Mr. Maximilian Rohleder Profile

Maximilian Rohleder

at Friedrich-Alexander-Univ. Erlangen-Nürnberg

SPIE Involvement:

Author

Area of Expertise:

Cone Beam CT , Deep Learning , Operator Learning , Metal Artifact Reduction

Maximilian Rohleder is a doctoral researcher from Munich, Germany. He is conducting his doctoral research in a collaboration between Friedrich-Alexander-University (FAU) and Siemens Healthineers with roles both in Mobile C-Arms Systems pre-development and at the university. In summer 2022, he visited the I-Star Laboratory at Johns Hopkins University to further investigate the topic of Metal Artifact Avoidance. Max studied Medical Engineering at FAU and the University of Lisbon (Instituto Superior Técnico) and conducted his Bachelor levels research at Stanford University. His research interests include new 2D and 3D imaging workflows for intraoperative Cone-Beam CT, the simulation of realistic X-Ray data, and integration of reconstruction operators in Neural Network architectures.

Proceedings Article | 3 April 2024 Poster + Paper

Geometric domain adaptation for CBCT segmentation

Anne Querfurth, Maximilian Rohleder, Andreas Maier, Wolfgang Hohenforst Schmidt, Holger Kunze

Proceedings Volume 12927, 129273B (2024) https://doi.org/10.1117/12.3005483

KEYWORDS: Cone beam computed tomography, Voxels, Image segmentation, Lung, Computed tomography, Medical imaging

Read Abstract +

Proceedings Article | 1 April 2024 Poster + Paper

3D metal segmentation from few x-ray images for metal artifact avoidance

Maximilian Rohleder, Holger Kunze, Andreas Maier, Bjoern Kreher

Proceedings Volume 12925, 129253C (2024) https://doi.org/10.1117/12.3005260

KEYWORDS: Image segmentation, Metals, Data modeling, Cone beam computed tomography, 3D projection, Matrices, X-rays, X-ray imaging, Deep learning

Read Abstract +

Intraoperative Cone Beam CT (CBCT) is routinely used for implant placement verification but is confounded by metal artifacts obscuring the clinically relevant area around implants. This work reports a novel method to estimate a metal distribution from as few as two scout views which enables existing Metal Artifact Avoidance (MAA) methods to predict an artifact minimized scanning trajectory. A new model architecture was developed to directly predict a volumetric metal segmentation from given projection images. This is achieved by embedding a differentiable back projection operator into the model architecture which allows the network to transfer features extracted from projection images into the reconstruction domain. To ensure a generalization to clinical data, the model is trained on projection images from clinical and pre-clinical CBCT scans. The metal labels are generated by a previously trained model segmenting metal in the CBCT reconstructions. To counteract the limited available dataset sizes, a geometric data augmentation strategy is presented, which reflects transformations applied to the pixel data in the applied projection geometry. We evaluate the effects of this data augmentation and additionally assess the model’s performance increase with respect to additional supplied views. The newly introduced method achieves an average segmentation quality of 0.66±0.15 measured by the dice coefficient on the test set which is comparable to methods from literature requiring six views. The suggested data augmentation method has a strong regularizing impact on model convergence, resulting in improved generalization over the non-augmented trainings. When presented with a third view, the model’s performance on average increases by 9.1% without re-training and 12.1% after finetuning. The presented method achieves competitive segmentation performance with only two scout images on realistic clinical data. This enables the application of existing MAA methods in the current clinical workflow without the need to acquire additional X-Ray scouts.

Proceedings Article | 7 April 2023 Presentation + Paper

Cone-beam CT trajectory optimization for metal artifact avoidance using ellipsoidal object parameterizations

M. Rohleder, L. Mekki, A. Uneri, A. Sisniega, H. Kunze, G. Kleinszig, A. Maier, B. Kreher, J. Siewerdsen

Proceedings Volume 12463, 1246312 (2023) https://doi.org/10.1117/12.2654349

KEYWORDS: Metals, 3D modeling, Image restoration, Cone beam computed tomography, Signal attenuation, Image segmentation, 3D projection, Prior knowledge, Expectation maximization algorithms, X-ray imaging

Read Abstract +

Metal Artifacts remain a problem in Cone-Beam CT (CBCT) imaging, especially reducing clinical value in trauma applications by obscuring the important area around implants. Building on existing Metal Artifact Avoidance (MAA) algorithms, we formulate a metric based on the scatter fraction, introduce a shape model which reduces computational requirements and analyze the feasibility of using only two scout views as prior information.

Driven by the observation that orbit optimization requires knowledge of the position, extent, and orientation of metallic objects in the volume of interest (VOI), we devise a shape model in the form of ellipsoids. Reconstructing an ellipsoid from two projection images is not unambiguously possible using analytic methods. By interpreting the problem as probability density estimation, a maximum likelihood fit can be recovered using a Gaussian Mixture Model (GMM). This parametric representation of metal objects is used to efficiently calculate metal pathlength maps for candidate projections on tilted circular trajectories through analytic forward projection. The scatter fraction behind the metal object is modelled as a function of metal pathlength to score views and choose artifact minimizing tilted trajectories.

Given two projection images of simulated ellipsoidal objects, the GMM accurately estimates the position and longest axis length within millimeter tolerance. Depending on the orientation relative to the two acquired scout views, an estimation error within the scout-view plane is observed. The generalization on measured data and the shape model hypothesis is verified in a phantom study showing a good correspondence of the modelled metric and observed reduction of artifacts in the tilted CBCT scans.

The severity of Metal Artifacts can be reduced by optimizing trajectories on low-fidelity shape models. These surrogate representations can be efficiently estimated from two views for most relative object orientations, but a well-defined ‘blind spot’ remains. The reconstruction error was found to have little effect on tilted orbit optimization if the tilt-axis is contained in the scout-view plane.

Proceedings Article | 18 October 2022 Open Access

Cross-domain metal segmentation for CBCT metal artifact reduction

Maximilian Rohleder, Tristan Gottschalk, Andreas Maier, Bjoern Kreher

Proceedings Volume 12304, 123040K (2022) https://doi.org/10.1117/12.2646382

KEYWORDS: Metals, Image segmentation, X-ray computed tomography, X-ray imaging, Network architectures, Neural networks, 3D image reconstruction, Machine learning

Read Abstract +

DOWNLOAD PAPER

Keywords/Phrases

Search In:

Publication Years