A5089002800- Advanced Radiotherapy Techniques
- Radiomics and Machine Learning in Medical Imaging
- Medical Imaging Techniques and Applications
- Radiation Therapy and Dosimetry
- Medical Image Segmentation Techniques
- Advanced MRI Techniques and Applications
- Advanced X-ray and CT Imaging
- Lung Cancer Diagnosis and Treatment
- Medical Imaging and Analysis
- MRI in cancer diagnosis
- Glioma Diagnosis and Treatment
- Colorectal and Anal Carcinomas
- Colorectal Cancer Surgical Treatments
- Radiation Dose and Imaging
- Lung Cancer Treatments and Mutations
- Advanced Vision and Imaging
- Artificial Intelligence in Healthcare and Education
- Advanced Neural Network Applications
- Prostate Cancer Diagnosis and Treatment
- 3D Shape Modeling and Analysis
- Gastric Cancer Management and Outcomes
- Ultrasound and Hyperthermia Applications
- COVID-19 diagnosis using AI
- Advances in Oncology and Radiotherapy
- Image and Object Detection Techniques
St James's University Hospital
2017-2024
Leeds Teaching Hospitals NHS Trust
2017-2024
Institut Gustave Roussy
2018
Background and purposeComprehensive dosimetric analysis is required prior to the clinical implementation of pelvic MR-only sites, other than prostate, due limited number site specific synthetic-CT (sCT) assessments in literature. This study aims provide a comprehensive assessment deep learning-based, conditional generative adversarial network (cGAN) model for large ano-rectal cancer cohort. The following challenges were investigated; T2-SPACE MR sequences, patient data from multiple centres...
Deep-learning auto-contouring (DL-AC) promises standardisation of organ-at-risk (OAR) contouring, enhancing quality and improving efficiency in radiotherapy. No commercial models exist for OAR contouring based on brain magnetic resonance imaging (MRI). We trained evaluated computed tomography (CT) MRI autosegmentation RayStation. To ascertain clinical usability, we investigated the geometric impact contour editing before training model quality.
Deformable image registration (DIR) is a widely used technique in radiotherapy. Complex deformations, resulting from large anatomical changes, are regular challenge. DIR algorithms generally seek balance between capturing deformations and preserving smooth deformation vector field (DVF). We propose novel structure-based term that can enhance the efficacy while ensuring DVF.
(1) Background: The STRIDeR (Support Tool for Re-Irradiation Decisions guided by Radiobiology) planning pathway aims to facilitate anatomically appropriate and radiobiologically meaningful re-irradiation (reRT). This work evaluated the robustness compared a more conservative manual pathway. (2) Methods: For ten high-grade glioma reRT patient cases, uncertainties were applied cumulative doses re-summed. Geometric of 3, 6 9 mm background dose, LQ model was tested using
Background and purposeMagnetic Resonance Imaging (MRI) exhibits scanner dependent contrast, which limits generalisability of radiomics machine-learning for radiation oncology. Current deep-learning harmonisation requires paired data, retraining new scanners often suffers from geometry-shift alters anatomical information. The aim this study was to investigate style-blind auto-encoders MRI accommodate unpaired training avoid harmonise data previously unseen scanners.Materials methodsA...
Deformable image registration (DIR) can be used to track cardiac motion. Conventional DIR algorithms aim establish a dense and non-linear correspondence between independent pairs of images. They are, nevertheless, computationally intensive do not consider temporal dependencies regulate the estimated motion in cycle. In this paper, leveraging deep learning methods, we formulate novel hierarchical probabilistic model, termed DragNet, for fast reliable spatio-temporal cine magnetic resonance...
In radiotherapy treatment planning, respiration-induced motion introduces uncertainty that, if not appropriately considered, could result in dose delivery problems. 4D cone-beam computed tomography (4D-CBCT) has been developed to provide imaging guidance by reconstructing a pseudo-motion sequence of CBCT volumes through binning projection data into breathing phases. However, it suffers from artefacts and erroneously characterizes the averaged motion. Furthermore, conventional 4D-CBCT can...
To establish the clinical applicability of deep-learning organ-at-risk autocontouring models (DL-AC) for brain radiotherapy. The dosimetric impact contour editing, prior to model training, on performance was evaluated both CT and MRI-based models. correlation between geometric measures also investigated whether assessment is required validation.
Abstract Purpose We have built a novel AI‐driven QA method called AutoConfidence (ACo), to estimate segmentation confidence on per‐voxel basis without gold standard segmentations, enabling robust, efficient review of automated (AS). demonstrated this in brain OAR AS MRI, using internal and external (third‐party) models. Methods Thirty‐two retrospectives, MRI planned, glioma cases were randomly selected from local clinical cohort for ACo training. A generator was trained adversarialy produce...
Abstract Introduction Limited evidence exists showing the benefit of magnetic resonance (MR)‐only radiotherapy treatment planning for anal and rectal cancers. This study aims to assess impact MR‐only on target volumes (TVs) plan doses organs at risks (OARs) cancers versus a computed tomography (CT)‐only pathway. Materials methods Forty‐six patients (29 rectum 17 anus) undergoing preoperative or radical external beam received CT T2 MR simulation. TV OARs were delineated MR, volumetric arc...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
We propose Deep-Motion-Net: an end-to-end graph neural network (GNN) architecture that enables 3D (volumetric) organ shape reconstruction from a single in-treatment kV planar X-ray image acquired at any arbitrary projection angle. Estimating and compensating for true anatomical motion during radiotherapy is essential improving the delivery of planned radiation dose to target volumes while sparing organs-at-risk, thereby therapeutic ratio. Achieving this using only limited imaging available...
(1) Purpose: We analysed overall survival (OS) rates following radiotherapy (RT) and chemo-RT of locally-advanced non-small cell lung cancer (LA-NSCLC) to investigate whether tumour repopulation varies with treatment-type, further characterise the low
Background and PurposeMagnetic resonance (MR)-only treatment pathways require either the MR-simulation or synthetic-computed tomography (sCT) as an alternative reference image for cone beam computed (CBCT) patient position verification. This study assessed whether using T2 MR sCT CBCT images introduces systematic registration errors compared to CT anal rectal cancers.Materials MethodsA total of 32 patients (18 rectum,14 anus) received pre-treatment CT- MR- simulation. Routine CBCTs were...
ConclusionOur preliminary data indicates that peri-tumoral regions are more susceptible to changes in vessel caliber and microvascular blood-volume when immunotherapy is added SRS.The relative decrease rCBV, together with increase rVSI these patients, suggest targets small immature blood vessels high dose regions.