total kidney volume (TKV) help to evaluate disease progression, and masks define the are important for automatic assessment multiparametric images collected in same data space. For accurate measures multicentre studies an automated method which is vendor agnostic robust against image artefacts needed. Here a single-vendor convolutional neural network retrained shown be on two vendors scanner associated with wrapping phase-encode direction.
The performance of multi-task learning in Convolutional Neural Networks (CNNs) hinges on the design feature sharing between tasks within architecture. number possible patterns are combinatorial depth network and tasks, thus hand-crafting an architecture, purely based human intuitions task relationships can be time-consuming suboptimal. In this paper, we present a probabilistic approach to task-specific shared representations CNNs for learning. Specifically, propose "stochastic filter...
Manual segmentation of the kidneys is very time consuming and reader dependent, this renders measurements total kidney volume (TKV) in large multi-site studies impractical. Here we use a convolutional neural network (CNN), trained on data from single MRI vendor, to segment volunteers scanned with harmonised FSE image protocol MR scanners three different vendors (GE, Philips Siemens). The were manually segmented by two readers, both which demonstrated significant difference TKV across...