Orcun Göksel
Professor at Department of Information Technology; Vi3; Image Analysis
- Telephone:
- +46 18 471 34 60
- E-mail:
- orcun.goksel@it.uu.se
- Visiting address:
- Hus 10, Lägerhyddsvägen 1
- Postal address:
- Box 337
751 05 UPPSALA
- Academic merits:
- Docent
- ORCID:
- 0000-0002-8639-7373
More information is available to staff who log in.
Short presentation
I am leading the Computer-assisted Applications in Medicine research (CAiM) group.
Here is a visual summary of my research interests.
For further information, please see my webpage at http://goksel.org/
A complete list of publications is available on my website above or on my Google scholar page,
For potential master's thesis projects, please contact by email.
Biography
Dr. Goksel received two BSc degrees in electrical engineering (2001) and in computer engineering/science (2002) from Middle East Technical University, Ankara, Turkey. He received his MASc (2004) and PhD (2009) degrees in the Department of Electrical and Computer Engineering at the University of British Columbia, Vancouver, Canada. Since 2014 he has been an assistant professor at the Department of Information Technology and Electrical Engineering at ETH Zurich, Switzerland. He founded and has been leading the Computer-assisted Applications in Medicine (CAiM) group within the institute Computer Vision Lab. In 2020, he joined the Department of Information Technology at Uppsala University, Sweden, as an associate professor, where he is affiliated with the Centre for Image Analysis as well as the Medtech Science and Innovation Centre.
Dr. Goksel has received the 2016 ETH Spark Award (for most promising invention of the year), the 2014 CTI Swiss MedTech Award, and the 2011 WAGS Innovation in Technology Award (for best dissertation in western North America). He supervised several master's and PhD students as well as postdoctoral fellows.
Research
Computer-assisted Applications in Medicine (CAiM) Group, led by Orcun Göksel, is part of the newly-established Medtech Innovation and Science Centre as well as of the Centre for Image Analysis. CAiM is within the administrative Division of Visual Information and Interaction at the Department of Information Technology of Uppsala University in Sweden.
Basic and applied research in CAiM involve data analysis and information extraction, on topics lying at the intersection of multiple disciplines: computer science, engineering, and medicine. With the involvement of diverse and cross-disciplinary skill-set, the group aims to devise novel imaging and image analysis techniques, and develop them for clinical translation. The group’s efforts push the boundaries of diagnostic and surgical procedures as well as minimally-invasive interventions.
Research in CAiM is conducted in close collaboration with clinical as well as industrial partners, where the research results have a strong translational component, both clinically and commercially. To that end, CAiM aims to develop innovative diagnostic and interventional applications, focusing on data analysis from imaging to abstracting patient-specific models and representations, and from there to optimal intervention planning and intra-operative execution.
Publications
Recent publications
- Model-Based Speed-of-Sound Reconstruction via Interpretable Pruned Priors (2024)
- Speed-of-Sound as a Novel Quantitative Imaging and Characterization Method (2024)
- Speed-of-Sound as a Novel Tissue Characterization Method (2024)
- Detection of Extremely Sparse Key Instances in Whole Slide Cytology Images via Self-supervised One-class Representation Learning (2024)
- Calpain Inhibition Protects against UVB-Induced Degradation of Dermal-Epidermal Junction-Associated Proteins (2024)
All publications
Articles
- Calpain Inhibition Protects against UVB-Induced Degradation of Dermal-Epidermal Junction-Associated Proteins (2024)
- Longevity interventions modulate mechanotransduction and extracellular matrix homeostasis in C. elegans (2024)
- Multi-scale Feature Alignment for Continual Learning of Unlabeled Domains (2024)
- Generative feature-driven image replay for continual learning (2024)
- HDRfeat (2024)
- Analytical Estimation of Beamforming Speed-of-Sound Using Transmission Geometry (2023)
- Generative appearance replay for continual unsupervised domain adaptation (2023)
- Weakly supervised joint whole-slide segmentation and classification in prostate cancer (2023)
- Robust Imaging of Speed-of-Sound Using Virtual Source Transmission (2023)
- Spectral Ultrasound Imaging of Speed-of-Sound and Attenuation Using an Acoustic Mirror (2022)
- Probabilistic spatial analysis in quantitative microscopy with uncertainty-aware cell detection using deep Bayesian regression (2022)
- Hierarchical graph representations in digital pathology (2022)
- Computational analysis of subscapularis tears and pectoralis major transfers on muscular activity (2022)
- Phase-Aberration Correction in Shear-Wave Elastography Imaging Using Local Speed-of-Sound Adaptive Beamforming (2021)
- IJCARS-IPCAI 2021 Special Issue (2021)
- Modality attention and sampling enables deep learning with heterogeneous marker combinations in fluorescence microscopy (2021)
- Learning ultrasound rendering from cross-sectional model slices for simulated training (2021)
- Probabilistic Spatial Analysis in Quantitative Microscopy with Uncertainty-Aware Cell Detection using Deep Bayesian Regression of Density Maps
- Match What Matters: Generative Implicit Feature Replay for Continual Learning
- FGGP: Fixed-Rate Gradient-First Gradual Pruning
Conferences
- Model-Based Speed-of-Sound Reconstruction via Interpretable Pruned Priors (2024)
- Speed-of-Sound as a Novel Quantitative Imaging and Characterization Method (2024)
- Speed-of-Sound as a Novel Tissue Characterization Method (2024)
- Detection of Extremely Sparse Key Instances in Whole Slide Cytology Images via Self-supervised One-class Representation Learning (2024)
- Pulse-Echo Speed-of-Sound as Imaging Biomarker for Breast Density: Virtual Source Acquisitions for In-Vivo Application (2023)
- Sound-Speed Reconstruction with Learned Kernels Based on a Convolutional Formulation of Sound-Speed and Speckle-Shift Relation (2023)
- Speed-of-sound as a Novel Ultrasound Imaging Biomarker for Breast Cancer and Density (2023)
- Model-based Deep Learning of Ultrasound Beamforming (2023)
- Motion Sensitivity of Transmit Sequences for Pulse-Echo Mapping of Sound Speed Based on Apparent Speckle Shifts (2023)
- Mean Speed-of-Sound Estimation Using Geometric Disparities (2022)
- Global Speed-of-Sound Prediction Using Transmission Geometry (2022)
- A unified deep learning approach for OCT segmentation from different devices and retinal diseases (2022)
- Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation (2022)
- Differentiable Zooming for Multiple Instance Learning on Whole-Slide Images (2022)
- Learning Whole-Slide Segmentation from Inexact and Incomplete Labels Using Tissue Graphs (2021)
- Estimating Mean Speed-of-Sound from Sequence-Dependent Geometric Disparities (2021)
- Estimating Mean Speed-of-Sound from Sequence-Dependent Geometric Disparities (2021)
- Time Of Arrival Delineation In Echo Traces For Reflection Ultrasound Tomography (2021)
- Utilizing Uncertainty Estimation in Deep Learning Segmentation of Fluorescence Microscopy Images with Missing Markers (2021)
- Quantifying Explainers of Graph Neural Networks in Computational Pathology (2021)
- Content-Preserving Unpaired Translation from Simulated to Realistic Ultrasound Images (2021)