A5050138162- MRI in cancer diagnosis
- Radiomics and Machine Learning in Medical Imaging
- Advanced Neuroimaging Techniques and Applications
- Prostate Cancer Diagnosis and Treatment
- Imbalanced Data Classification Techniques
- Quantum Information and Cryptography
- Liver Disease and Transplantation
- Currency Recognition and Detection
- Astronomical Observations and Instrumentation
- Crime Patterns and Interventions
- Advanced MRI Techniques and Applications
- Computability, Logic, AI Algorithms
- Quantum Computing Algorithms and Architecture
- Muscle and Compartmental Disorders
- Anomaly Detection Techniques and Applications
- Drug-Induced Hepatotoxicity and Protection
Manipal Academy of Higher Education
2024
University College London
2002-2024
Royal London Hospital
2002
The objective of this study is to evaluate the efficacy deep learning (DL) techniques in improving quality diffusion MRI (dMRI) data clinical applications. aims determine whether use artificial intelligence (AI) methods medical images may result loss critical information and/or appearance false information. To assess this, focus was on angular resolution dMRI and a trial conducted migraine, specifically between episodic chronic migraine patients. number gradient directions had an impact...
Demonstrating and assessing self-supervised machine-learning fitting of the VERDICT (vascular, extracellular restricted diffusion for cytometry in tumors) model prostate cancer.
Microstructure models are traditionally fitted via computationally expensive non-linear least squares. Recent model fitting techniques use supervised deep learning algorithms trained on synthetic datasets, however the training data distribution affects parameter estimates. Self-supervised can address this by extracting labels directly from input data. We introduce a self-supervised machine algorithm for VERDICT MRI prostate to diffusion-weighted MRI. On simulated data, our approach improves...
Diffusion MRI has shown promising results for characterizing prostate cancer. However, diagnostic clinical apparent diffusion coefficient (ADC) limited specificity and interpretability. Towards addressing these limitations, we aim to unravel ADC into microstructural components using histology. Histology from two prostatectomies with cancer (Gleason 3+4, 4+3) were analysed in benign, inflammation regions. Cell tissue properties used decouple intracellular, extracellular-extravascular ADCs....
Purpose: Demonstrating and assessing self-supervised machine learning fitting of the VERDICT (Vascular, Extracellular Restricted DIffusion for Cytometry in Tumours) model prostate. Methods: We derive a neural network (ssVERDICT) that estimates parameter maps without training data. compare performance ssVERDICT to two established baseline methods diffusion MRI models: conventional nonlinear least squares (NLLS) supervised deep learning. do this quantitatively on simulated data, by comparing...