Contact Information

Email: sharib[dot]ali[at]

Sharib Ali

Adj. Research Scientist

Dr. Sharib Ali works as research scientist (voluntary position) and leads the computational endoscopy and surgery research at NAAMII. His research has progressed from understanding and tackling challenges in endoscopy to developing robust systems for tasks such as automated lesion segmentation, detection, 3D reconstruction, and real-world measurements and beyond. He has integrated both current deep learning models and classical computer vision concepts in these works. However, the challenges remain in several tasks in endoscopic computer vision development and its clinical usability, model generalisation, resource constraints settings, and real-time requirements. Similarly, precise tool tracking in surgery is critical, and scene understanding is often complex and needs to be thought more comprehensively. Dr Ali is currently a full-time lecturer (assistant professor) at the University of Leeds, UK. He has conducted his research in the past at other internationally recognised universities and research centres including University of Oxford, Oxford, UK and German Cancer Research Center, DKFZ, Germany. He has published in major journals and conferences including medical image analysis, pattern recognition, IEEE TNLLS, CVIU, Scientific reports, MICCAI conference, IEEE ISBI, IEEE EMBC, ICPR, and more. At this position, he offers selected students (motivation and eager to learn) from low and middle income countries (LMICs) an opportunity to work with him on various topics of medical/biomedical imaging.

Other public profiles:

Google scholar

Previous interns:

Shruti Shrestha (Project on GI tract anomaly detection from endoscopy images)

Nikhil Kumar Tomar (Semantic segmentation of polyps, accepted paper at MICCAI 2022)

Relevant publications:

  • Ensemble U-Net model for efficient polyp segmentation CEUR Workshop proceeding (MediaEval 2020), 2020. Link to paper.
  • TGANet: Text-guided attention for improved polyp segmentation. (Accepted at MICCAI 2022) Link to paper.
  • Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge. arXiv 2022 Link to paper.
  • Iterative deep learning for improved segmentation of endoscopic images, Vol. 1 No. 1 (2021): MedAI: Transparency in Medical Image Segmentation. Link to paper.

Internship positions:
Summer internship positions are now open for low and middle-income country applicants. I work voluntarily at this position to assist students who do not have exposure to competitive research as compared to European or US students.

The internship positions will last from 3 up to 6 months. Only selected applicants will be invited for interviews. I am looking for motivated individuals who has strong appetite for learning, implementing and doing cutting edge research in medical/biomedical field. If you are one of this then please submit the application form at this link:

Internship details:

  • Requirements:
    • Coding: Python skills and knowledge of at least one machine learning/deep learning library
    • You must have worked on any image analysis problems before (you do not have to have a solid background, you just need to understand what pixels are and how images are treated for analysis)
    • You should be either final year undergraduate student or above.
  • Area of work: Bio/Medical image analysis problems – You can propose either your own topic of interest or we will give some ideas and you can pick one. This process will be done after the interview
  • Hours requirement: It is up to you, however, we think that to get most of the internship you must dedicate at least 20 hours per week. You will meet your supervisors depending upon your progress.
  • Interview day: Please prepare 2 slides to introduce yourself and what you want to achieve during your internship. The interviews will be 10 mins. The actual date and time will be communicated to you after your application.
  • Salary: Currently there is no funding for this so this is an unpaid summer internship for motivated students only.