Skip to main content

AI in Medicine and Surgery (AIMS group)

AI in Medicine and Surgery (AIMS group)

Dr Sharib Ali

Head of AIMS group
Associate professor/ Researcher in Artificial Intelligence for Healthcare (expertise in Biomedical and medical image analysis)
PhD and Master's by research in Computer Vision

Dr Jiangbei Yue

Research Fellow
AMS funded research project on risk prognosis

Gerardo Loza Galindo

Research Fellow
Surgical AI and computer vision (primary research topics in registration and surgical scene tracking for EPSRC funded research)

Dr Tao Chen

Research Fellow
NIHR BRC Pump-prime funding

Pedro Chavarrias Solano

PhD research student
(video 3D reconstruction)

Raneem Toman

PhD research student
(multi-omics data analysis)

Edward Ellis

PhD research student
(ultrasound image analysis)

Patryk Wasniewski

PhD research student
(biomedical high-throughput data analysis)

Omar Choudhry

PhD research student
AI-Driven Surgical Skill Training in Resource-Constrained Environments

Mikolaj Kowal

Clinical PhD candidate

Gyanateet Dutta

Research intern
Endoscopy project support

Current Research interns

Aya Hammad - University of York, York, UK (intern)
Maksim Richards - University of Oxford, Oxford, UK (intern)

Past members

  • Ziang Xu - DPhil graduate from University of Oxford, UK (Now PDRA at CU HK)
    Xukun Zhang - PhD graduate from Fudan University, China (Now PDRA at HKU)
  • Mansoor Ali - PhD graduate from Tec de Monterrey (Now PDRA at Tec de Monterrey)
  • Soumya Gupta, DPhil graduate from the University of Oxford (Now Research Engineer at Vision RT Ltd, London, UK)
  • Darshita Budhadev, MRes graduate, University of Leeds (Now AI Researcher at Hartree Centre, STFC Daresbury, UK)
  • Juan Carlos Ángeles Cerón, Master's graduate from Tec de Monterrey (Now Data and Applied Scientist II at Microsoft, Washington, US)
  • Shruti Shrestha, research intern (Now Machine Learning Research Scientist @ Georgia State University, Atlanta, US)
  • Ajay Patha - NAAMII, Kathmandu, Nepal (Now with COAC gmbh)
  • Helena Valencia - Tec de Monterrey, Mexico (Now with Amazon)
  • Nikhil K Tomar, research intern (Now working with collaborators at the Northwestern University, Chicago, US)

Open positions in the group

 

News!!!

 

Research highlights

New papers:

ESPNet: Edge-Aware Feature Shrinkage Pyramid for Polyp Segmentation

Despite numerous techniques developed for polyp segmentation, the issue of generalizability to new centers and populations persists. To address these issues, we compile a multicenter train set consisting of 4,000 polyp frames and propose a novel approach toward generalizing to different data centers, difficult polyp morphologies (e.g., flat or small), and inflammatory conditions such as inflammatory bowel disease (IBD). In this regard, we propose a transformer-based polyp segmentation model to leverage global contextual information, and enhancement of local feature interactions through a novel feature decoding and fusion method, and polyp edge features. This combines the vision transformers' strong contextual understanding with enhanced locality modeling through graph-based relational understanding and multiscale feature aggregation.




Published at: MICCAI conference 2025 (9% early accept)

An objective comparison of methods for augmented reality in laparoscopic

Augmented reality for laparoscopic liver resection is a visualisation mode that allows a surgeon to localise tumours and vessels embedded within the liver by projecting them on top of a laparoscopic image. Preoperative 3D models extracted from Computed Tomography (CT) or Magnetic Resonance (MR) imaging data are registered to the intraoperative laparoscopic images during this process. Regarding 3D–2D fusion, most algorithms use anatomical landmarks to guide registration, such as the liver’s inferior ridge, the falciform ligament, and the occluding contours. These are usually marked by hand in both the laparoscopic image and the 3D model, which is time-consuming and prone to error. Therefore, there is a need to automate this process so that augmented reality can be used effectively in the operating room. We present the Preoperative-to-Intraoperative Laparoscopic Fusion challenge (P2ILF), held during the Medical Image Computing and Computer Assisted Intervention (MICCAI 2022) conference, which investigates the possibilities of detecting these landmarks automatically and using them in registration. The challenge was divided into two tasks: (1) A 2D and 3D landmark segmentation task and (2) a 3D–2D registration task.

Published at: Medical Image Analysis (IF: 11.8)

Robust and smooth Couinaud segmentation via point-voxel network

We introduce a novel multi-scale point-voxel fusion framework for fully automated Couinaud segmentation, a critical task for liver surgery planning. By innovatively leveraging the topological relationships of coordinate points in 3D space and the rich semantic information encoded in voxel grids, our method not only recognizes but also intricately understands the spatial hierarchies and relationships crucial for precise Couinaud segmentation. Moreover, our approach is the integration of the dense point sampling strategy, enriched with vessel priors, which significantly enhances our model’s focus on critical areas. This strategy facilitates a detailed understanding of the trajectories of key vascular structures, thus paving the way for safer surgical pathways that substantially minimize the risk of damaging major blood vessels.

Published at Computers in Biology and Medicine (IF: 7.0)

Self-supervised learning with composite pretext-class discrimination

Despite the publicly available datasets and datasets that can be generated within hospitals, most supervised models still underperform. While self-supervised learning has addressed this problem to some extent in natural scene data, there is a considerable performance gap in the medical image domain. In this paper, we propose to explore patch-level instance-group discrimination and penalisation of inter- class variation using additive angular margin within the co- sine similarity metrics. Our novel approach enables models to learn to cluster similar representations, thereby improv- ing their ability to provide better separation between differ- ent classes. Our results demonstrate significant improvement on all metrics over the state-of-the-art (SOTA) methods on the test set from the same and diverse datasets.

Published at: IEEE Transactions in Medical Imaging (IF: 8.9)

Assessing generalisability of deep learning-based in colonoscopy

To assist in clinical procedures and reduce missed rates, automated methods for detecting and segmenting polyps using machine learning have been achieved in past years. However, the major drawback in most of these methods is their ability to generalise to out-of-sample unseen datasets from different centres, populations, modalities, and acquisition systems. To test this hypothesis rigorously, we, together with expert gastroenterologists, curated a multi-centre and multi-population dataset acquired from six different colonoscopy systems and challenged the computational expert teams to develop robust automated detection and segmentation methods in a crowd-sourcing Endoscopic computer vision challenge. This work put forward rigorous generalisability tests and assesses the usability of devised deep learning methods in dynamic and actual clinical colonoscopy procedures.

Published at: Nature Scientific Reports

Where do we stand in AI for endoscopic image analysis?

The paper reviews recent works on endoscopic image analysis with artificial intelligence (AI) and emphasises the current unmatched needs in this field. Finally, it outlines the future directions for clinically relevant complex AI solutions to improve patient outcomes. Published at npj Digit. Med. (December 2022) - Click to read more.

Real-time surgical tool detection with multi-scale positional encoding & CL

We propose an anchor-free architecture based on a transformer that utilises multi-scale features within the feature extraction layer and at the transformer-based detection architecture through positional encoding that can refine and capture context-aware and structural information of different-sized tools. Furthermore, a supervised contrastive loss is introduced to optimize representations of object embeddings, resulting in improved feed-forward network performances for classifying localized bounding boxes. Compared to the most accurate existing SOTA method, our approach has an improvement of nearly 4% on mAP50 and a reduction in the inference time by 113%. It also showed a 7% higher mAP50 than the baseline model.

Published at: Wiley, Health Technology Letters

Anatomical-aware Point-Voxel Network for Couinaud Segmentation in Liver CT

We design a multi-scale point-voxel fusion network to capture the anatomical structure and semantic information of the liver and vessels, respectively, while also increasing important data access through vessel structure prior. Finally, the network outputs the classification of Couinaud segments in the continuous liver space, producing a more accurate and smooth 3D Couinaud segmentation mask. Our proposed method outperforms several state-of-the-art methods, both point-based and voxel-based, as demonstrated by our experimental results on two public liver datasets.

Published at: MICCAI conference 2023

A semi-supervised Teacher-Student framework for surgical tool localisation

Semi-supervised learning (SSL) has recently emerged as a viable alternative showing promise in producing models retaining competitive performance to supervised methods. This paper introduces an SSL framework in the surgical tool detection paradigm, which aims to mitigate training data scarcity and data imbalance problems through a knowledge distillation approach.


Published at: MICCAI conference workshop AE-CAI'2022

Selected/latest publications

Conference (selected)

  • Toman, R, Subramanian, V., Ali, S. (2025). ESPNet: Edge-Aware Feature Shrinkage Pyramid for Polyp Segmentation. In Medical Image Computing and Computer Assisted Intervention (MICCA’2025), South Korea. (9% early accepted papers)
  • Ali, M., Toman, R., Ochoa-Ruiz, G., & Ali, S. (2026). PolypDINO: Adapting DINOv2 for Domain Generalized Polyp Segmentation. In 29th Conference on Medical Image Understanding and Analysis, Lecture Notes in Computer Science (pp. 190-203). Springer Nature Switzerland. doi:1007/978-3-031-98694-9_14
  • Borgars, J., Raja, J., Ramakrishnan, A., Abbas, A. K., Gallagher, A., Mohamad Shahir, A. N., . . . Ali, S. (2026). Intraoperative Segmentation Through Deep Learning and Mask Post-processing in Laparoscopic Liver Surgery. In 29th Conference on Medical Image Understanding and Analysis, Lecture Notes in Computer Science (pp. 204-218). Springer Nature Switzerland. doi:1007/978-3-031-98694-9_15
  • Abbas, A. K., Gallagher, A., Vraimakis, T., Borgars, J., Mohamad Shahir, A. N., Raja, J., . . . Ali, S. (2026). Midline-Constrained Loss in the Anatomical Landmark Segmentation of 3D Liver Models. In 29th Conference on Medical Image Understanding and Analysis, Lecture Notes in Computer Science (pp. 216-229). Springer Nature Switzerland. doi:1007/978-3-031-98691-8_16
  • Martinez-Garcia-Peña, R., Teevno, M. A., Ochoa-Ruiz, G., & Ali, S. (2023). SUPRA: Superpixel Guided Loss for Improved Multi-modal Segmentation in Endoscopy. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 285-294). IEEE. doi:1109/cvprw59228.2023.00034
  • Zhang, X., Liu, Y., Ali, S., Zhao, X., Sun, M., Han, M., . . . Zhang, L. (2023). Anatomical-Aware Point-Voxel Network for Couinaud Segmentation in Liver CT. In Lecture Notes in Computer Science (pp. 465-474). Springer Nature Switzerland. doi:1007/978-3-031-43898-1_45
  • Eisenmann, M., Reinke, A., Weru, V., Tizabi, M. D., Isensee, F., Adler, T. J., . . . Maier-Hein, L. (2023). Why is the Winner the Best?. In 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 19955-19966). IEEE. doi:1109/cvpr52729.2023.01911
  • Tomar, N. K., Jha, D., Bagci, U., & Ali, S. (2022). TGANet: Text-Guided Attention for Improved Polyp Segmentation. In L. Wang, Q. Dou, P. T. Fletcher, S. Speidel, & S. Li (Eds.), Medical Image Computing and Computer Assisted Intervention – MICCAI 2022, Lecture Notes in Computer Science (Vol. 13433, pp. 151-160). Cham, Switzerland: Springer Nature Switzerland. doi:1007/978-3-031-16437-8_15
  • Xu, Z., Ali, S., East, J., & Rittscher, J. (2022). Additive Angular Margin Loss and Model Scaling Network for Optimised Colitis Scoring. In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI) (pp. 1-5). IEEE. doi:1109/isbi52829.2022.9761437
  • Gupta, S., Ali, S., Xu, Z., Bhattarai, B., Turney, B., & Rittscher, J. (2022). UNet-eVAE: Iterative Refinement Using VAE Embodied Learning for Endoscopic Image Segmentation. In Machine Learning in Medical Imaging. MLMI 2022 (pp. 161-170). Springer Nature Switzerland. doi:1007/978-3-031-21014-3_17
  • Celik, N., Ali, S., Gupta, S., Braden, B., & Rittscher, J. (2021). EndoUDA: A Modality Independent Segmentation Approach for Endoscopy Imaging. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2021 (pp. 303-312). Springer International Publishing. doi:1007/978-3-030-87199-4_29
  • Tomar, N. K., Jha, D., Ali, S., Johansen, H. D., Johansen, D., Riegler, M. A., & Halvorsen, P. (2021). DDANet: Dual Decoder Attention Network for Automatic Polyp Segmentation. In ICPR International Workshops and Challenges. ICPR 2021. (pp. 307-314). Springer International Publishing. doi:1007/978-3-030-68793-9_23

Journals (selected, past 3 years)

  • Zhang, X., Feng, J., Liu, P., Han, M., Kang, Y., Zhu, J., Wang, L., Wang, X., Ali, S., Zhang, L. (2026). Nested resolution mesh-graph CNN for automated extraction of liver surface anatomical landmarks, Medical Image Analysis, Volume 107, Part B, 2026, 103825, https://doi.org/10.1016/j.media.2025.103825. (shared corresponding author) (IF: 11.8)
  • Zhang, X., Ali, S., Han, M., Kang, Y., Wang, X., & Zhang, L. (2025). Two-stream MeshCNN for key anatomical segmentation on the liver surface. International Journal of Computer Assisted Radiology and Surgery. doi:1007/s11548-025-03358-5 (shared first author) (IF: 2.47)
  • Chavarrias Solano, P. E., Bulpitt, A., Subramanian, V., & Ali, S. (2025). Multi-task learning with cross-task consistency for improved depth estimation in colonoscopy. Medical Image Analysis, 99, 103379. doi:1016/j.media.2024.103379 (IF: 11.8)
  • Ali, S., Espinel, Y., Jin, Y., Liu, P., Güttner, B., Zhang, X., . . . Bartoli, A. (2025). An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion from the MICCAI2022 challenge. Medical Image Analysis, 99, 103371. doi:1016/j.media.2024.103371 (IF: 11.8)
  • Jha, D., Sharma, V., Banik, D., Bhattacharya, D., Roy, K., Hicks, S. A., . . . Bagci, U. (2025). Validating polyp and instrument segmentation methods in colonoscopy through Medico 2020 and MedAI 2021 Challenges. Medical Image Analysis, 99, 103307. doi:1016/j.media.2024.103307 (IF: 11.8)
  • Zhang, X., Ali, S., Liu, T., Zhao, X., Cui, Z., Han, M., . . . Zhang, L. (2024). Robust and smooth Couinaud segmentation via anatomical structure-guided point-voxel network. in Biology and Medicine, 182, 109202. doi:10.1016/j.compbiomed.2024.109202 (IF: 6.3)
  • Kron, P., Farid, , Ali, S., & Lodge, P. (2024). Artificial Intelligence. Annals of Surgery, 280(5), 713-718. doi:10.1097/sla.0000000000006464 (IF: 6.4)
  • Xu, Z., Rittscher, J., & Ali, S. (2024). SSL-CPCD: Self-Supervised Learning With Composite Pretext-Class Discrimination for Improved Generalisability in Endoscopic Image Analysis. IEEE Transactions on Medical Imaging, 43(12), 4105-4119. doi:1109/tmi.2024.3411933 (IF: 9.8)
  • Loza, G., Valdastri, P., & Ali, S. (2024). Real‐time surgical tool detection with multi‐scale positional encoding and contrastive learning. Healthcare Technology Letters, 11(2-3), 48-58. doi:1049/htl2.12060 (IF: 3.3)
  • Ali, S., Ghatwary, N., Jha, D., Isik-Polat, E., Polat, G., Yang, C., . . . East, J. E. (2024). Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge. Scientific Reports, 14(1). doi:1038/s41598-024-52063-x (IF: 3.9)
  • Tomar, N. K., Jha, D., Riegler, M. A., Johansen, H. D., Johansen, D., Rittscher, J., . . . Ali, S. (2022). FANet: A Feedback Attention Network for Improved Biomedical Image Segmentation. IEEE Transactions on Neural Networks and Learning Systems. doi:1109/tnnls.2022.3159394 (IF: 8.9)
  • Ali, S., Jha, D., Ghatwary, N., Realdon, S., Cannizzaro, R., Salem, O. E., . . . East, J. E. (2023). A multi-centre polyp detection and segmentation dataset for generalisability assessment. Scientific Data, 10. doi:1038/s41597-023-01981-y (IF: 6.9)
  • Ali, S. (2022). Where do we stand in AI for endoscopic image analysis? Deciphering gaps and future directions. npj Digital Medicine, 5. doi:1038/s41746-022-00733-3 (IF: 15.1)
  • Cerón, J. C. Á., Ruiz, G. O., Chang, L., & Ali, S. (2022). Real-time instance segmentation of surgical instruments using attention and multi-scale feature fusion. Medical Image Analysis, 81. doi:1016/j.media.2022.102569 (IF: 11.8)
  • Gupta, S., Ali, S., Goldsmith, L., Turney, B., & Rittscher, J. (2022). Multi-class motion-based semantic segmentation for ureteroscopy and laser lithotripsy. Computerized Medical Imaging and Graphics, 101. doi:1016/j.compmedimag.2022.102112 (IF: 4.9)
  • Srivastava, A., Jha, D., Chanda, S., Pal, U., Johansen, H., Johansen, D., . . ., Ali, S., Halvorsen, P. (2022). MSRF-Net: A Multi-Scale Residual Fusion Network for Biomedical Image Segmentation. IEEE Journal of Biomedical and Health Informatics, 26(5), 2252-2263. doi:1109/jbhi.2021.3138024 (shared senior author) (IF: 6.8)

Grants & awards

AR in liver laparoscopy

Leveraging multi-modality data for targeted biopsy and risk stratification

Bowel cancer prediction

AI for Surgical Training Towards Safer and Effective ESD

ARMADILLO Liver Project supported by Leeds BRC Pump-prime funding

Collaborators

We collaborate with cross-faculty researchers and clinical colleagues at the Leeds Teaching Hospital Trust  and other hospitals in the UK including Oxford University Hospitals, Oxford. We have also extended collaboration across Europe (France, Italy, Sweden, and Germany), Canada, Asia (China, Nepal)  and Africa (Egypt). Thanks to all colleagues for their continuous support in our research that we do. If your research resonate to something we do please reach out to us at s.s.ali[at]leeds[dot]ac[dot]uk

Conferences/Workshops co-ordinated by AIMS group

WUN networking event 2023

"Opportunities and challenges in emerging technologies for healthcare"
14th September 2023, 09:00 – 13:30AM (UK time) (please check your time zone)
Venue: HELIX, Level 7, EC Stoner (University of Leeds)

MIUA 2025

15-17th July 2025

Mini-Workshops on Computational Surgery

Room: William Bragg LT (2.37), School of Computer Science
Date(s): Tuesday, 5th of August 2025
Time: 11:00-13:00