Scholar
Sulaiman Vesal
Google Scholar ID: SQOL8eYAAAAJ
Microsoft
Citations & Impact
Citations
2,145
H-index
20
i10-index
28
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- Placed 3rd in the DCASE competition [Jul 2024]; PICAI 2023 paper accepted in LANCET Oncology journal (Impact Factor: 50.8) [Jun 2024]; ProsDectNet: Bridging the gap for prostate cancer detection on Transrectal Ultrasound paper accepted to Medical Imaging workshop at NeurIPS 2023 [Dec 2023]; Domain Generalized Prostate Gland Segmentation on Transrectal Ultrasound Images paper accepted to Medical Image Analysis (MedIA) (Impact Factor: 10.8) [Feb 2022]; Adapt Everywhere UDA paper accepted to IEEE Transaction in Medical Imaging (IEEE-TMI) (Impact Factor: 10.8) [Mar 2021]; Spatio-Temporal Multi-task Learning for Full LV Quantification paper accepted to IEEE Journal of Biomedical Health and Informatic (IEEE-TMI) (Impact Factor: 7.7) [Jan 2021]; Fully Automated 3D Cardiac MRI Localisation and Segmentation Using Deep Neural Networks paper accepted to MDPI Jounral of Imaging (Impact Factor: 2.0) [Apr 2020]. Additionally, gave talks at multiple international conferences and won second place in several challenges including MICCAI-STCOM 2019, MICCAI-STCOM 2018.
Research Experience
- Currently an AI researcher at Hanwha Vision America, focusing on object detection, action recognition, and multi-modal imaging. Previously, worked as an R&D Scientist and Engineer at Urologic Cancer Innovation Lab (UCIL) in Stanford. Also served as a research data scientist at ArnaoutLab, University of California San Francisco (UCSF).
Education
- He received his M.Sc. in Computer Science from South Asian University in 2013; B.Sc. in Computer Science from Kabul University in 2010. Currently, he is a PhD candidate at the Pattern Recognition Lab, FAU Erlangen-Nuremberg, supervised by Prof. Dr.-Ing. habil. Andreas Maier.
Background
- Research interests include medical image processing, computer vision, deep learning, and machine learning. He has developed deep learning models for cardiovascular MR segmentation/quantification, unsupervised domain adaptation for cross-modality imaging, and multi-modal breast cancer diagnosis.
Miscellany
- Contact: sulaiman.vesal@fau.de; Links: Google Scholar, Twitter, Github, ResearchGate
