Dr. Michael Grass Profile

Dr. Michael Grass

Principal Scientist at Philips GmbH Innovative Technologies

SPIE Involvement:

Author

Area of Expertise:

Image Reconstruction , Image Guided Interventions , Neural Networks , Computed Tomography , Cardiac Imaging , Artificial Intelligence

Websites:

Personal Website | Company Website

Publications (35)

Proceedings Article | 2 April 2024 Presentation + Paper

On TotalSegmentator’s performance on low-dose CT images

A. Tsanda, H. Nickisch, T. Wissel, T. Klinder, T. Knopp, M. Grass

Proceedings Volume 12926, 129260B (2024) https://doi.org/10.1117/12.3000186

KEYWORDS: Image segmentation, Computed tomography, X-ray computed tomography, Neural networks, Deep learning

Read Abstract +

Proceedings Article | 1 April 2024 Poster + Paper

Improved coronary artery calcium (CAC) detection in conventional CT with deep-learning image de-blurring

Christian Wülker, Niels van der Werf, Nikolas Schnellbächer, Marcel J. Greuter, Michael Grass

Proceedings Volume 12925, 129252B (2024) https://doi.org/10.1117/12.3006693

KEYWORDS: Deblurring, Computed tomography, Medical image reconstruction, Image quality, Image sharpness, Image processing, Arteries, Calcium, Denoising, Deep learning, Artificial intelligence

Read Abstract +

SPIE Journal Paper | 28 March 2022

Cascaded learning in intravascular ultrasound: coronary stent delineation in manual pullbacks

Tobias Wissel, Katharina Riedl, Klaus Schaefers, Hannes Nickisch, Fabian Brunner, Nikolas Schnellbächer, Stefan Blankenberg, Moritz Seiffert, Michael Grass

JMI, Vol. 9, Issue 02, 025001, (March 2022) https://doi.org/10.1117/12.10.1117/1.JMI.9.2.025001

KEYWORDS: Intravascular ultrasound, Image segmentation, Sensors, Computer programming, Calcium, Transducers, Speckle, Image resolution, Data modeling, Monte Carlo methods

Read Abstract +

Purpose: Implanting stents to re-open stenotic lesions during percutaneous coronary interventions is considered a standard treatment for acute or chronic coronary syndrome. Intravascular ultrasound (IVUS) can be used to guide and assess the technical success of these interventions. Automatically segmenting stent struts in IVUS sequences improves workflow efficiency but is non-trivial due to a challenging image appearance entailing manifold ambiguities with other structures. Manual, ungated IVUS pullbacks constitute a challenge in this context. We propose a fully data-driven strategy to first longitudinally detect and subsequently segment stent struts in IVUS frames. Approach: A cascaded deep learning approach is presented. It first trains an encoder model to classify frames as “stent,” “no stent,” or “no use.” A segmentation model then delineates stent struts on a pixel level only in frames with a stent label. The first stage of the cascade acts as a gateway to reduce the risk for false positives in the second stage, the segmentation, which is trained on a smaller and difficult-to-annotate dataset. Training of the classification and segmentation model was based on 49,888 and 1826 frames of 74 sequences from 35 patients, respectively. Results: The longitudinal classification yielded Dice scores of 92.96%, 82.35%, and 94.03% for the classes stent, no stent, and no use, respectively. The segmentation achieved a Dice score of 65.1% on the stent ground truth (intra-observer performance: 75.5%) and 43.5% on all frames (including frames without stent, with guidewires, calcium, or without clinical use). The latter improved to 49.5% when gating the frames by the classification decision and further increased to 57.4% with a heuristic on the plausible stent strut area. Conclusions: A data-driven strategy for segmenting stents in ungated, manual pullbacks was presented—the most common and practical scenario in the time-critical clinical workflow. We demonstrated a mitigated risk for ambiguities and false positive predictions.

Proceedings Article | 15 February 2021 Poster + Presentation + Paper

Machine-learning-based clinical plaque detection using a synthetic plaque lesion model for coronary CTA

Nikolas Schnellbächer, Haissam Ragab, Hannes Nickisch, Tobias Wissel, Clemens Spink, Gunnar Lund, Michael Grass

Proceedings Volume 11597, 115972T (2021) https://doi.org/10.1117/12.2582195

KEYWORDS: Solid modeling, Diagnostics, Nuclear medicine, Neural networks, Image-guided intervention, Image classification, Computer programming, Computer aided diagnosis and therapy, Computed tomography, Arteries

Read Abstract +

Coronary computed tomography angiography (coronary CTA) is a robust and well-established non-invasive diagnostic tool to detect and assess coronary artery disease (CAD). The accurate detection, quantification and characterization of the coronary plaque burden has become an important part of this imaging modality. The quality and performance of modern machine-learning-based data-driven learning approaches is often impacted by either insufficient or inconsistently-labeled training data and is further subject to additional bias from human annotators. To address these shortcomings for coronary plaque characterization, we have developed a synthetic lesion generating framework for CTA applications, which can produce accurate and high-quality labeled training data for data-driven learning approaches. This approach can help to ease the manual annotation burden, which is often the limiting factor in data-driven learning algorithms and instead provides reliable ground truth data for modern deep learning approaches. Furthermore, this framework can easily be used to create custom tailored training data that can be used for pre- or post-training steps of already existing machine learning approaches for CTA applications. We tested this data generation framework by inserting synthetic lesions in 11 clinical CTA scans of healthy patients resulting in a data set of ~7000 annotated 2D slices. With this data we performed several plaque detection experiments using a data-driven machine learning approach with a neural encoder architecture. In this plaque classification task we first demonstrate that the synthetic lesion generation module can consistently perform well in recognizing unseen synthetic test data with an overall classification accuracy of 93%. Next we apply the synthetic lesion framework in a transfer learning experiment, where we demonstrate the feasibility to learn to classify real clinical plaque lesions with a purely synthetic model (overall classification accuracy 84%) that never saw real clinical lesions during model training. Second, we show that using synthetically data for pre-training with a subsequent training on clinical data can enhance the overall classification accuracy (from 91% to 92%) while strongly increasing the true positive count. We conclude that the synthetic plaque lesions model faithfully covers many important image characteristics of real plaque lesions in coronary CTA imaging and can thus help reduce the annotation burden for data-driven predictive vascular systems in this domain. This allows the creation of exhaustively annotated and site-specific customizable training data with a computationally fast forward model.

Proceedings Article | 15 February 2021 Presentation + Paper

Delineation of coronary stents in intravascular ultrasound pullbacks

Tobias Wissel, Katharina Riedl, Klaus Schaefers, Hannes Nickisch, Fabian Brunner, Nikolas Schnellbaecher, Stefan Blankenberg, Moritz Seiffert, Michael Grass

Proceedings Volume 11598, 115980Y (2021) https://doi.org/10.1117/12.2580710

KEYWORDS: Intravascular ultrasound, Computer programming, Heart, Image segmentation, Cardiology, Calcium

Read Abstract +

Proceedings Article | 15 February 2021 Presentation + Paper

Tailored methods for segmentation of intravascular ultrasound images via convolutional neural networks

Lennart Bargsten, Katharina Riedl, Tobias Wissel, Fabian Brunner, Klaus Schaefers, Johanna Sprenger, Michael Grass, Moritz Seiffert, Stefan Blankenberg, Alexander Schlaefer

Proceedings Volume 11602, 1160204 (2021) https://doi.org/10.1117/12.2580720

KEYWORDS: Image segmentation, Intravascular ultrasound, Convolutional neural networks, Independent component analysis, Arteries, Speckle, Shape analysis, Optical coherence tomography, Error analysis

Read Abstract +

Proceedings Article | 28 May 2019 Paper

Reduction of metal artefacts in CBCT caused by needles crossing the FOV border

Dirk Schäfer, Christian Haase, William van der Sterren, Michael Grass

Proceedings Volume 11072, 110720H (2019) https://doi.org/10.1117/12.2534839

KEYWORDS: Metals, Biopsy, Medicine, CT reconstruction, Computer simulations, Computed tomography, Reconstruction algorithms, 3D acquisition, Detection and tracking algorithms

Read Abstract +

Proceedings Article | 9 March 2018 Paper

Motion compensated reconstruction of the aortic valve for computed tomography

T. Elss, R. Bippus, H. Schmitt, T. Ivanc, M. Morlock, M. Grass

Proceedings Volume 10573, 1057331 (2018) https://doi.org/10.1117/12.2292877

KEYWORDS: Computed tomography, Heart, Image filtering, Printed circuit board testing, Motion estimation, Scanners, Image quality, CT reconstruction, Image registration, Aorta

Read Abstract +

Proceedings Article | 9 March 2018 Paper

Motion compensation for non-gated helical CT: application to lung imaging

M. Grass, R. Bippus, A. Thran, D. Schäfer, S. Kabus, K. Brown

Proceedings Volume 10573, 105733H (2018) https://doi.org/10.1117/12.2292879

KEYWORDS: Computed tomography, Lung imaging, Lung, Image registration, Motion estimation, Scanners, Data acquisition, 3D image reconstruction, CT reconstruction, Reconstruction algorithms

Read Abstract +

Proceedings Article | 2 March 2018 Paper

Deep-learning-based CT motion artifact recognition in coronary arteries

T. Elss, H. Nickisch, T. Wissel, H. Schmitt, M. Vembar, M. Morlock, M. Grass

Proceedings Volume 10574, 1057416 (2018) https://doi.org/10.1117/12.2292882

KEYWORDS: Motion measurement, Arteries, Motion models, Data modeling, Computed tomography, Machine learning, 3D modeling, Heart, 3D image processing, Neural networks

Read Abstract +

Proceedings Article | 3 March 2017 Paper

Spine segmentation from C-arm CT data sets: application to region-of-interest volumes for spinal interventions

C. Buerger, C. Lorenz, D. Babic, J. Hoppenbrouwers, R. Homan, R. Nachabe, J. Racadio, M. Grass

Proceedings Volume 10135, 101351N (2017) https://doi.org/10.1117/12.2249031

KEYWORDS: Image segmentation, Spine, X-ray computed tomography, 3D image processing, Data modeling, X-rays, Surgery, Image quality, Computed tomography, Image fusion, 3D modeling

Read Abstract +

Proceedings Article | 19 March 2014 Paper

Automatic cable artifact removal for cardiac C-arm CT imaging

C. Haase, D. Schäfer, M. Kim, S. J. Chen, J. Carroll, P. Eshuis, O. Dössel, M. Grass

Proceedings Volume 9033, 90330K (2014) https://doi.org/10.1117/12.2043488

KEYWORDS: X-ray computed tomography, Reconstruction algorithms, Image segmentation, Image quality, Heart, Sensors, X-rays, Metals, Imaging systems, 3D acquisition

Read Abstract +

Proceedings Article | 3 March 2012 Paper

Generalized filtered back-projection for digital breast tomosynthesis reconstruction

Klaus Erhard, Michael Grass, Sebastian Hitziger, Armin Iske, Tim Nielsen

Proceedings Volume 8313, 831320 (2012) https://doi.org/10.1117/12.911163

KEYWORDS: Reconstruction algorithms, Digital breast tomosynthesis, Image quality, Sensors, Image filtering, Image quality standards, Breast, Tomography, Signal attenuation, X-rays

Read Abstract +

Proceedings Article | 3 March 2012 Paper

Low kV rotational 3D x-ray imaging for improved CNR of iodine contrast agent

Dirk Schäfer, Martin Ahrens, Peter Eshuis, Michael Grass

Proceedings Volume 8313, 83132V (2012) https://doi.org/10.1117/12.909909

KEYWORDS: Iodine, Copper, X-rays, X-ray imaging, 3D image processing, X-ray computed tomography, Tissues, 3D acquisition, Polymethylmethacrylate, Visibility

Read Abstract +

Proceedings Article | 3 March 2012 Paper

Breathing motion compensated reconstruction for C-arm cone beam CT imaging: initial experience based on animal data

D. Schäfer, M. Lin, P. Rao, R. Loffroy, E. Liapi, N. Noordhoek, P. Eshuis, A. Radaelli, M. Grass, J.-F. Geschwind

Proceedings Volume 8313, 83131D (2012) https://doi.org/10.1117/12.909914

KEYWORDS: Image segmentation, Image quality, Image filtering, Imaging systems, Motion estimation, Tumors, Tomography, Stereoscopy, 3D image processing, Spine

Read Abstract +

Proceedings Article | 17 February 2012 Paper

Automated volume of interest delineation and rendering of cone beam CT images in interventional cardiology

Cristian Lorenz, Dirk Schäfer, Peter Eshuis, John Carroll, Michael Grass

Proceedings Volume 8316, 831606 (2012) https://doi.org/10.1117/12.910962

KEYWORDS: Data modeling, Spine, Computed tomography, Image segmentation, Performance modeling, X-ray computed tomography, 3D image processing, Cardiology, Lung, Chest

Read Abstract +

Proceedings Article | 16 March 2011 Paper

A second pass correction method for calcification artifacts in digital breast tomosynthesis

Klaus Erhard, Michael Grass, Tim Nielsen

Proceedings Volume 7961, 796119 (2011) https://doi.org/10.1117/12.877949

KEYWORDS: Breast, Image segmentation, Digital breast tomosynthesis, Tissues, Magnetic resonance imaging, Reconstruction algorithms, Sensors, Tomography, Image quality, Mammography

Read Abstract +

Proceedings Article | 24 February 2010 Paper

Artifact reduction method for improved visualization of 3D coronary artery reconstructions from rotational angiography acquisitions

Anne Neubauer, Eberhard Hansis, John Carroll, Michael Grass

Proceedings Volume 7625, 76250A (2010) https://doi.org/10.1117/12.843824

KEYWORDS: Visualization, 3D image processing, Arteries, Reconstruction algorithms, Angiography, Image segmentation, 3D image reconstruction, 3D acquisition, 3D visualizations, Image processing

Read Abstract +

Proceedings Article | 14 March 2009 Paper

Advanced processing for motion-compensated reconstruction in cardiac cone-beam CT

Udo van Stevendaal, Peter Forthmann, Thomas Köhler, Jens von Berg, Cristian Lorenz, Michael Grass

Proceedings Volume 7258, 725833 (2009) https://doi.org/10.1117/12.811086

KEYWORDS: Heart, Motion models, Reconstruction algorithms, Data modeling, Image quality, Tissues, Computed tomography, Motion estimation, Detection and tracking algorithms, Lung

Read Abstract +

Proceedings Article | 14 March 2009 Paper

A second pass gated reconstruction scheme with conjugate weights

Klaus Erhard, Michael Grass

Proceedings Volume 7258, 725834 (2009) https://doi.org/10.1117/12.812099

KEYWORDS: Data acquisition, Heart, Reconstruction algorithms, Image segmentation, X-rays, Electrocardiography, Data modeling, Signal attenuation, 3D image reconstruction, Arteries

Read Abstract +

Proceedings Article | 11 March 2009 Paper

Four-dimensional cardiac reconstruction from rotational x-ray sequences: first results for 4D coronary angiography

Eberhard Hansis, Hermann Schomberg, Klaus Erhard, Olaf Dössel, Michael Grass

Proceedings Volume 7258, 72580B (2009) https://doi.org/10.1117/12.811104

KEYWORDS: Reconstruction algorithms, Arteries, Motion estimation, Angiography, X-rays, Heart, 3D modeling, 3D image processing, Lithium, Image quality

Read Abstract +

Proceedings Article | 22 March 2007 Paper

Three-dimensional reconstruction of coronary stents in vivo based on motion compensated x-ray angiography

Dirk Schäfer, Babak Movassaghi, Michael Grass, Gert Schoonenberg, Raoul Florent, Onno Wink, Andrew Klein, James Chen, Joel Garcia, John Messenger, John Carroll

Proceedings Volume 6509, 65091M (2007) https://doi.org/10.1117/12.706439

KEYWORDS: X-rays, Angiography, 3D modeling, In vivo imaging, 3D image processing, Data acquisition, Sensors, 3D acquisition, Spatial resolution, Heart

Read Abstract +

Proceedings Article | 21 March 2007 Paper

4D coronary artery reconstruction based on retrospectively gated rotational angiography: first in-human results

B. Movassaghi, M. Grass, D. Schaefer, V. Rasche, O. Wink, G. Schoonenberg, J. Chen, J. Garcia, B. Groves, J. Messenger, J. Carroll

Proceedings Volume 6509, 65090P (2007) https://doi.org/10.1117/12.706435

KEYWORDS: Arteries, Angiography, X-rays, 3D image processing, 3D image reconstruction, 3D acquisition, Data acquisition, X-ray imaging, Sensors, Imaging systems

Read Abstract +

Proceedings Article | 19 March 2007 Paper

Automatic generation of 3D coronary artery centerlines

Uwe Jandt, Dirk Schäfer, Volker Rasche, Michael Grass

Proceedings Volume 6510, 65104Y (2007) https://doi.org/10.1117/12.708941

KEYWORDS: 3D modeling, Arteries, Motion models, X-rays, Angiography, Heart, Quantization, Visualization, Electrocardiography, Computer simulations

Read Abstract +

Proceedings Article | 19 March 2007 Paper

ECG gated circular cone-beam multi-cycle short-scan reconstruction algorithm

Udo van Stevendaal, Peter Koken, Philipp Begemann, Ralf Koester, Gerhard Adam, Michael Grass

Proceedings Volume 6510, 65105P (2007) https://doi.org/10.1117/12.707854

KEYWORDS: Heart, Temporal resolution, Scanners, Beam propagation method, Image quality, Electrocardiography, Sensors, Reconstruction algorithms, Data acquisition, Fluctuations and noise

Read Abstract +

Proceedings Article | 13 March 2007 Paper

An iterative method for the reconstruction of the coronary arteries from rotational x-ray angiography

Eberhard Hansis, Dirk Schäfer, Michael Grass, Olaf Dössel

Proceedings Volume 6510, 651026 (2007) https://doi.org/10.1117/12.709319

KEYWORDS: Arteries, X-rays, Angiography, Electrocardiography, Reconstruction algorithms, Absorption, Iterative methods, 3D image processing, 3D modeling, Data acquisition

Read Abstract +

Proceedings Article | 2 March 2006 Paper

Iterative reconstruction of a region of interest for transmission tomography

Andy Ziegler, Tim Nielsen, Michael Grass

Proceedings Volume 6142, 614223 (2006) https://doi.org/10.1117/12.650666

KEYWORDS: Reconstruction algorithms, Signal to noise ratio, Sensors, Heart, Absorption, Image resolution, Tomography, Photons, Chemical elements, Computed tomography

Read Abstract +

Proceedings Article | 2 March 2006 Paper

ECG gated continuous circular cone-beam multi-cycle reconstruction for in-stent coronary artery imaging: a phantom study

Udo van Stevendaal, Peter Koken, Philipp Begemann, Ralf Koester, Gerhard Adam, Michael Grass

Proceedings Volume 6142, 61420L (2006) https://doi.org/10.1117/12.652011

KEYWORDS: Heart, Temporal resolution, Beam propagation method, Scanners, Sensors, Electrocardiography, Data acquisition, Image quality, Reconstruction algorithms, Visualization

Read Abstract +

Proceedings Article | 12 May 2004 Paper

Iterative cardiac cone-beam CT reconstruction

Tim Nielsen, Robert Manzke, Thomas Koehler, Michael Grass, Roland Proksa

Proceedings Volume 5370, (2004) https://doi.org/10.1117/12.534847

KEYWORDS: Heart, CT reconstruction, Reconstruction algorithms, Computed tomography, Detection and tracking algorithms, Scanners, Image quality, Medical imaging, Image processing, Image resolution

Read Abstract +

Proceedings Article | 12 May 2004 Paper

Automatic phase point determination for cardiac CT imaging

Robert Manzke, Michael Grass, Tim Nielsen, Thomas Koehler, David Hawkes

Proceedings Volume 5370, (2004) https://doi.org/10.1117/12.534108

KEYWORDS: Heart, Computed tomography, Image quality, Electrocardiography, Arteries, Spatial resolution, Data acquisition, Imaging systems, Scanners, Temporal resolution

Read Abstract +

Proceedings Article | 12 May 2004 Paper

Determination of the temporal and spatial resolution in retrospectively gated cardiac cone-beam CT

Udo van Stevendaal, Philipp Begemann, Joern Borgert, Ruediger Grewer, Sascha Krueger, Holger Timinger, Michael Grass

Proceedings Volume 5370, (2004) https://doi.org/10.1117/12.534772

KEYWORDS: Spatial resolution, Heart, Scanners, Temporal resolution, Beam propagation method, Reconstruction algorithms, Computed tomography, Data acquisition, Electrocardiography, Polymethylmethacrylate

Read Abstract +

Proceedings Article | 5 June 2003 Paper

Coherent scatter computed tomography: a novel medical imaging technique

Jens-Peter Schlomka, Adrian Harding, Udo van Stevendaal, Michael Grass, Geoffrey Harding

Proceedings Volume 5030, (2003) https://doi.org/10.1117/12.479949

KEYWORDS: Sensors, Tissues, Collagen, Scattering, X-ray computed tomography, X-rays, Reconstruction algorithms, Signal attenuation, Medical imaging, Photons

Read Abstract +

Proceedings Article | 15 May 2003 Paper

Cardiac image reconstruction on a 16-slice CT scanner using a retrospectively ECG-gated multicycle 3D back-projection algorithm

Gilad Shechter, Galit Naveh, Ami Altman, Roland Proksa, Michael Grass

Proceedings Volume 5032, (2003) https://doi.org/10.1117/12.480117

KEYWORDS: Reconstruction algorithms, Temporal resolution, Heart, 3D image processing, 3D image reconstruction, Visualization, Scanners, Arteries, Computed tomography, Sensors

Read Abstract +

Proceedings Article | 15 May 2003 Paper

Filtered back-projection reconstruction technique for coherent-scatter computed tomography

Udo van Stevendaal, Jens-Peter Schlomka, Michael Grass

Proceedings Volume 5032, (2003) https://doi.org/10.1117/12.480113

KEYWORDS: Computed tomography, Data acquisition, Reconstruction algorithms, Medical imaging, Image processing, Computer simulations, Laser scanners, 3D scanning, Image quality, CT reconstruction

Read Abstract +

Proceedings Article | 9 May 2002 Paper

Three-dimensional imaging using low-end C-arm systems

Joern Luetjens, Reiner Koppe, Erhard Klotz, Michael Grass, Volker Rasche

Proceedings Volume 4684, (2002) https://doi.org/10.1117/12.467239

KEYWORDS: Calibration, Distortion, Image intensifiers, Sensors, X-rays, X-ray imaging, Imaging systems, Magnetism, 3D image processing, Reconstruction algorithms

Read Abstract +