Dr. Hannes Nickisch Profile

Dr. Hannes Nickisch

SPIE Involvement:

Author

Area of Expertise:

Medical Image Processing , Probabilistic Machine Learning , Gaussian Processes

Websites:

Personal Website

Publications (9)

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 +

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 | 2 March 2018 Presentation + Paper

Nearest neighbor 3D segmentation with context features

Evelin Hristova, Heinrich Schulz, Tom Brosch, Mattias Heinrich, Hannes Nickisch

Proceedings Volume 10574, 105740M (2018) https://doi.org/10.1117/12.2292181

KEYWORDS: Image segmentation, Kidney, Binary data, Feature extraction, Computed tomography, Magnetic resonance imaging, Liver, Bladder, Prostate, Spleen

Read Abstract +

Proceedings Article | 2 March 2018 Paper

Orientation regression in hand radiographs: a transfer learning approach

Ivo M. Baltruschat, Axel Saalbach, Mattias Heinrich, Hannes Nickisch, Sascha Jockel

Proceedings Volume 10574, 105741W (2018) https://doi.org/10.1117/12.2291620

KEYWORDS: X-rays, X-ray imaging, Radiography, Medical imaging, Neural networks, Automatic alignment, X-ray detectors, Chest, Digital x-ray imaging, Digital imaging

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 | 21 March 2016 Paper

Automatic coronary lumen segmentation with partial volume modeling improves lesions' hemodynamic significance assessment

M. Freiman, Y. Lamash, G. Gilboa, H. Nickisch, S. Prevrhal, H. Schmitt, M. Vembar, L. Goshen

Proceedings Volume 9784, 978403 (2016) https://doi.org/10.1117/12.2209476

KEYWORDS: Hemodynamics, Image segmentation, Arteries, Computer simulations, Image analysis, Angiography, 3D modeling, Solid modeling, Computed tomography, Computer aided design, Binary data, Computer aided diagnosis and therapy, Data modeling

Read Abstract +

Proceedings Article | 21 March 2016 Paper

SVM-based failure detection of GHT localizations

T. Blaffert, C. Lorenz, H. Nickisch, J. Peters, J. Weese

Proceedings Volume 9784, 97841J (2016) https://doi.org/10.1117/12.2216855

KEYWORDS: Image segmentation, Medical imaging, Hough transforms, Model-based design, Image analysis, Machine learning, Pattern recognition, Heart, Arteries, Veins, 3D modeling, Data modeling, Computed tomography, Inspection

Read Abstract +

Showing 5 of 9 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years