Thomas C. Booth
A5003607819- Radiomics and Machine Learning in Medical Imaging
- Glioma Diagnosis and Treatment
- Artificial Intelligence in Healthcare and Education
- Acute Ischemic Stroke Management
- Brain Tumor Detection and Classification
- Medical Imaging Techniques and Applications
- Intracranial Aneurysms: Treatment and Complications
- MRI in cancer diagnosis
- Traumatic Brain Injury and Neurovascular Disturbances
- Machine Learning in Healthcare
- Cerebrovascular and Carotid Artery Diseases
- COVID-19 diagnosis using AI
- Advanced MRI Techniques and Applications
- Meningioma and schwannoma management
- Radiology practices and education
- Vascular Malformations Diagnosis and Treatment
- Venous Thromboembolism Diagnosis and Management
- Advanced NMR Techniques and Applications
- Enzyme function and inhibition
- Radiation Dose and Imaging
- AI in cancer detection
- Soft Robotics and Applications
- Topic Modeling
- Amino Acid Enzymes and Metabolism
- Stroke Rehabilitation and Recovery
King's College London
2018-2025
King's College Hospital NHS Foundation Trust
2016-2025
King's College Hospital
2014-2025
St Thomas' Hospital
2018-2025
National Health Service
2021-2025
King's College - North Carolina
2021-2025
University Hospitals of Cleveland
2024
University Health System
2024
University School
2024
Case Western Reserve University
2024
Convolutional neural networks (CNN) can accurately predict chronological age in healthy individuals from structural MRI brain scans. Potentially, these models could be applied during routine clinical examinations to detect deviations ageing, including early-stage neurodegeneration. This have important implications for patient care, drug development, and optimising data collection. However, existing brain-age are typically optimised scans which not part of (e.g., volumetric T1-weighted...
BackgroundWhether the large effect size of endovascular thrombectomy (EVT) for stroke due to large-vessel occlusion applies medium-vessel is unclear.MethodsIn a multicenter, prospective, randomized, open-label trial with blinded outcome evaluation, we assigned patients acute ischemic who presented within 12 hours from time that they were last known be well and had favorable baseline noninvasive brain imaging receive EVT plus usual care or alone. The primary was modified Rankin scale score...
The impact on clinical outcomes of patient selection using perfusion imaging for endovascular thrombectomy (EVT) in patients with acute ischemic stroke presenting beyond 6 hours from onset remains undetermined routine practice.
The aim was to predict survival of glioblastoma at 8 months after radiotherapy (a period allowing for completing a typical course adjuvant temozolomide), by applying deep learning the first brain MRI completion.
Rationale: Clinical outcomes in acute ischemic stroke due to medium vessel occlusion (MeVO) are often poor when treated with best medical management. Data from non-randomized studies suggest that endovascular treatment (EVT) may improve MeVO stroke, but randomized data on potential benefits and risks hitherto lacking. Thus, there is insufficient evidence guide EVT decision-making stroke. Aims: The primary aim of the ESCAPE-MeVO trial demonstrate acute, rapid patients results better clinical...
Artificial intelligence (AI) tools can triage radiology scans to streamline the patient pathway and also relieve clinician workload. Validated AI mitigate delays in reporting by flagging time-sensitive actionable findings. In this study, we aim investigate current stakeholder perspectives identify obstacles integrating clinical pathways. We created a survey ascertain of 133 clinicians across United Kingdom regarding acceptability an tool that triages MRI brain into 'normal' 'abnormal'. As...
The purpose of this study was to build a deep learning model derive labels from neuroradiology reports and assign these the corresponding examinations, overcoming bottleneck computer vision development.Reference-standard were generated by team neuroradiologists for training evaluation. Three thousand examinations labelled presence or absence any abnormality manually scrutinising radiology ('reference-standard report labels'); subset (n = 250) assigned 'reference-standard image labels'...
The growing demand for head magnetic resonance imaging (MRI) examinations, along with a global shortage of radiologists, has led to an increase in the time taken report MRI scans recent years. For many neurological conditions, this delay can result poorer patient outcomes and inflated healthcare costs. Potentially, computer vision models could help reduce reporting times abnormal examinations by flagging abnormalities at imaging, allowing radiology departments prioritise limited resources...
Abstract Estimated age from brain MRI data has emerged as a promising biomarker of neurological health. However, the absence large, diverse, and clinically representative training datasets, along with complexity managing heterogeneous data, presents significant barriers to development accurate generalisable models appropriate for clinical use. Here, we present deep learning framework trained on routine ( N up 18,890, range 18–96 years). We five separate prediction (all mean absolute error...
Abstract Purpose Autonomous navigation of catheters and guidewires can enhance endovascular surgery safety efficacy, reducing procedure times operator radiation exposure. Integrating tele-operated robotics could widen access to time-sensitive emergency procedures like mechanical thrombectomy (MT). Reinforcement learning (RL) shows potential in navigation, yet its application encounters challenges without a reward signal. This study explores the viability autonomous guidewire MT vasculature...