About
I am a Deep Learning Researcher and Engineer with a Ph.D. from the University of Oxford, working under Professor Andrew Zisserman at the Visual Geometry Group (VGG). My research focuses on the intersection of computer vision and medical imaging, with particular emphasis on 3D reconstruction, large-scale semi-supervised learning, and generative models for medical applications.
Work Experience
May 2025 – Sep 2025
Deep Learning Research Engineer
QuantCo, London, UK
- Developed weakly supervised and self-supervised models for image segmentation and classification grading
- Developed strategies to handle scarce and noisy labels
- Led implementation of production-ready ML pipelines, collaborating with cross-functional teams of 10+ members
- Presented technical findings to non-technical stakeholders, translating complex ML concepts into actionable insights
Sep 2020 – Sep 2021
AI Software Engineer Intern
GE Healthcare, Oxford, UK
- Implemented automated quality-checks using C++ on data from different institutions for downstream AI tasks
- Collaborated effectively with senior software engineering team of 8+ members
- Communicated technical requirements and solutions across multidisciplinary teams
Jun 2020 – Sep 2020
AI Research Intern
Netdevices, Paris, France
- Automated data management pipelines using ML for hospital applications
Publications
2025
UKBOB: One Billion MRI Labeled Masks for Generalizable 3D Medical Image Segmentation
International Conference on Computer Vision (ICCV)
Developed large-scale semi-supervised framework for 3D medical image segmentation with 1B+ labeled masks from 48K+ datasets, enabling generalizable models across diverse medical imaging modalities.
2025
FrEVL: Leveraging Frozen Pretrained Embeddings for Efficient Vision-Language Understanding
Spotlight
International Conference on Computer Vision Safe and Trustworthy Multimodal AI Systems Workshop (ICCVW)
Safe and trustworthy vision-language multi-modal approach leveraging frozen pretrained embeddings for efficient understanding without expensive fine-tuning.
2025
X-Diffusion: Generating 3D MRI Volumes From a Single Image Using Cross-Sectional Diffusion Models
Oral
International Conference on Computer Vision GAIA Workshop (ICCVW)
Novel diffusion model approach for generating detailed 3D MRI volumes from single 2D images using cross-sectional conditioning.
2024
Estimating 3D Shape of Spine from 2D DXA
Oral
International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI)
2D-to-3D reconstruction using Vision Transformers for spine shape estimation from DXA images, achieving clinical-grade accuracy.
2024
Multi-Modal Information Bottleneck Attribution with Cross-Attention Guidance
British Machine Vision Conference (BMVC)
Multi-modal attribution method using information bottleneck theory with cross-attention mechanisms for interpretable AI.
2024
MVDiff: Scalable and Flexible Multi-View Diffusion for 3D Object Reconstruction from Single-View
Computer Vision and Pattern Recognition Workshop on Generative AI (CVPR)
Scalable multi-view diffusion approach for 3D object reconstruction from single images with flexible viewpoint generation.
2023
3D Shape Analysis of Scoliosis
Oral
International Conference on Medical Image Computing and Computer-Assisted Intervention Shape in Medical Imaging Workshop (MICCAI)
Comprehensive 3D shape analysis framework for scoliosis assessment and characterization using geometric deep learning.
2022
Scoliosis Measurement on DXA Scans Using Combined Deep Learning and Spinal Geometry
Medical Imaging with Deep Learning (MIDL)
Combined deep learning and geometric approaches for automated scoliosis measurement on DXA scans achieving expert-level accuracy.
2021
Multimodal PET/CT Tumour Segmentation and Progression-Free Survival Prediction
International Conference on Medical Image Computing and Computer-Assisted Intervention Head and Neck Tumor Segmentation Challenge (MICCAI)
Multi-modal approach for tumor segmentation and survival prediction using PET/CT imaging with attention mechanisms.
Education
2021 - 2025
Ph.D. in Engineering - Computer Vision
University of Oxford
2019 - 2020
MSc in Translational Neurosciences
Imperial College London
2016 - 2019
BSc in Mathematics/Statistics and Neuroscience
University College London (UCL)
Technical Skills
Languages & Tools:
C++, Python, MATLAB, R, Git, Docker, CUDA, OpenCV, SQL
ML/DL Frameworks:
PyTorch, TensorFlow, JAX, Keras, scikit-learn, Weights & Biases, TensorBoard, Hugging Face
Computer Vision:
Object detection, segmentation, 3D reconstruction, generative models, medical imaging
Deep Learning:
CNNs, transformers, vision transformers (ViT), multi-modal learning, domain adaptation, transfer learning
Infrastructure:
AWS, Google Cloud, Azure, distributed training, MLOps
Soft Skills:
Research leadership, cross-functional collaboration, scientific communication, mentorship, project management, problem-solving, critical thinking, adaptability
Research Projects
UKBOB: Large-Scale Medical Segmentation
Developing one billion labeled masks for generalizable 3D medical image segmentation using the UK Biobank dataset, enabling large-scale training of medical AI models.
View Project →3D Spine Reconstruction from 2D DXA
Automated framework to estimate 3D spine shape from single 2D DXA scans by predicting sagittal views, achieving high accuracy for scoliosis assessment.
View Project →X-Diffusion
Cross-sectional diffusion model for generating complete 3D MRI volumes from single slices, setting new benchmarks in medical image synthesis.
View Project →