Hemin Ali Qadir
- Researcher; PhD
About
Hemin Ali Qadir is an AI researcher at the Intervention Centre (IVS), the Technology and Innovation Clinic, Oslo University Hospital (OUS). He holds an MSc. in computer engineering with a focus on image processing and computer vision from the Florida Institute of Technology, Florida, USA since 2013. He furthered his academic journey by completing a Ph.D. in the informatics department at Faculty of Mathematics and Natural Sciences from at the University of Oslo in 2020, specializing in Machine Learning and Deep Learning for image processing and computer vision, particularly applied to medical image analysis and understanding. Throughout his distinguished research career, he has authored over 20 scientific papers in prestigious journals and conferences, contributing significantly to fields such as image processing and computer vision, medical image analysis, deep learning and artificial intelligence.
Hemin possesses over a decade of extensive teaching experience in the field of computer engineering and science and related disciplines, He's had the privilege of instructing a diverse array of undergraduate and graduate courses. These encompassed vital subjects such as Data Science, Digital Signal Processing, Machine Learning, Object Oriented Programming, Artificial Intelligence (AI), Image Processing, Computer Vision, mathematics, and electronics. From mentoring in practical applications to providing comprehensive theoretical knowledge, his commitment to fostering a robust learning environment has been a consistent hallmark across his roles as a visiting assistant professor, lecturer, and teaching assistant.
Hemin has been honored with multiple awards for his exceptional contributions to research during both his master's and Ph.D. studies, including the DRS Technologies recognition in 2013 for exceptional innovation in utilizing the company's Infrared Camera, Achieved second place in the MICCAI 2017 challenge held in Quebec, Canada, for pioneering work in angiodysplasia detection and localization, as well as securing third place for polyp detection and localization in the same competition. Further accolades include clinching the first prize for polyp segmentation at MICCAI 2018 in Granada, Spain.
Research Profile
Hemin Qadir's primary focus lies in the advancement of robust and generalized multimodal AI algorithms aimed at extracting valuable insights from a spectrum of clinical data types. His research spans the integration and analysis of diverse data modalities, including tabular, 2D/3D imaging, genomic, proteomic, and various multidimensional datasets within the healthcare domain. With a keen focus on revolutionizing healthcare practices, Hemin aspires to contribute significantly to the fields of diagnosis, prognosis, and the critical evaluation of treatment efficacy. His proactive leadership and unwavering enthusiasm are poised to redefine the landscape of medical AI, fostering breakthroughs that promise to elevate patient care and outcomes.
Links
Publications 2024
Deep learning-assisted survival prognosis in renal cancer: A CT scan-based personalized approach
Heliyon, 10 (2), e24374
DOI 10.1016/j.heliyon.2024.e24374, PubMed 38298725
Multimodal Deep Learning Improves Recurrence Risk Prediction in Pediatric Low-Grade Gliomas
Neuro Oncol (in press)
DOI 10.1093/neuonc/noae173, PubMed 39211987
Publications 2023
Multimodal deep learning for personalized renal cell carcinoma prognosis: Integrating CT imaging and clinical data
Comput Methods Programs Biomed, 244, 107978
DOI 10.1016/j.cmpb.2023.107978, PubMed 38113804
Publications 2020
Toward real-time polyp detection using fully CNNs for 2D Gaussian shapes prediction
Med Image Anal, 68, 101897
DOI 10.1016/j.media.2020.101897, PubMed 33260111
Publications 2019
Improving Automatic Polyp Detection Using CNN by Exploiting Temporal Dependency in Colonoscopy Video
IEEE J Biomed Health Inform, 24 (1), 180-193
DOI 10.1109/JBHI.2019.2907434, PubMed 30946683
Polyp Detection and Segmentation using Mask R-CNN: Does a Deeper Feature Extractor CNN Always Perform Better?
INT SYM MED INFORM, 181-186
A Framework With a Fully Convolutional Neural Network for Semi-Automatic Colon Polyp Annotation
IEEE Access, 7, 169537-169547
DOI 10.1109/ACCESS.2019.2954675
Publications 2018
Abnormal Colon Polyp Image Synthesis Using Conditional Adversarial Networks for Improved Detection Performance
IEEE Access, 6, 56007-56017
DOI 10.1109/ACCESS.2018.2872717
Automatic Colon Polyp Detection Using Region Based Deep CNN and Post Learning Approaches
IEEE Access, 6, 40950-40962
DOI 10.1109/ACCESS.2018.2856402