|
|
Research
My research is mainly focused on the validation, registration, and segmentation of medical images, in particular:- enhancement, segmentation, and registration of angiographic imagery
- vessel modeling
- estimation and analysis of the hemodynamics of blood
- Image-based tracking in fluoroscopic images
- breathing motion compensation in interventional procedures
- analysis, reconstruction, and registration of histology slices
- validation of new imaging technologies via registration to histology
- dynamic analysis of microscopic image sequences
Active research projects
|
|
Estimation of Flow Parameters from X-ray DataRecognizing stenosis in angiographic images is a quite difficult task. Most methods are only 2D so that overlapping, foreshortening or a bad perspective of the view causes a false diagnoses. The aim of this project is to reconstruct the blood flow from 3D X-ray data to get a realistic and patient specific computer fluid dynamic simulation of the blood flow. With this any type of images concerning blood flow can be simulated. Also the perspective of these images can be chosen by the user without taking X-ray images from the patient. |
 |
Registration of Angiographic ImagesAngiographic images visualize vascular structure in different modalities like X-Ray, CT, or MR data sets. In many medical applications, a registration and proper visualization of the data sets, especially the vasculature is useful for a better navigation. The focus of this project lies on 2D/3D registration of angiographic data where intensity-based, feature-based, and hybrid approaches are evaluated, the latter two of them requiring an accurate 2D and 3D segmentation of the data. The main clinical partner is the radiology department of the Universitätsklinikum Großhadern (Ludwig-Maximilian Universität München) , industrial partner is Siemens Medical Solutions, Forchheim. |
 |
Reconstruction and Registration of Histology and Phase Contrast Images for Clinical Validation of Imaging ModalitiesBefore its introduction into the hospital, a new imaging modality has to be validated. In other words, appearing structures need to be correlated to the imaged tissues. Such a cross validation is only meaningful when performed against the gold standard which is histology. Currently, cross validation is performed by qualitative comparison of 3D datasets to 2D histology slices. Since the acquisition of a consistent 3D histology volume is a challenging task, its comparison to the corresponding dataset always remained qualitative.The classic histology procedure can be divided in four steps: pre processing, cutting, post processing and imaging of the tissues. In the first step, the sample is chemically processed to preserve the tissues and is then embedded in a paraffin block. By using a microtome, it is cut in very thin slices, and put on a glass slide. During post processing the sample is stained to enhance the structures of interest. The imaging is performed with a camera mounted in a microscope, or with a dedicated scanner. Several difficulties inherent to this process can have a dramatic influence on the quality of the reconstructed histology volume. For instance, since the cutting process is done manually, problems like flipping, bending or ripping of the slides may happen. If the knife starts to wear off, some banding will appear over the slices. Moreover, a few slices could be missing. Finally since the staining color is time dependent, variation in the color of the slices can occur. In this project, we propose to improve the histology procedure and to develop methods towards a consistent reconstruction of 3D histology volumes. |
 |
Assessment of Fluid Tissue Interaction Using Multi-Modal Image Fusion for Characterization and Progression of Coronary AtherosclerosisCoronary artery diseases such as atherosclerosis are the leading cause of death in the industrialized world. In this project, we develop computational tools for segmentation and registration problems on intravascular images including IVUS (Intravascular Ultrasound) and OCT (Optical Coherence Tomography). One sample component of this project is Automatic Stent Implant Follow-up from Intravascular OCT Pullbacks. The stents are automatically detected and their distribution is analyzed for monitoring of the stents: their malpositioning and/or tissue growth over stent struts. |
 |
Endovascular Stenting of Aortic AneurysmsEndovascular stenting is a minimally invasive treatment technique for aortic aneurysms or dissections. Thereby, a certain aortic prosthesis (stent graft) is placed inside the aortic aneurysm in order to prevent a life-threatening rupture of the aortic wall. Prior to the intervention, a computed tomography angiography (CTA) is acquired on which the surgical staff can measure the parameter of the desired stent graft and finalize the intervention workflow. The entire interventional catheter navigation is done under 2D angiography imaging where the physician is missing the important 3D information. The purpose of our project is two-fold:1. In the planning phase, a modified graph cuts algorithm automatically segments the aorta and aneurysm, so the surgical staff can choose an appropriate type of stent to match the segmented location, length, and diameter of the aneurysm and aorta. By visualizing the defined stent graft next to the three-dimensionally reconstructed aneurysm, mismeasurements can be detected in an early stage. Our main goal is the creation of an interactive simulation system that predicts the behaviour of the aortic wall and the movement of the implanted stent graft. 2. During implantation of the stent graft, after an intensity based registration of CTA and angiography data, the current navigation can be visualized in the 3D CT data set at any time. This includes solutions for electro-magnetic tracking of catheters as well as guide wires and stent grafts. Eventually, Our main goal is the creation of solutions that enable the surgeon to enhance the accuracy of the navigation and positioning, along with a minimum use of angiography, leading to less radiation exposure and less contrast agent injection. |
 |
Semi-Automatic Patellar Cartilage SegmentationDevelopment and refinement of a software system for semi-automatic segmentation of the patellar cartilage is the main goal of this project. By providing tools for sub-pixel accurate edge tracing, automatic contour completion, and adequate visualization, a remarkable speed-up of the physicians segmentation process can be achieved. Also, improved exactness can be reached for cartilage segmentation if expertise and automation are merged in a meaningful way. |
 |
Assessment of Knee CartilageDegeneration of knee joint cartilage is an important and early indicator of osteoarthritis (OA) which is one of the major socio-economic burdens nowadays. Accurate quantification of the articular cartilage degeneration in an early stage using MR images is a promising approach in diagnosis and therapy for this disease. Particularly, volume and thickness measurement of cartilage tissue has been shown to deliver significant parameters in assessment of pathologies. Here, accurate computer-aided diagnosis tools could improve the clinical routine where image segmentation plays a crucial role. In order to overcome the time-consuming and tedious work of manual segmentation, one tries to automate the segmentation as much as possible. We focus on novel atlas-based segmentation methods for knee cartilage as well as improve today’s clinical routine of manual segmentation methods. In addition, we try to evaluate different methods for the assessment of parameters such as volume and thickness which could allow computer-aided diagnosis of knee cartilage pathologies in an early stage. |
 |
Automatic thrombus segmentation in in vivo micoscopic video sequences under low contrast and highly dynamic conditionsThe Bloodomics EU project aims are to identify the genetic risks factors of coronary heart diseases.One of the most common methods is to study the thrombus formation in the dorsal aorta of mutant Zebrafish larvae. The developing thrombus is imaged in vivo through a microscope/camera setup. The derived time to attachment, growth speed, and time to occlusion permits the characterization of the thrombus formation. However, this step presently remains manual. Our objective is to provide the geneticists in the Wellcome Trust Sanger Institute with an image processing tool to automatically detect and segment the growing thrombus. This will significantly speed up and improve the precision of this current analysis. |
Dissertation
Abstract: Angiographic imaging is a widely used monitoring tool for minimally invasive vascular treatment and pathology access. Especially in deforming abdominal areas, the registration of pre- and intraoperative image data is still an unsolved problem, but important in several aspects. In particular, treatment time and radiation exposure to patient and physician can be significantly reduced with the resulting 2D-3D data fusion. The focus of this work is to provide methods for the registration of 2D vascular images acquired by a stationary C-arm to preoperative 3D angiographic Computed Tomography (CT) volumes, in order to improve the workflow of catheterized liver tumor treatments. Fast and robust vessel segmentation techniques are used to prepare the necessary graph data structures for a successful alignment. Here, we introduce restricted correspondence selection and iterative feature space correction to drive the proposed rigid-body algorithms to global and accurate solutions. Moreover, it is shown for the first time that the assignment of natural constraints on vessel structures allows for a successful recovery of a 3D non-rigid transformation despite a single-view scenario. Based on these results, novel volumetric visualization and roadmapping techniques are developed in order to resolve interventional problems of reduced depth perception, blind navigation, and motion blur.
|
|
M. Groher 2D-3D Registration of Angiographic Images Technische Universtät München, 2008 (bib) |
Publications
Teaching
Finished and Currently active Diploma Theses, SEPs, IDPs I (co-)supervised
Available:- Histology Fold Detection (DA/MA/BA)
This project is part of a larger project that aims at the registration of histology volumes to in-vivo volumes. Before the registration is performed, first a histology volume needs to be reconstructed from histological slices. The reconstruction of histology volumes is performed in three stages first the embedding of a sample in paraffin block; second, the slicing (cutting) the block and imaging the slices; and third, the reconstructing a 3D volume from the 2D slices. One of the difficulties encountered in reconstruction is that the slicing causes deformations shears and tears and folds in the slices, which introduce "inconsistencies" between subsequent slices. The goal of this project is to classify the slices corrupted by such deformations and to detect the tears and folds in the image.
- Fusion of in-vivo and ex-vivo microscopy volumes of mouse brain samples by Eleni Siampli (IDP/Klinisches Anwendungsprojekt)
- Blood Flow Simulation for Angiographic Interventions by Max Hainz (DA/MA/BA 2009/06/15)
- Real-Time Respiratory Motion Tracking: Roadmap Correction for Endovascular Interventions by Selen Atasoy (DA/MA/BA 2007/06/15)
- Rapid prototyping with Open Inventor for Medical Applications by Stephan v. Watzdorf (SEP 2007/01/01)
- Hepatic Vessel Extraction for 2D/3D Registration by Nicolas Padoy (DA/MA/BA 2005/09/15)
- Development and Implementation of a User-Friendly Tool for Analysis of the Patella Cartilage Using Magnetic Resonance Tomography by Lorenz König (IDP )
- Optimization Algorithms for 3D Computer Vision: by Moritz Blume (SEP )
- Implementation of a Fast Covariant Feature Detector by Stefan Hinterstoisser (SEP )
- Segmentation, Centerline Extraction, and Graph Creation of Angiographic Vessels in 2D by Josef Minde and Gefei Fu (SEP )
- 2D / 3D Pose Estimation by Christian Waechter (SEP )
Teaching Assistance
- Lecture 3D Computer Vision (2004SoSe)
- Programmierpraktikum Graphikprogrammierung in C++ (2004WiSe)
- Lecture 3D Computer Vision (2004WiSe)
- Hauptseminar Medical Image Registration (2004WiSe)
- Lecture 3D Computer Vision (2005WiSe)
- Hauptseminar Basics of Medical Image Segmentation and Registration (2005WiSe)
- Lecture Computer Aided Medical Procedures II (2006SoSe)
- Programmierpraktikum Graphikprogrammierung in C++ (2006SoSe)
- Lecture Computer Aided Medical Procedures (2006WiSe)
- Lecture 3D Computer Vision (2006WiSe)
- Hauptseminar Basics of Medical Image Formation, Segmentation and Registration (2006WiSe)
- Lecture Computer Aided Medical Procedures II (2007SoSe)
- Lecture Computer Aided Medical Procedures II (2008SoSe)
- Lecture Computer Aided Medical Procedures II (2009SoSe)
- Lecture Computer Aided Medical Procedures (2009WiSe)
- Lecture 3D Computer Vision II (2010WiSe)
- Lecture Medical Imaging Entrepreneurship (2010WiSe)
People I helped moving to a new flat while at the chair
3x Joerg Traub + one IKEA shopping...?Tobias Sielhorst
Pierre Georgel And I live on the fifth floor without elevator, look how nice he is
Nicolas Padoy
Ben Glocker
Olivier Pauly
It's never good to have the biggest car at a chair...
| UsersForm | |
|---|---|
| Title: | Dr. |
| Firstname: | Martin |
| Middlename: | |
| Lastname: | Groher |
| Picture: |  |
| Birthday: | |
| Nationality: | Germany |
| Languages: | |
| Groups: | Registration/Visualization, Medical Imaging |
| Expertise: | Registration/Visualization, Segmentation, Medical Imaging, Computer Vision |
| Position: | External Collaborator |
| Status: | Alumni |
| Emailbefore: | groher |
| Emailafter: | cs.tum.edu |
| Room: | microDimensions |
| Telephone: | +49 89 289 10932 |
| Alumniactivity: | CEO of microDimensions |
| Defensedate: | 8 April 2008 |
| Thesistitle: | 2D-3D Registration of Angiographic Images |
| Alumnihomepage: | |
| Personalvideo01: | |
| Personalvideotext01: | |
| Personalvideopreview01: | |
| Personalvideo02: | |
| Personalvideotext02: | |
| Personalvideopreview02: | |
