University of Bamberg
open search form
You are here

Information Systems and Applied Computer Sciences

Chair of Explainable Machine Learning

  1.  University of bamberg
  2. Faculties
  3. Information Systems and Applied Computer Sciences
  4. Subject groups
  5. Applied Computer Science
  6. Chair of Explainable Machine Learning
  7. Team
  8. Sleiman Sharara, M.Sc.

Sleiman Sharara

Research Assistant

M.Sc., Doctoral Candidate

Adresse: An der Weberei 5, 96047 Bamberg
Room: WE5/04.093

E-mail: sleiman.sharara(at)uni-bamberg.de

Consultation hours: Possible by arrangement via email.

 

Biographie: 

Sleiman Sharara has been a PhD candidate at the Chair of Explainable Machine Learning at the University of Bamberg since 2026, carrying out an industrial PhD jointly with Siemens Healthineers in Forchheim. He holds a Master's degree in Medical Engineering from Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), specializing in medical image and data processing. He previously completed a Bachelor's degree in Biomedical Engineering.

His research focuses on generative AI for synthetic data in image-guided minimally invasive interventions. He works on simulating and generating realistic interventional X-ray images, including the devices used during these procedures, and evaluates the synthetic data on deep learning downstream tasks. His broader interests include explainable AI, medical image analysis and computer vision.

Before starting his PhD, Sleiman worked as a working student at Siemens Healthineers on the segmentation and detection of mechanical thrombectomy devices in interventional X-ray imaging. He developed preprocessing and augmentation strategies and built training and evaluation pipelines. Building on this work, he also wrote his Master's thesis there, titled "Sequence-Based Deep Learning for Endovascular Device Segmentation in Interventional X-ray Imaging", investigating how temporal information can improve segmentation beyond frame-by-frame approaches.

During his studies, he also worked as a research assistant at the Institute of Applied Mechanics (LTM) at FAU, where he implemented and optimized convolutional neural networks for mechanical engineering applications. In addition, he completed the project "Deep Learning-Based Classification of Skin Diseases: A Comparative Analysis of CNN and Transformer Architectures" at the Pattern Recognition Lab, in which he classified melanoma, nevus and benign keratosis. At the Machine Learning and Data Analytics Lab, he worked on "Efficient Multi-Task Learning for Multi-Tissue Wound Segmentation with Attention-Enhanced U-Net", in which he jointly segmented different wound tissue types.

Outside of his academic life, Sleiman enjoys running, hiking and strength training.