Dr Sharib Ali

Profile

I am the Founder and Lead of the AI in Medicine and Surgery (AIMS) Group at the University of Leeds, with over 15 years of experience in medical, biomedical, and surgical data analysis, specialising in medical imaging and computer vision.

My research focuses on developing foundational artificial intelligence methods for general medical/biomedical imaging, endoscopy, minimally invasive surgery, robotic surgery, and image-guided interventions, with an emphasis on clinically robust and generalisable systems.

I have been recognised among the Elsevier and Stanford World’s Top 2% Scientists (2023–2025). My work has also been supported by major competitive funding, including the Academy of Medical Sciences Springboard Award (2025), EPSRC New Investigator Award (2025), and Worldwide Universities Network (WUN) grants (2024–2025), enabling international and interdisciplinary collaborations.

Research Expertise

My research lies at the intersection of computer vision, machine learning, and medical image analysis, with a strong focus on translational healthcare applications. Key areas include:

• Computational endoscopy and surgical vision systems

• 2D and 3D medical image analysis

• 3D reconstruction of endoscopic and surgical scenes

• 3D–2D fusion, registration, and cross-modal alignment

• Segmentation, detection, and anomaly analysis in medical imaging

• Surgical workflow and phase recognition

• Surgical scene understanding, tracking, and reconstruction

• Surgical tool detection and tool–tissue interaction modelling

• Multimodal learning and domain generalisation

• Depth estimation and robotic surgery scene understanding

I have developed several foundational methodological research in endoscopic and surgical computer vision and in general medical imaging (some works include US, CT, MRI, high-throughput imaging). I have authored nearly 40 peer-reviewed journals (mostly as first/senior author) and over 60 conference papers at top venues (IEEE Transactions in Medical Imaging, Medical Image Analysis, MICCAI and many others). Some of my pioneering works includes (but not limited to) 3D reconstruction of GI/surgical endoscopic videos (Barrett’s oesophagus, colonic scenes and surgical scenes), 3D-2D image fusion, 3D/2D segmentation methods, anamoly detection/segmentation (e.g., polyps, colitis scoring), surgical phase recognition, surgical scene segmentation, surgical scene tracking, tool detection and tool-tissue interaction, generalisation and multimodal modeling for various downstream tasks and more. I also led the frontier in establishing automated 3D to 2D laparoscopic fusion problem introducing several computer vision solutions to 2D and 3D anatomical liver landmark methods. My initiative of Preoperative to intraoperative fusion (P2ILF) is a landmark dataset and problem formulation which has been main stream research in AR research in robotic/laparoscopic surgery.

Key Contributions

I have contributed to several foundational problems in medical AI and surgical computer vision:

Endoscopic and Surgical 3D Vision

Developed methods for 3D reconstruction of gastrointestinal and surgical endoscopic videos, including applications in Barrett’s oesophagus, colonoscopy, and laparoscopic surgery.

Preoperative-to-Intraoperative Fusion (P2ILF)

Pioneered the P2ILF framework, enabling robust 2D–3D correspondence between preoperative imaging and intraoperative laparoscopic video. This work has established a key paradigm for augmented reality and image-guided surgery.

Multimodal and Generalisable Medical AI

Advanced methods for cross-domain learning and multimodal fusion to improve robustness across institutions, devices, and clinical environments.

Publications

I have authored approximately 40 peer-reviewed journal articles and over 60 conference papers at leading venues, including:

• IEEE Transactions on Medical Imaging (TMI)

• Medical Image Analysis (MedIA)

• MICCAI

My work spans foundational methodological research and translational clinical applications.

Datasets and Resources

I have initiated and contributed to several widely used datasets in medical imaging and surgical AI:

• Endoscopic Artefact Detection (EAD) https://data.mendeley.com/datasets/c7fjbxcgj9/4

• Endoscopy Disease Detection and Segmentation (EDD2020) https://ieee-dataport.org/competitions/endoscopy-disease-detection-and-segmentation-edd2020

• PolypGen: Multi-centre Polyp Segmentation Dataset https://doi.org/10.7303/syn26376615

• Preoperative to Intraoperative Laparoscopic Fusion (P2ILF) https://doi.org/10.7303/syn63689257

• DRENDS: Depth in Robotic Endoscopy with Dynamic Scenarios https://zenodo.org/records/17598453

• LASK: Laparoscopic Skill and Kinematics Dataset

Research Leadership & Service

I actively contribute to the research community through:

• Organisation of international challenges and workshops in endoscopic and surgical computer vision (since 2019)

• MICCAI workshops and the P2ILF challenge (MICCAI 2022)

• General chair roles (e.g., MIUA 2025)

• Programme committee membership (e.g., IEEE CBMS 2024)

• Editorial and peer-review activities for leading journals (e.g., IEEE TMI, TPAMI, Medical Image Analysis, Nature Communications)

• Grant review panels (UKRI, ERC, NIHR)

• Membership of the Royal Society Newton International Fellowships Committee

I am also a founding member of NAAMII (Nepal Applied Mathematics and Informatics Institute for Research), supporting capacity building and training for students from low- and middle-income countries.

Education and Early Career

I obtained my MSc (by research) in Computer Vision from the University of Burgundy, France (2010–2012), focusing on retinal image analysis in collaboration with Oak Ridge National Laboratory (USA) and Le2I, University of Burgundy.

I completed my PhD in Image Analysis (awarded 2016) at the University of Lorraine (CNRS–CRAN, France), where I developed computer vision methods for endoscopic video mosaicking and bladder cancer monitoring through robust feature tracking and motion-based reconstruction.

I subsequently held postdoctoral positions at:

• University of Heidelberg & DKFZ, Germany (2015–2018), working on physics-based deformable multi-modal image registration and neuroimaging reconstruction

• University of Oxford, UK (2018–2022), where I developed AI systems for computer-assisted endoscopy in collaboration with clinical partners at Oxford University Hospitals

I currently hold a Visiting Fellow position at the University of Oxford.

Research Vision

My long-term vision is to develop robust, generalisable, and clinically deployable AI systems that improve surgical safety, enhance decision-making, and enable intelligent, computer-assisted operating environments that benefit patients globally.

Supervision & Teaching

I supervise and co-supervise PhD students working on medical AI, including surgical vision, 3D reconstruction, and multimodal learning. I also support research training for students globally, including through volunteer academic roles.

Graduated PhDs/DPhis:

Soumya Gupta (Thesis at: University of Oxford, graduated in 2022)

Ziang Xu (Thesis at: University of Oxford, graduated in 2025)

Xukun Zhang (Thesis at: Fudan University, graduated in 2025)

Mansoor Ali (PhD Graduate in 2026)

Public activitiy (available on Spotify): My recent podcast interview highlighting the need for multi-modality, multi-center approach for tackling generalisability and bias in AI for medical image analysis.

Responsibilities

• Teaching/Research

Research interests

My research interest lies in solving computer vision and image processing related problems which includes building new mathematical models and implementation of the methods for both research purposes and practical use. I mostly work around applications in medical and biomedical image analysis and multimodal data analysis. I am keen towards learning about new technologies and open to meeting new people, establishing interesting and innovative collaborations (both academia and industry), mentoring students and looking forward for new and exciting opportunities.

I have an extensive experience in building cutting edge computer vision technologies for object detection, semantic segmentation, image restoration, depth estimation, optical flow, image registration and 3D reconstruction. I have developed tools in these topics with both classical mathematical models and deep learning models. I am a passionate researcher with knowledge, energy and enthusiasm to contribute towards healthcare technologies that can benefit patients and assist clinicians around the world. I am a promotor of translational research and equality in access to digital healthcare for all. 

Primary investigator (PI)

• Artificial Intelligence for Surgical Training Towards Safer and Effective Sub-mucosal Dissection
• Leveraging multi-modality data for targeted biopsy and risk stratification of patients with inflammatory Bowel disease
• Real-time High-Fidelity Augmented Reality in Laparoscopic Liver Resection

Qualifications

• PhD in medical image analysis from University of Lorraine, France
• MSc in Computer Vision (by research), University of Dijon, France

Professional memberships

• IEEE
• MICCAI Society
• IEEE EMBS

Student education

Deep Learning

Research groups and institutes

• Leeds Cancer Research Centre

Current postgraduate researchers

• Edward Ellis
• Raneem Toman
• Pedro Chavarrias
• Omar Choudhry