Interventional Imaging |

Interventional Imaging |https://albarqouni.github.io/areas/interventional-imaging/Interventional ImagingHugoBlox Kit (https://hugoblox.com)en-ushttps://albarqouni.github.io/media/logo_hu_43a0798e7da4e673.pngInterventional Imaginghttps://albarqouni.github.io/areas/interventional-imaging/SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions--An EndoVis' 24 Challengehttps://albarqouni.github.io/publications/ding-2024-segstrong/Thu, 01 Jan 2026 00:00:00 +0000https://albarqouni.github.io/publications/ding-2024-segstrong/Robust surgical tool segmentation with state-space vision modelshttps://albarqouni.github.io/projects/surgical-tools/Mon, 01 Jan 2024 00:00:00 +0000https://albarqouni.github.io/projects/surgical-tools/<p>This exploratory collaboration investigated state-space vision models for robust surgical tool segmentation under realistic visual corruptions. In collaboration with Kyung Hee University, we participated in the MICCAI EndoVis 2024 SegSTRONG-C challenge, benchmarking robustness to non-adversarial corruptions such as smoke, bleeding, and illumination changes. The proposed Vision Mamba–UNet approach achieved competitive performance across corruption types and ranked 7th overall among international submissions.</p> <h3 id="perspective">Perspective</h3> <p>The project supported early exploration of state-space models in medical image analysis and international doctoral mentorship. A jointly submitted DAAD exchange proposal, although not funded, laid the groundwork for continued collaboration and future joint research activities.</p>Eine computergestützte automatische Polypencharakterisierung von Hyperplasten, Adenomen und Serratierten Adenomen im Kolorektum-Ergebnisse der CASSANDRA Studiehttps://albarqouni.github.io/publications/zvereva-2021-computergestutzte/Fri, 01 Jan 2021 00:00:00 +0000https://albarqouni.github.io/publications/zvereva-2021-computergestutzte/A learning without forgetting approach to incorporate artifact knowledge in polyp localization taskshttps://albarqouni.github.io/publications/soberanis-2020-learning/Wed, 01 Jan 2020 00:00:00 +0000https://albarqouni.github.io/publications/soberanis-2020-learning/An objective comparison of detection and segmentation algorithms for artefacts in clinical endoscopyhttps://albarqouni.github.io/publications/ali-2020-objective/Wed, 01 Jan 2020 00:00:00 +0000https://albarqouni.github.io/publications/ali-2020-objective/Polyp-artifact relationship analysis using graph inductive learned representationshttps://albarqouni.github.io/publications/soberanis-2020-polyp/Wed, 01 Jan 2020 00:00:00 +0000https://albarqouni.github.io/publications/soberanis-2020-polyp/Precise proximal femur fracture classification for interactive training and surgical planning.https://albarqouni.github.io/publications/jimenez-2020-precise/Wed, 01 Jan 2020 00:00:00 +0000https://albarqouni.github.io/publications/jimenez-2020-precise/Understanding the effects of artifacts on automated polyp detection and incorporating that knowledge via learning without forgettinghttps://albarqouni.github.io/publications/kayser-2020-understanding/Wed, 01 Jan 2020 00:00:00 +0000https://albarqouni.github.io/publications/kayser-2020-understanding/Focal loss for artefact detection in medical endoscopyhttps://albarqouni.github.io/publications/kayser-2019-focal/Tue, 01 Jan 2019 00:00:00 +0000https://albarqouni.github.io/publications/kayser-2019-focal/Learning-based x-ray image denoising utilizing model-based image simulationshttps://albarqouni.github.io/publications/hariharan-2019-learning/Tue, 01 Jan 2019 00:00:00 +0000https://albarqouni.github.io/publications/hariharan-2019-learning/Machine Learning and Medical Engineering for Cardiovascular Health and Intravascular Imaging and Computer Assisted Stenting: First International Workshop, MLMECH 2019, and 8th Joint International Workshop, CVII-STENT 2019, Held in Conjunction with MICCAI 2019, Shenzhen, China, October 13, 2019, Proceedingshttps://albarqouni.github.io/publications/liao-2019-machine/Tue, 01 Jan 2019 00:00:00 +0000https://albarqouni.github.io/publications/liao-2019-machine/Preliminary results of DSA denoising based on a weighted low-rank approach using an advanced neurovascular replication systemhttps://albarqouni.github.io/publications/hariharan-2019-preliminary/Tue, 01 Jan 2019 00:00:00 +0000https://albarqouni.github.io/publications/hariharan-2019-preliminary/A photon recycling approach to the denoising of ultra-low dose X-ray sequenceshttps://albarqouni.github.io/publications/hariharan-2018-photon/Mon, 01 Jan 2018 00:00:00 +0000https://albarqouni.github.io/publications/hariharan-2018-photon/Intraoperative stent segmentation in X-ray fluoroscopy for endovascular aortic repairhttps://albarqouni.github.io/publications/breininger-2018-intraoperative/Mon, 01 Jan 2018 00:00:00 +0000https://albarqouni.github.io/publications/breininger-2018-intraoperative/Intravascular Imaging and Computer Assisted Stenting and Large-scale Annotation of Biomedical Data and Expert Label Synthesis: 7th Joint International Workshop, CVII-STENT 2018 and Third International Workshop, LABELS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 16, 2018, Proceedingshttps://albarqouni.github.io/publications/stoyanov-2018-intravascular/Mon, 01 Jan 2018 00:00:00 +0000https://albarqouni.github.io/publications/stoyanov-2018-intravascular/Intravascular Imaging and Computer Assisted Stenting, and Large-Scale Annotation of Biomedical Data and Expert Label Synthesishttps://albarqouni.github.io/publications/cardoso-2017-intravascular/Mon, 01 Jan 2018 00:00:00 +0000https://albarqouni.github.io/publications/cardoso-2017-intravascular/LABELS 2018 Prefacehttps://albarqouni.github.io/publications/sznitman-2018-labels/Mon, 01 Jan 2018 00:00:00 +0000https://albarqouni.github.io/publications/sznitman-2018-labels/Multiple device segmentation for fluoroscopic imaging using multi-task learninghttps://albarqouni.github.io/publications/breininger-2018-multiple/Mon, 01 Jan 2018 00:00:00 +0000https://albarqouni.github.io/publications/breininger-2018-multiple/X-ray Depthmaps: Revealing the Hidden Structureshttps://albarqouni.github.io/publications/demirci-2018-x/Mon, 01 Jan 2018 00:00:00 +0000https://albarqouni.github.io/publications/demirci-2018-x/Machine Learning for Biomedical Applications: From Crowdsourcing to Deep Learninghttps://albarqouni.github.io/publications/albarqouni-2017-machine/Sun, 01 Jan 2017 00:00:00 +0000https://albarqouni.github.io/publications/albarqouni-2017-machine/X-ray in-depth decomposition: Revealing the latent structureshttps://albarqouni.github.io/publications/albarqouni-2017-x/Sun, 01 Jan 2017 00:00:00 +0000https://albarqouni.github.io/publications/albarqouni-2017-x/Cathnets: detection and single-view depth prediction of catheter electrodeshttps://albarqouni.github.io/publications/baur-2016-cathnets/Fri, 01 Jan 2016 00:00:00 +0000https://albarqouni.github.io/publications/baur-2016-cathnets/Optimisation of X-ray images with respect to image quality and dosehttps://albarqouni.github.io/projects/siemens-xray-dose/Fri, 01 Jan 2016 00:00:00 +0000https://albarqouni.github.io/projects/siemens-xray-dose/<p>X-ray guidance is at the heart of interventional procedures, but it exposes patients — and clinical staff, over a whole career — to ionising radiation. Following the “as low as reasonably achievable” principle, the dose can only be lowered if the image quality is kept, yet lower dose means fewer photons and noisier images, and at very low dose conventional denoisers oversmooth or create artefacts. Supervised deep learning would need aligned low- and high-dose image pairs, which cannot ethically be acquired during an intervention.</p> <h3 id="what-we-did">What we did</h3> <ul> <li><strong>Photon recycling for ultra-low-dose sequences.</strong> A patch-based spatio-temporal denoiser with a properly parameterised Poisson–Gaussian noise model exploits non-local self-similarity across frames and low-rank approximation, without needing an initial estimate — better denoising at lower computational cost ( ).</li> <li><strong>Low-dose digital subtraction angiography.</strong> Spatially aligned DSA frames vary mainly through the flow of contrast agent, so a constrained, weighted rank-1 approximation of the temporal stack denoises each frame — evaluated with an advanced neurovascular replication system towards reducing both X-ray dose and contrast agent ( ).</li> <li><strong>Learning to denoise without clean images.</strong> A model-based simulation of realistic low-dose X-ray images — accounting for system gain, electronic noise and detector blur — generates training data from routine acquisitions, and the same imaging model normalises the input through noise-variance stabilisation. The resulting real-time network outperformed BM3D and WNNM on phantom and clinical data and was preferred by experts for sharp, artefact-free and realistic results ( ).</li> </ul> <h3 id="our-role">Our role</h3> <p>Scientific lead of the project as postdoc at TUM CAMP under Nassir Navab (PI and main supervisor), and mentoring of Sai Gokul Hariharan’s industrial PhD, run jointly with Norbert Strobel and Markus Kowarschik at Siemens Healthineers and completed at TU Munich in 2023.</p> <h3 id="perspective">Perspective</h3> <p>The thesis concluded that the X-ray dose can be reduced substantially without sacrificing clinically relevant information; the work continued at Siemens Healthineers in patents on X-ray noise reduction.</p>Single-view X-ray depth recovery: toward a novel concept for image-guided interventionshttps://albarqouni.github.io/publications/albarqouni-2016-single/Fri, 01 Jan 2016 00:00:00 +0000https://albarqouni.github.io/publications/albarqouni-2016-single/